← back to all models ← RevenueBench home
scaledown

scaledown/extract

Mean 0.955 · 32/40 perfect tests · $1.97 total · modalities in: text, image, file · out: text · each card: the prompt → the correct answer (gold) → this model's actual answer

What do the modalities mean?

Modalities in means what you can send this model: text, images, files, video, or audio. Modalities out means what it can send back. Bench tasks feed text extracts, so modalities do not change the score. They are here so you know what this model can handle in real work.

data-crm 5 tests
stage-hygiene-auditPASS 1.00
Plain-English question: How much of the open DS2+ pipeline is missing a substantive why-buys, and is anything missing DS1 timestamps or out of order?
Prompt — what the model saw
Audit stage hygiene on the open pipeline below. Rules: a deal at DS2 or later must have a substantive why-buys (15+ characters, not a placeholder such as tbd, n/a, see notes). A why_buys value of the form LONG(n) means the real text was present but truncated for display; treat it as present and substantive. Every deal should have a DS1 entry timestamp. A deal whose stage entry timestamps are out of order regressed (an earlier-stage timestamp is later than a later-stage timestamp). Report: percent of DS2+ deals non-compliant on why-buys overall and by owner (use the owners table for names), count of deals with no DS1 timestamp, count that regressed, and three process fixes. State definitions before numbers.
cost $0.0488 · 111s · in 120 / out 10,317 tok
✓ noncomp_pct✓ no_ds1_0✓ regressed_0✓ per_owner_breakdown✓ definitions_first✓ three_fixes

✓ Correct Answer (ground truth)

Plain-English answer: 81.5% of the 124 DS2+ deals are missing a substantive why-buys — Alex Franklin 48, Cole Ingram 19, Dana Mercer 18, Bryce Harmon 15, Farid Osman 1 — and every deal has a DS1 timestamp with none regressed.
The answer in one line: n_deals = 156; ds2plus = 124; noncomp_pct = 81.5; bryce_noncomp = 15; no_ds1 = 0; regressed = 0 (+1 more below)
n_deals156
bryce_noncomp15
ds2plus124
no_ds10
noncomp_pct81.5
regressed0
per_owner_noncompAlex Franklin=48 of 61 (78.7%); Cole Ingram=19 of 22 (86.4%); Dana Mercer=18 of 22 (81.8%); Bryce Harmon=15 of 18 (83.3%); Farid Osman=1 of 1 (100%)
graded checksnoncomp_pct · no_ds1_0 · regressed_0 · per_owner_breakdown · definitions_first · three_fixes

Model's actual answer

show the model's full answer
Definitions:
- DS2+ set = stage DS2, DS3, DS4, or DS5.
- why-buys non-compliant = DS2+ deal where why_buys is empty, <15 chars, or placeholder (tbd, n/a, see notes). LONG(n) = compliant per instructions.
- Missing DS1 = blank t_ds1.
- Regressed = any present pair t_ds_i, t_ds_j with i<j and t_ds_i > t_ds_j.

Numbers:
- Total open deals: 156. DS1: 32. DS2+: 124.
- DS2+ with LONG(n): 23. List: Deal-9AAE5F, Deal-6787C2, Deal-584EE5, Deal-FC22A3, Deal-93C8BF, Deal-D0BC96, Deal-8AD4A5, Deal-15D24F, Deal-1E2498, Deal-BE3D9D, Deal-792D44, Deal-E0B692, Deal-ED725A, Deal-530B50, Deal-7599B8, Deal-627646, Deal-885F45, Deal-F67D31, Deal-D7E999, Deal-92D97D, Deal-44EA29, Deal-342E96, Deal-C7F9BF.
- No other DS2+ row has non-empty why_buys.
- Non-compliant = 124-23 = 101. 101/124 = 81.5% non-compliant.

By owner (DS2+ non-compliant / DS2+ total):
- Bryce Harmon: 15/18 = 83.3%. Compliant 3: Deal-6787C2, Deal-FC22A3, Deal-93C8BF.
- Dana Mercer: 18/22 = 81.8%. Compliant 4: Deal-9AAE5F, Deal-584EE5, Deal-44EA29, Deal-7599B8.
- Alex Franklin: 48/61 = 78.7%. Compliant 13: Deal-D0BC96, Deal-885F45, Deal-8AD4A5, Deal-15D24F, Deal-1E2498, Deal-BE3D9D, Deal-792D44, Deal-E0B692, Deal-ED725A, Deal-530B50, Deal-F67D31, Deal-D7E999, Deal-92D97D.
- Cole Ingram: 19/22 = 86.4%. Compliant 3: Deal-C7F9BF, Deal-342E96, Deal-627646.
- Farid Osman: 1/1 = 100%. Deal-499BF6 non-compliant.
- Elena Sinclair: 0 DS2+ deals, no rate.

Missing DS1 timestamp: 0 deals. Every row has t_ds1 present.

Regressed timestamps: 0 deals. No present pair violates t_ds1 <= t_ds2 <= t_ds3 <= t_ds4 <= t_ds5.

Three process fixes:
1. Block DS2 save when why_buys is blank, <15 chars, or placeholder; show character count.
2. Require why-buys backfill for the 101 non-compliant DS2+ deals before forecast lock, oldest close_date first.
3. Add missing-timestamp check: block DS3+ save when intermediate t_ds is blank, e.g. Deal-317E6F at DS3 with no t_ds3; blank gaps hide regression.
owner-resolutionPASS 1.00
Plain-English question: Every open deal has a blank owner name — resolve each one to a real person using the owners table.
Prompt — what the model saw
The deal extract below has an owner name field that is blank on nearly every row and an owner id field that is populated. Using the owners table, resolve each open deal to an owner name. Report: number of deals resolved, deals whose owner id has no match in the owners table (list them), the owner ids that map to archived/deactivated owners (list their names), and the total pipeline amount per resolved owner. Do not guess a name for any unmatched id.
cost $0.0868 · 82s · in 13,256 / out 14,278 tok
✓ resolved_count✓ unmatched_none✓ deactivated_flagged✓ bryce_amount✓ alex_amount✓ no_invented

✓ Correct Answer (ground truth)

Plain-English answer: All 156 deals resolve to six named owners; jake_amount maps to Bryce Harmon ($1,054,144) and justin_amount to Alex Franklin ($624,310).
The answer in one line: jake_amount = 1,054,144; justin_amount = 624,310; resolved = 156
jake_amount1,054,144
justin_amount624,310
resolved156
deactivated
per_ownerBryce Harmon=1,054,144; Alex Franklin=624,310; Dana Mercer=341,195; Cole Ingram=288,161.43; Farid Osman=4,134; Elena Sinclair=2,100
graded checksresolved_count · unmatched_none · deactivated_flagged · bryce_amount · alex_amount · no_invented

Model's actual answer

show the model's full answer
Owner resolution for deals_open.csv using owners.csv:

1. Deals resolved: 156 of 156
   - 119337721 -> Bryce Harmon: 35 deals
   - 84342457 -> Alex Franklin: 67 deals
   - 83155923 -> Dana Mercer: 24 deals
   - 83155924 -> Cole Ingram: 22 deals
   - 716654662 -> Farid Osman: 7 deals
   - 701163055 -> Elena Sinclair: 1 deal
   - 35+67+24+22+7+1 = 156

2. Deals whose owner_id has no match in owners table: 0
   - None. Every owner_id in deals_open.csv exists in owners.csv. No unmatched list to report. No name guessed.

3. Owner ids that map to archived/deactivated owners:
   - owners.csv archived=true: 1520255671 = Gavin Porter, 77260721 = Hugo Lindqvist
   - Open deals mapping to an archived owner: 0. No open deal has owner_id 1520255671 or 77260721.

4. Total pipeline amount per resolved owner (sum of amount):
   - Bryce Harmon (119337721): 1,054,144
   - Alex Franklin (84342457): 624,310
   - Dana Mercer (83155923): 341,195
   - Cole Ingram (83155924): 288,161.43
   - Farid Osman (716654662): 1,249 + 1 + 1 + 1 + 2,880 + 1 + 1 = 4,134
   - Elena Sinclair (701163055): 2,100
   - Check: 1,054,144 + 624,310 + 341,195 + 288,161.43 + 4,134 + 2,100 = 2,314,044.43 total open pipeline
gong-hubspot-join-integrityPASS 1.00
Plain-English question: How many call records point at deal ids that do not exist in the open pipeline?
Prompt — what the model saw
Check the integrity of the call-to-deal mapping below. The gong table lists calls in the last 90 days keyed to HubSpot deal ids; deals_open lists the current open default-pipeline deals. Report: (a) count of gong rows whose deal id has NO match in deals_open (orphans; list a few sample aliases), (b) duplicate conversation keys (rows where calls_90d exceeds distinct_conversation_keys), (c) among the open deals that ARE at stage DS3 or later, the share that have at least one logged call. Give sample aliases for the orphan finding, all taken from the data. Note: gong_owner_id is a Gong user id, not a HubSpot owner id.
cost $0.1519 · 100s · in 52,739 / out 17,594 tok
✓ orphan_count✓ dup_keys_0✓ ds3_coverage✓ sample_ids_present

✓ Correct Answer (ground truth)

Plain-English answer: 30 Gong call rows are orphans keyed to dead deal ids, none are duplicates, and DS3 call coverage is 29.4%.
The answer in one line: orphans = 30; ds3_cov_pct = 29.4; dup = 0
orphans30
ds3_cov_pct29.4
dup0
orphan_aliasesDeal-8FA85D, Deal-8FC3F9, Deal-3B7945, Deal-42B265, Deal-9CCC42, Deal-36EA09
graded checksorphan_count · dup_keys_0 · ds3_coverage · sample_ids_present

Model's actual answer

show the model's full answer
Call-to-deal mapping integrity:

(a) Orphans: 30 of 67 gong rows have a deal id with NO match in deals_open.
Arithmetic: 67 - 30 = 37 matched.
Sample orphan aliases (all from data): Deal-8FA85D (46 calls), Deal-8FC3F9 (24 calls), Deal-3B7945 (21 calls), Deal-42B265 (21 calls), Deal-9CCC42 (17 calls).

(b) Duplicate conversation keys: 0.
Arithmetic: 0 of 67 rows have calls_90d > distinct_conversation_keys; all rows have calls_90d = distinct_conversation_keys.

(c) DS3+ open deals with at least one logged call:
Open DS3+ denominator: 61 DS3 + 14 DS4 + 10 DS5 = 85.
Numerator with a gong match: 25.
Share: 25 / 85 = 29.4%.

Note: gong_owner_id not joined to HubSpot owner_id per instructions.
snowflake-sql-trapped-catalog0.67
Plain-English question: Write one Snowflake query for first-month usage per customer using only the provided, trap-laden catalog.
Prompt — what the model saw
Using ONLY the catalog provided, write one Snowflake SQL query returning, per customer company, for its first calendar month as a customer: unique givers, recognition count, successful redemption count. Read the catalog notes carefully: some tables are stale or unpopulated and must be avoided, and one documented filter (excluding deleted givers) must NOT be applied to historical giving counts. Put a comment above each FROM or JOIN explaining the table choice. Return only fenced SQL.
cost $0.0336 · 72s · in 17,210 / out 2,717 tok
✓ avoids_stale_deals✓ avoids_unpopulated_live✗ uses_cohort_summary✗ succeeded_filter✓ no_giver_deletion_filter✓ returns_sql

✓ Correct Answer (ground truth)

Plain-English answer: A single correct SQL query that uses the right catalog tables and avoids the trap columns — graded on the exact tables and columns.
The answer in one line: use_table = PRODUCTION.PLG.COMPANY_COHORT_SUMMARY
avoid_stalePRODUCTION.HUBSPOT.DEALS (stale)
avoid_unpopulatedV2_LIVE.OBJECTS_DEALS (unpopulated)
forbidden_filterdeleted-giver exclusion must NOT be applied
outputone fenced SELECT with per-FROM/JOIN table-choice comment
required_filtersucceeded redemptions only
use_tablePRODUCTION.PLG.COMPANY_COHORT_SUMMARY
graded checksavoids_stale_deals · avoids_unpopulated_live · uses_cohort_summary · succeeded_filter · no_giver_deletion_filter · returns_sql

Model's actual answer

show the model's full answer
```sql
-- INSUFFICIENT CATALOG TO BUILD REQUESTED QUERY -- DO NOT RUN FOR METRICS
-- Per-customer first-calendar-month unique givers / recognition count / successful redemption count
-- cannot be returned from ONLY this catalog without inventing tables/columns/joins.
-- Missing, explicitly:
-- 1) No recognition/giving events table is listed (no giver ID, no recognition timestamp, no company key).
--    Therefore unique givers and recognition count cannot be sourced. No deleted-givers filter is
--    applied here, per business rule that it must NOT be applied to historical giving counts.
-- 2) No canonical customer-company table with company key + customer start date is listed.
--    PRODUCTION.PLG.COMPANY_COHORT_SUMMARY is self-serve only (SIGNUP_DATE, FIRST_SUB_PAYMENT_DATE,
--    M1_USERS, M1_GIVES, M1_REDEMPTIONS) and is not documented as all customers / first calendar month.
--    PRODUCTION.CHARGEBEE.SUBSCRIPTIONS lists ID, CUSTOMER_ID, CURRENT_TERM_START but no mapping to
--    company key or first calendar month definition.
-- 3) PRODUCTION.DEPRECATED_RECOGNITION.REDEMPTION_RECORDS_V2 is documented as the redemption source
--    with STATE = 'succeeded' only, but no columns for company key or event date are listed, so the
--    company join and first-calendar-month filter cannot be built without invention.
-- Avoided per notes (no FROM/JOIN to them): HUBSPOT_HUB_1973303.V2_LIVE.OBJECTS_DEALS (UNPOPULATED),
-- PRODUCTION.HUBSPOT.DEALS (STALE 2023-03), PRODUCTION.HUBSPOT.GONG_HUBSPOT_MAP_FAST (RETIRED).
-- Arithmetic: none -- inputs missing, so no calculation is shown to avoid invented numbers.
-- Aliases: none given in prompt/catalog -- no deal/company aliases to cite.
SELECT
  'MISSING_DATA' AS status,
  'No giving/recognition table; no all-customer first-month key; no redemption join keys in catalog' AS explanation
;
```
crm-completeness-enrichmentPASS 1.00
Plain-English question: Audit the CRM for missing and invalid fields, and propose the fixes.
Prompt — what the model saw
Audit the CRM extract for completeness and propose fixes. Deals need owner, stage, amount, close date, why-buys; companies need industry, employee count, HQ country; contacts need email, title, persona. Report completeness percent per field. Identify duplicate company clusters (name variants, shared domain) with a survivor per cluster. List invalid emails and domain mismatches. Fill missing company fields only where the enrichment export has a matching row; where CRM and enrichment disagree list both and recommend a source. Never invent a value. End with the 10 fixes with the most pipeline amount at stake.
cost $0.0763 · 95s · in 17,524 / out 10,535 tok
✓ dup_clusters✓ invalid_emails✓ survivor_language✓ completeness_pct✓ no_invent

✓ Correct Answer (ground truth)

Plain-English answer: 9 companies missing employee count, 6 missing HQ country, 4 invalid emails, 1 domain mismatch, 2 duplicate clusters, and 25 enrichment matches.
The answer in one line: n_contacts = 52; n_companies = 34; enrichment_matches = 25; invalid_email_count = 4; n_dup_clusters = 2; domain_mismatch_count = 1 (+4 more below)
n_contacts52
domain_mismatch_count1
enrichment_matches25
invalid_email_count4
n_companies34
n_dup_clusters2
company_missingindustry=0; employee_count=9; hq_country=6
domain_mismatchesCT-0011
duplicate_clusters['C-0A092931', 'C-0A092932'], ['C-0A092933', 'C-0A092934']
invalid_emailsCT-0010, CT-0080, CT-0081, CT-0192
graded checksdup_clusters · invalid_emails · survivor_language · completeness_pct · no_invent

Model's actual answer

show the model's full answer
Deals audit: cannot be performed. No deals file was provided. Completeness for owner, stage, amount, close date, why-buys is unknown. Pipeline amount at stake cannot be computed for any fix.

COMPANY COMPLETENESS (n=34)

- company_alias: 34/34 = 100.0%
- domain: 34/34 = 100.0%
- industry: 34/34 = 100.0%
- employee_count: 25/34 = 73.5%. Missing 9: C-EC3025, C-96039F, C-44EA29, C-D04904, C-B23205, C-60C75F, C-7BBDFA, C-50D386, C-93C8BF
- hq_country: 28/34 = 82.4%. Missing 6: C-2D1F1B, C-D73B89, C-44EA29, C-D04904, C-2C60E5, C-EE9FFB

Note: industry is 100% filled but not standardized. Variants present: tech, Tech with trailing space, Technology, Computer Software equivalent, Healthcare vs health care, Retail, Manufacturing, Finance, SaaS. hq_country variants present: US, USA, United States, Canada, UK.

CONTACT COMPLETENESS (n=52)

- email non-blank: 52/52 = 100.0%
- email valid (local-part + @ + domain with dot): 48/52 = 92.3%. Invalid 4, see below.
- title filled: 39/52 = 75.0%. Missing 13: CT-0000, CT-0022, CT-0072, CT-0080, CT-0081, CT-0092, CT-0120, CT-0121, CT-0122, CT-0132, CT-0141, CT-0162, CT-0170
- persona filled: 37/52 = 71.2%. Missing 15: CT-0000, CT-0022, CT-0041, CT-0060, CT-0070, CT-0081, CT-0082, CT-0092, CT-0110, CT-0132, CT-0162, CT-0171, CT-0172, CT-0180, CT-0181
- Missing both title and persona (5): CT-0000, CT-0022, CT-0092, CT-0132, CT-0162

Coverage gap: 14 companies have zero contacts in contacts.csv: C-2C60E5, C-B97B4E, C-2D7423, C-7BBDFA, C-50D386, C-BA969B, C-332637, C-93C8BF, C-EE9FFB, C-C9BB20, C-0A092931, C-0A092932, C-0A092933, C-0A092934

DUPLICATE COMPANY CLUSTERS

Cluster 1 - shared domain acme-corp.com:
C-0A092931 (Technology, 500, US) + C-0A092932 (tech, 510, USA)
Survivor: C-0A092931. Reason: standardized casing Technology and ISO country US; employee_count conflicts 500 vs 510, requires human validation before merge. Merge C-0A092932 into C-0A092931.

Cluster 2 - shared domain globex.io:
C-0A092933 (SaaS, 200, US) + C-0A092934 (Technology, 200, US)
Survivor: C-0A092934. Reason: provisional only; industry conflicts SaaS vs Technology with identical count/country. Requires human validation of correct industry before merge. No enrichment row for globex.io to resolve.

No other shared domains in companies.csv.

INVALID EMAILS (4)

- CT-0010 (C-66D1FC): user0@
- CT-0080 (C-92D97D): user0@
- CT-0081 (C-92D97D): user1@
- CT-0192 (C-425E2A): user2@
All have missing domain after @. Fix: re-collect, do not guess.

DOMAIN MISMATCHES (1)

- CT-0011 (C-66D1FC): user1@other-domain.com vs company domain 66d1fc.com
Fix: verify if contact belongs to C-66D1FC or move to correct company; do not alter domain by guessing.

ENRICHMENT FILLS - missing company fields with matching zoominfo_enrichment.csv row

employee_count fills (8):
- C-EC3025: fill 400 (CRM blank vs zi 400)
- C-96039F: fill 400 (blank vs 400)
- C-44EA29: fill 400 (blank vs 400)
- C-D04904: fill 400 (blank vs 400)
- C-B23205: fill 400 (blank vs 400)
- C-60C75F: fill 400 (blank vs 400)
- C-7BBDFA: fill 400 (blank vs 400)
- C-50D386: fill 400 (blank vs 400)

Cannot fill:
- C-93C8BF employee_count: no enrichment row for 93c8bf.com. Data missing, say so explicitly.
- hq_country for C-2D1F1B, C-D73B89, C-44EA29, C-D04904, C-2C60E5: enrichment rows exist but zi_hq_country is also blank. Cannot fill.
- C-EE9FFB hq_country: no enrichment row for ee9ffb.com. Cannot fill.
- C-BA969B, C-332637, C-C9BB20, C-0A092931, C-0A092932, C-0A092933, C-0A092934: no enrichment rows for ba969b.com, 332637.com, 93c8bf.com, ee9ffb.com, c9bb20.com, acme-corp.com, globex.io. No fill or comparison possible.

CRM vs ENRICHMENT DISAGREEMENTS (both present, values differ)

Industry - CRM vs zi_industry:
- C-66D1FC: CRM tech vs ZI Computer Software
- C-EC3025: CRM Technology vs ZI Computer Software
- C-44EA29: CRM tech vs ZI Computer Software
- C-92D97D: CRM Technology vs ZI Computer Software
- C-D04904: CRM Technology vs ZI Computer Software
- C-77A95A: CRM Technology vs ZI Computer Software
- C-AA8DDA: CRM Technology vs ZI Computer Software
- C-B25F40: CRM Technology vs ZI Computer Software
- C-60C75F: CRM tech vs ZI Computer Software
- C-425E2A: CRM Tech [trailing space] vs ZI Computer Software
Recommendation: standardize taxonomy first, then accept ZI Computer Software for these 10 if Computer Software is the standard; otherwise keep CRM and document mapping. Do not invent; requires taxonomy decision + human review.
No disagreement where CRM already equals ZI case-insensitively: C-2D1F1B, C-C6FE92, C-950043, C-D73B89, C-96039F, C-31ED2A, C-B23205, C-E51FB7, C-63A874, C-D0662E, C-2C60E5, C-B97B4E, C-2D7423, C-7BBDFA, C-50D386.

hq_country - after normalizing US=USA=United States:
No true disagreements. All matched rows are equivalent: e.g. C-66D1FC CRM US vs ZI United States, C-E51FB7 CRM USA vs ZI United States. Recommendation: standardize CRM to ISO codes: US, Canada, UK. Source: normalization rule, not new data.

employee_count - no filled-vs-filled conflicts. All CRM-filled counts match ZI exactly where both exist.

10 FIXES WITH MOST PIPELINE AMOUNT AT STAKE

Cannot rank by pipeline amount. No deals file with amount was provided. Never inventing amounts. Below are the 10 highest-coverage completeness fixes, unranked by dollars:

1. Deduplicate acme-corp.com: merge C-0A092932 into C-0A092931 after resolving 500 vs 510 employees
2. Deduplicate globex.io: resolve C-0A092933 SaaS vs C-0A092934 Technology, then merge
3. Fix 4 invalid emails: CT-0010, CT-0080, CT-0081, CT-0192
4. Resolve domain mismatch CT-0011
5. Fill employee_count from enrichment for 8 companies: C-EC3025, C-96039F, C-44EA29, C-D04904, C-B23205, C-60C75F, C-7BBDFA, C-50D386 (all 400)
6. Standardize industry for 10 companies listed above (tech/Technology vs Computer Software) + fix Tech trailing space C-425E2A, C-BA969B, C-C9BB20 + Healthcare vs health care
7. Standardize hq_country to US/Canada/UK (affects 12 rows with USA/United States variants)
8. Collect missing title for 13 contacts and persona for 15 contacts, priority 5 missing both: CT-0000, CT-0022, CT-0092, CT-0132, CT-0162
9. Add contacts for 14 zero-contact companies listed above; obtain hq_country for 6 missing and employee_count for C-93C8BF by direct collection since enrichment cannot fill
10. Provide deals extract with owner, stage, amount, close date, why-buys before any pipeline-weighted prioritization
deal-intelligence 5 tests
closed-lost-classificationPASS 1.00
Plain-English question: Why did we lose the last six months of deals — one primary category per deal, and whose side is the reason on?
Prompt — what the model saw
Classify every deal lost in the last 6 months below into one primary category: pricing, competitor, no decision, timing, product gap, champion left, or other. Also assign a side (Bonusly, buyer, unknown). Then summarize: category counts, the side split, the number of deals where the structured closed_lost_tag clearly disagrees with the free-text reason, and the two patterns most worth acting on. Base everything only on the tag and free-text provided.
cost $0.1079 · 148s · in 27,458 / out 15,066 tok
✓ total_90✓ competitor_top✓ category_counts_present✓ side_split✓ two_patterns

✓ Correct Answer (ground truth)

Plain-English answer: Every closed-lost deal gets exactly one category (pricing, competitor, no decision, timing, product gap, champion left, other) plus a side, per the computed classification.
The answer in one line: total_lost_6mo = 90; top_reason = competitor (26)
total_lost_6mo90
categoriespricing, competitor, no decision, timing, product gap, champion left, other
patternstwo most actionable, tag-vs-text disagreements counted
sideBonusly / buyer / unknown per deal
top_reasoncompetitor (26)
graded checkstotal_90 · competitor_top · category_counts_present · side_split · two_patterns

Model's actual answer

show the model's full answer
Rules used, only from tag + reason text:
competitor = text names/chooses/stays with another vendor or RFP elimination after evaluation. pricing = budget/price/cost/approval/cuts. timing = explicit pause/on hold/reconnect to a future date with interest retained. no decision = deprioritized/manual build/internal/scope loss/leadership pause with no date. product gap = missing feature/customization/UI/geo/integration explicitly the driver. champion left = buyer contact left. other = MIA/unresponsive/no contact/spam/thin brush-off with no driver. Side: pricing/competitor/timing/no decision = buyer; product gap = Bonusly; other/champion left with no info = unknown.

Per-deal (alias: category / side):
Deal-DB0AAC: timing / buyer - pause, reconnect timeline
Deal-F7F635: competitor / buyer - evaluating options, another direction
Deal-AC944F: other / unknown - unresponsive
Deal-214060: other / unknown - unresponsive
Deal-91A056: timing / buyer - reconnect early 2027
Deal-29326C: timing / buyer - Timing
Deal-5DB9B0: other / unknown - Spam, ICP mismatch
Deal-831B7B: timing / buyer - circle back new year
Deal-F97C37: competitor / buyer - other vendor more diversified
Deal-13E9CF: no decision / buyer - R&R deprioritized, not budget
Deal-39E25C: timing / buyer - reconnect next year
Deal-7ED004: pricing / buyer - no budget approval
Deal-21B045: other / unknown - MIA
Deal-B3ABED: timing / buyer - revisit Q2 next year for 2028 budget
Deal-422BA6: competitor / buyer - chose vendor, ADP TotalSource partner
Deal-ED9AE7: timing / buyer - Timing, budget, authority mixed, timing first
Deal-988493: other / unknown - mia
Deal-381C8C: other / unknown - not moving forward, no context
Deal-F308CA: other / unknown - no contact since intro, ignored outreach
Deal-F1E8A6: other / unknown - not moving forward, no reason
Deal-B6AC09: timing / buyer - revisiting 2027
Deal-70F704: other / unknown - anniversary-only scope + MIA
Deal-E6E80A: timing / buyer - pushed early 2027
Deal-B038F0: timing / buyer - pushed early 2027
Deal-4664E1: other / unknown - no contact after intro
Deal-175756: timing / buyer - hold until 2027, other priorities
Deal-E74A73: no decision / buyer - test manually before investing
Deal-DDAB52: competitor / buyer - Rippl more at same cost
Deal-ACE061: competitor / buyer - feel went with HeyTaco
Deal-BB78F3: timing / buyer - interested end goal, other items first
Deal-D48E0B: other / unknown - MIA
Deal-15DA99: timing / buyer - early 2027
Deal-F4AF5D: timing / buyer - early next year
Deal-79B7A1: timing / buyer - Timing
Deal-583ADB: other / unknown - MIA
Deal-8E27DA: no decision / buyer - swag only, did not want R&R
Deal-2D2F8D: other / unknown - different direction, no vendor named
Deal-E0441F: other / unknown - stale inherited, no contact
Deal-7CB44D: other / unknown - no contact since demo, ignored outreach
Deal-0F96AA: competitor / buyer - RFP, cut before finalist demo
Deal-1BCA50: competitor / buyer - budget + gift cards, stakeholder down path with vendor
Deal-7CC678: other / unknown - Nothing specific provided
Deal-FAC17C: pricing / buyer - no final approval Exec IT Director
Deal-242273: product gap / Bonusly - points currency + onsite spend differentiator
Deal-50E5D8: no decision / buyer - leadership pause
Deal-A2C349: competitor / buyer - stick with Awardco + surveying
Deal-9F176A: timing / buyer - pause to end of year
Deal-7B2236: pricing / buyer - budget + simpler cheaper
Deal-AFA56C: other / unknown - unresponsive
Deal-C7156E: competitor / buyer - selected another vendor
Deal-C33D91: pricing / buyer - budget cuts, no approval
Deal-9048EB: product gap / Bonusly - bad fit, desired setup, multiple gaps
Deal-5E64CE: competitor / buyer - locked in Nectar to Oct 2027
Deal-8A0992: competitor / buyer - Canadian provider aligns
Deal-D0C698: competitor / buyer - wants Kudos again
Deal-69CF3D: timing / buyer - On Hold
Deal-ECBF89: timing / buyer - On Hold
Deal-3618CC: product gap / Bonusly - Wanted Surveys
Deal-EECC02: competitor / buyer - went another direction
Deal-5AD03E: product gap / Bonusly - wanted defined budget access
Deal-D1A623: timing / buyer - timing
Deal-413C56: no decision / buyer - back to school priority, CEO not ready
Deal-47F1A1: competitor / buyer - staying with WorkTango 12 mo
Deal-BF2A98: competitor / buyer - deployed HiThrive
Deal-2A292B: no decision / buyer - build simple internally
Deal-D1AABF: other / unknown - No response
Deal-FEDBCB: timing / buyer - reconnect end of year
Deal-1E7DA9: competitor / buyer - selected another platform
Deal-2BBA21: other / unknown - no contact since intro, ignored nudges
Deal-286F9C: competitor / buyer - another platform, not good fit
Deal-7FBAC6: no decision / buyer - leadership pause again
Deal-369281: competitor / buyer - went with Paylocity
Deal-386F6E: other / unknown - No response
Deal-9FCD0D: competitor / buyer - Canadian company, CEO preference
Deal-55867E: other / unknown - will not move forward, no date/vendor/reason
Deal-DAFB82: pricing / buyer - priorities, not budgeted until 2028
Deal-2FEDDB: timing / buyer - unsure on timing
Deal-64B19A: competitor / buyer - likely stayed Motivosity
Deal-3F86A0: other / unknown - unresponsive
Deal-096750: other / unknown - no contact after intro
Deal-F325A5: no decision / buyer - layoffs/leadership change, not priority
Deal-ABD14C: no decision / buyer - not interested in signing
Deal-79E61A: other / unknown - Unresponsive
Deal-8A119B: pricing / buyer - did not get approval
Deal-AE7C4E: other / unknown - Unresponsive
Deal-DAB4F1: other / unknown - Unresponsive
Deal-B4B50F: other / unknown - Unresponsive
Deal-981AD4: product gap / Bonusly - UI fit + not UK focused
Deal-DC77FE: product gap / Bonusly - price not factor, more customization points-as-dollars
Deal-5885B9: other / unknown - MIA

Arithmetic, n=90:
timing 21 + competitor 20 + other 28 + no decision 9 + pricing 6 + product gap 6 + champion left 0 = 90.
21+20=41, +28=69, +9=78, +6=84, +6=90, +0=90.

Side split:
buyer = 21 timing + 20 competitor + 9 no decision + 6 pricing = 56. 56/90 = 62.2%.
Bonusly = 6 product gap. 6/90 = 6.7%.
unknown = 28 other. 28/90 = 31.1%.
56+6+28 = 90.

Tag-vs-text clear disagreements: 10 of 90 (11.1%):
Deal-381C8C, Deal-F1E8A6, Deal-7CC678 - Competitor tag, text gives no vendor or reason.
Deal-2D2F8D excluded as borderline; counted: Deal-70F704 - Lost DM tag, text is narrow scope + MIA, no DM.
Deal-3618CC - Lost DM tag, text Wanted Surveys.
Deal-8E27DA - Feature Request tag, text is scope loss to swag-only.
Deal-5AD03E - Competitor tag, text is budget-access feature, no vendor.
Deal-9048EB - MIA tag, text states bad fit + multiple feature gaps.
Deal-5E64CE - Doing nothing tag, text is Nectar lock-in to Oct 2027.
Deal-55867E - Timing tag, text gives no timeframe.
Data missing to judge further: many Competitor rows name no vendor (Deal-F7F635, Deal-EECC02, Deal-1E7DA9); many MIA rows are one word.

Two patterns to act on:
1. Ghosting is the largest bucket: 28/90 other/unknown (31.1%). Repeat text: no contact since intro, ignored outreach from rep + ADR (Deal-F308CA, Deal-4664E1, Deal-7CB44D, Deal-2BBA21, Deal-096750), plus bare unresponsive/MIA (Deal-AC944F, Deal-214060, Deal-AFA56C, Deal-D1AABF, Deal-386F6E). Act on qualification and early follow-up, not loss reasons.
2. Competitor + gap cluster decides evaluative deals: 20 competitor + 6 product gap = 26/90 (28.9%). Named drivers only in this file: ADP integration/partnership (Deal-422BA6), surveys/Awardco (Deal-A2C349, Deal-3618CC), points-currency + onsite spend (Deal-242273), customization points-as-dollars (Deal-DC77FE), diversified offerings (Deal-F97C37), budget access (Deal-5AD03E), incumbents Nectar/Kudos/WorkTango/Motivosity/Paylocity/HiThrive (Deal-5E64CE, Deal-D0C698, Deal-47F1A1, Deal-64B19A, Deal-369281, Deal-BF2A98). Separately, 21 timing deferrals to 2027/2028 risk rotting without a dated nurture queue.
pipeline-tieringPASS 1.00
Plain-English question: Score all 156 open deals into exactly one of LOCK / ACTION / BUILD / REVIVE / WATCH / RISKY.
Prompt — what the model saw
Score the open pipeline below on these signals: forecast category, stage, meetings_30d, contact count, and engagement recency. Assign exactly one tier per deal: LOCK, ACTION, BUILD, REVIVE, WATCH, or RISKY (RISKY = the forecast category disagrees with the engagement evidence). Never tier a deal LOCK if it has zero meetings_30d. Do NOT list every deal. Return ONLY a compact JSON object with exactly these keys: - "tier_counts": object mapping each tier to the number of deals in it (must sum to the total deal count), - "tier_examples": object mapping each tier to up to 3 example deal aliases from the data, - "risky_deals": array of the deal aliases you tiered RISKY, - "lock_violations": number of deals tiered LOCK that have zero meetings_30d (should be 0), - "pipeline_shape": one short paragraph on the overall pipeline shape. Note: inbound_emails_30d is 0 for every row due to a data defect, so treat meetings_30d as the inbound signal.
cost $0.0260 · 64s · in 57 / out 4,816 tok
✓ json_returned✓ tier_vocabulary✓ tier_counts_sum✓ risky_deals_listed✓ no_lock_violation_claimed

✓ Correct Answer (ground truth)

Plain-English answer: All 156 open deals tiered exactly once across the six tiers using forecast category, stage, meetings, contacts, and recency.
The answer in one line: total = 156
total156
graded checksjson_returned · tier_vocabulary · tier_counts_sum · risky_deals_listed · no_lock_violation_claimed

Model's actual answer

show the model's full answer
{"tier_counts": {"LOCK": 3, "ACTION": 18, "BUILD": 45, "REVIVE": 35, "WATCH": 47, "RISKY": 8}, "tier_examples": {"LOCK": ["Deal-C26D20", "Deal-D348E1", "Deal-403845"], "ACTION": ["Deal-25F752", "Deal-C6FE92", "Deal-944310"], "BUILD": ["Deal-D73B89", "Deal-CA7DC0", "Deal-927338"], "REVIVE": ["Deal-2D1F1B", "Deal-950043", "Deal-278DEC"], "WATCH": ["Deal-6787C2", "Deal-E53952", "Deal-5408B0"], "RISKY": ["Deal-547B2B", "Deal-B7EBD1", "Deal-A5E80A"]}, "risky_deals": ["Deal-547B2B", "Deal-B7EBD1", "Deal-A2B47C", "Deal-2465CE", "Deal-584EE5", "Deal-FD9F4E", "Deal-A5E80A", "Deal-499BF6"], "lock_violations": 0, "pipeline_shape": "Early-heavy pipeline: 3+8+18+45+35+47=156 deals; only 3 DS5 COMMIT deals have meetings_30d>0 for LOCK, 8 COMMITs mismatch engagement for RISKY, while the bulk sits in DS1/DS2/DS3 PIPELINE with 55 deals showing meetings_30d>0 and ~101 with zero, leaving most value in BUILD/WATCH with a large stale REVIVE tail."}
call-transcript-extractionPASS 1.00
Plain-English question: Extract the CRM write-back fields from each call transcript as JSON.
Prompt — what the model saw
For each transcript, extract CRM write-back fields as JSON: why-buys (prospect statements only), pain points, stakeholders from the speaker list, budget signal (prospect-stated or null), timeline signal, competitor mentioned (only if the prospect raised it), next step (only if explicitly agreed), objections, confidence. Never fill a field from what the rep said or hoped.
cost $0.0149 · 76s · in 1,786 / out 2,275 tok
✓ json_emitted✓ budget_signal✓ null_discipline✓ stakeholders✓ competitor_prospect_only

✓ Correct Answer (ground truth)

Plain-English answer: Per transcript: prospect-only why-buys, pain points, stakeholders, budget and timeline signals, and competitors — e.g. TX-001: '$40k earmarked', live before open enrollment.
The answer in one line: rep = Alex Franklin
allowed_newTX-001, TX-002, TX-003, TX-004, TX-005, TX-006, Achievers, Bucketlist, Nectar
per_transcript{"TX-001": {"why_buys": ["automating anniversary and birthday awards"], "pain_points": ["HR team of three cannot keep up with it manually", "track everything in a spreadsheet, and people slip through
repAlex Franklin
rep_sourced_nulls{"TX-003": ["budget_signal \u2014 only the rep mentioned pricing/budget"], "TX-004": ["next_step \u2014 rep proposed, prospect said 'no promises'"], "TX-006": ["budget_signal \u2014 rep decoy, prospec
graded checksjson_emitted · budget_signal · null_discipline · stakeholders · competitor_prospect_only

Model's actual answer

show the model's full answer
[
  {
    "transcript_id": "TX-001",
    "deal_alias": "Deal-CFE7F4",
    "why_buys": ["automating anniversary and birthday awards"],
    "pain_points": ["HR team of three cannot keep up with it manually", "track everything in a spreadsheet, and people slip through the cracks"],
    "stakeholders": ["Prospect (VP People)", "Prospect (HR Admin)"],
    "budget_signal": "We have about $40k earmarked for engagement tools this fiscal year.",
    "timeline_signal": "Ideally we would have this live before open enrollment in November.",
    "competitor_mentioned": "Achievers",
    "next_step": "security review on September 12",
    "objections": ["we need SSO and audit logs for IT to sign off"],
    "confidence": "high"
  },
  {
    "transcript_id": "TX-002",
    "deal_alias": "Deal-70BB30",
    "why_buys": ["tie recognition to retention for our hourly workforce"],
    "pain_points": ["regretted turnover there is over 30%", "Integration with Workday has to be rock solid"],
    "stakeholders": ["Prospect (Head of Total Rewards)", "Prospect (CFO)"],
    "budget_signal": "Finance has approved a $25k pilot budget for this quarter.",
    "timeline_signal": "We want a decision by end of September.",
    "competitor_mentioned": null,
    "next_step": "send the pilot agreement and we'll route it to legal this week",
    "objections": ["Integration with Workday has to be rock solid — that's my one condition"],
    "confidence": "high"
  },
  {
    "transcript_id": "TX-003",
    "deal_alias": "Deal-530B50",
    "why_buys": ["make recognition visible across our 12 retail locations"],
    "pain_points": ["Store managers have zero budget autonomy for on-the-spot recognition today"],
    "stakeholders": ["Prospect (People Ops Manager)"],
    "budget_signal": null,
    "timeline_signal": "Honestly there's no rush on our side until Q1.",
    "competitor_mentioned": "Bucketlist",
    "next_step": "schedule a call with our CEO — I'll send two times",
    "objections": ["The CEO has to be sold first — she decides anything people-related"],
    "confidence": "medium"
  },
  {
    "transcript_id": "TX-004",
    "deal_alias": "Deal-180D02",
    "why_buys": ["consolidate three separate recognition tools into one"],
    "pain_points": ["We're paying for three tools and none of them talk to our HRIS", "procurement cycle runs six to eight weeks minimum", "security review took three months for our last vendor"],
    "stakeholders": ["Prospect (VP People)", "Prospect (IT Security Lead)"],
    "budget_signal": "If it's under $15k annually, I can approve it without going to the board.",
    "timeline_signal": "procurement cycle runs six to eight weeks minimum",
    "competitor_mentioned": null,
    "next_step": null,
    "objections": ["The security review took three months for our last vendor — that's my hesitation"],
    "confidence": "low"
  },
  {
    "transcript_id": "TX-005",
    "deal_alias": "Deal-F8767A",
    "why_buys": ["automate service milestones", "give us analytics on recognition equity across departments"],
    "pain_points": ["Our night-shift teams feel invisible — their engagement scores run 20 points lower", "Our exec team is skeptical after a failed rollout two years ago"],
    "stakeholders": ["Prospect (HR Director)", "Prospect (People Ops Coordinator)"],
    "budget_signal": "We have $12k approved under our engagement line.",
    "timeline_signal": "We need this running before our January all-hands.",
    "competitor_mentioned": "Nectar",
    "next_step": "come present to our exec team on October 2",
    "objections": ["We're mid-pilot with Nectar right now, so you'd need to beat that experience", "Our exec team is skeptical after a failed rollout two years ago"],
    "confidence": "medium"
  },
  {
    "transcript_id": "TX-006",
    "deal_alias": "Deal-EE195F",
    "why_buys": ["cut the admin time on service awards"],
    "pain_points": ["I personally spend five hours a month ordering and shipping plaques", "Budget isn't the issue — time is"],
    "stakeholders": ["Prospect (HR Manager)"],
    "budget_signal": null,
    "timeline_signal": "Our fiscal year resets in February, so a Q1 start is realistic.",
    "competitor_mentioned": null,
    "next_step": "send the one-page overview and I'll forward it to our COO this week",
    "objections": ["our COO usually prefers building things in-house", "we're comparing this against just doing it internally"],
    "confidence": "medium"
  }
]
next-to-close0.75
Plain-English question: Which 3 deals are closest to signature right now?
Prompt — what the model saw
Which 3 deals are closest to signature right now? Use the CRM data and the Slack thread; Slack often has the real status before the CRM does. For each: deal, amount, why it is close, what is left. Under 250 words.
cost $0.0308 · 67s · in 20,685 / out 1,152 tok
✓ exactly_three✗ top3_named✓ slack_first✓ blocked_excluded

✓ Correct Answer (ground truth)

Plain-English answer: Deal-547B2B ($11,200), Deal-B7EBD1 ($9,000), and Deal-403845 ($9,000) — all DS5 COMMIT deals closing September 10-11, with what is left on each.
blocked_excludeddeal_alias=Deal-2465CE; reason=champion left + procurement freeze (Slack #sales-sparring 2026-09-04)
exactly_three1
ranking_ruleSlack signature-imminent deal ranks first; remaining ranked by stage (DS5>DS4), forecast (COMMIT>BEST_CASE>PIPELINE), close_date asc, amount desc
top3rank=1; deal_alias=Deal-547B2B; amount=11200; stage=DS5; forecast_category=COMMIT; close_date=2026-09-11 | rank=2; deal_alias=Deal-B7EBD1; amount=9000; stage=DS5; forecast_category=COMMIT; close_date=2026-09-10 | rank=3; deal_alias=Deal-403845; amount=9000; stage=DS5; forecast_category=COMMIT; close_date=2026-09-11
graded checksexactly_three · top3_named · slack_first · blocked_excluded

Model's actual answer

show the model's full answer
1. Deal-547B2B — $11,200
Why close: DS5/COMMIT, close 2026-09-11. Slack 2026-09-04: redlines clean, signing page out, VP People signing tomorrow. Signature-imminent.
Left: signature only.

2. Deal-403845 — $9,000
Why close: DS5/COMMIT, close 2026-09-11. Slack 2026-09-04: order form with their finance team, moving fine.
Left: finance approval + signature.

3. Deal-A2B47C — $6,360
Why close: DS5/COMMIT, close 2026-09-11. Slack 2026-09-04: still warm, normal legal-review pace.
Left: complete legal review + signature.

Excluded: Deal-2465CE ($5,400, DS5/COMMIT) is blocked per Slack — champion left, procurement froze new vendors, moving to Q4.

Arithmetic: 11,200 + 9,000 + 6,360 = 26,560
product-gap-detectionPASS 1.00
Plain-English question: Which prospect complaints are true product gaps versus rollout or enablement issues?
Prompt — what the model saw
Surface true product gaps raised by prospects in active deals. For each candidate: quote the prospect line, classify as real gap, plan gate, or rollout/enablement issue using the product docs excerpt, and name the deal and amount. Only real gaps go in the summary. Rep language does not count as prospect voice.
cost $0.0102 · 71s · in 714 / out 1,486 tok
✓ real_gaps✓ plan_gate_classified✓ enablement_classified✓ gap_summary

✓ Correct Answer (ground truth)

Plain-English answer: Two real gaps (SCIM provisioning, ADP Workforce Now integration) separated from plan gates and enablement issues, each with the prospect quote and deal.
allowed_newTG-001, TG-002, TG-003, TG-004, TG-005, SCIM user provisioning, ADP Workforce Now integration, Custom report builder
enablement_issuestranscript_id=TG-004; deal_alias=Deal-84DBA6; amount=16000; feature=Slack integration recognition adoption; quote=We turned on the Slack integration in July, but half our managers still haven't given a single recognition — nobody ever trained them on it.; why_enablement=Slack integration exists on all plans; managers were never trained
excluded_rep_voicetranscript_id=TG-005; line=Full transparency — we don't have a native mobile app for hourly workers yet, though it's on the roadmap.; reason=rep voice, not prospect-raised
plan_gatestranscript_id=TG-003; deal_alias=Deal-CFE7F4; amount=32000; feature=Custom report builder; tier_required=Enterprise; quote=I tried to build a custom report combining recognition frequency with turnover and couldn't — is that possible on our current plan?
real_gapstranscript_id=TG-001; deal_alias=Deal-EC3025; amount=62000; feature=SCIM user provisioning; quote=We need SCIM user provisioning — our security team will not approve any tool that requires manual account management.; why_real=not listed in product docs at any tier | transcript_id=TG-002; deal_alias=Deal-D0D6B5; amount=23800; feature=ADP Workforce Now integration; quote=Our payroll runs on ADP Workforce Now and I don't see ADP anywhere in your integration list — that's a dealbreaker for us.; why_real=supported HRIS list is Workday/BambooHR/Gusto/Rippling only
graded checksreal_gaps · plan_gate_classified · enablement_classified · gap_summary

Model's actual answer

show the model's full answer
Candidates (prospect voice only):

1. Deal-EC3025 — Amount: not provided in data (missing)
Prospect line: "We need SCIM user provisioning — our security team will not approve any tool that requires manual account management."
Classification: real gap
Reason: product_docs.md states "SCIM user provisioning and ADP Workforce Now integrations are NOT currently listed as supported capabilities."

2. Deal-D0D6B5 — Amount: not provided in data (missing)
Prospect line: "Our payroll runs on ADP Workforce Now and I don't see ADP anywhere in your integration list — that's a dealbreaker for us."
Classification: real gap
Reason: product_docs.md lists HRIS as "Workday, BambooHR, Gusto, Rippling (Pro and above)" and states ADP Workforce Now is NOT currently listed as supported.

3. Deal-CFE7F4 — Amount: not provided in data (missing)
Prospect line: "I tried to build a custom report combining recognition frequency with turnover and couldn't — is that possible on our current plan?"
Classification: plan gate
Reason: product_docs.md lists "Custom report builder" as Enterprise yes only (Core —, Pro —).

4. Deal-84DBA6 — Amount: not provided in data (missing)
Prospect line: "We turned on the Slack integration in July, but half our managers still haven't given a single recognition — nobody ever trained them on it."
Classification: rollout/enablement issue
Reason: product_docs.md lists "Slack and Microsoft Teams integration" as yes on all plans; issue described is training/adoption, not missing capability.

5. Deal-36C33F — Excluded
No prospect-raised gap. Mobile app gap was raised by Alex Franklin ("Full transparency — we don't have a native mobile app for hourly workers yet, though it's on the roadmap."), and prospect replied "Good to know. The web version should be fine for our office staff for now." Rep language does not count as prospect voice.

Arithmetic: 5 transcripts reviewed = 2 real gaps + 1 plan gate + 1 rollout/enablement + 1 excluded (rep-originated). Total dollar value of gaps: cannot be calculated — deal amounts missing from data.

Summary — real gaps only:
- Deal-EC3025 — Amount: missing — "We need SCIM user provisioning — our security team will not approve any tool that requires manual account management."
- Deal-D0D6B5 — Amount: missing — "Our payroll runs on ADP Workforce Now and I don't see ADP anywhere in your integration list — that's a dealbreaker for us."
rep-performance 5 tests
stale-pipeline-by-rep0.83
Plain-English question: Which open deals have had no email, call, or meeting in the last 7 days?
Prompt — what the model saw
The snapshot date is 2026-09-05. Using the open deals and the engagements-by-deal table, list every open deal with no logged email, call, or meeting in the last 7 days. Compute recency from the engagements table's last_email/last_call/last_meeting fields, NOT from any date field on the deal (the deal's last_contacted_field is unreliable). For each stale deal give: deal alias, owner name, stage, amount, days since last contact. Group by owner, order by amount descending within each owner. Then state, per owner, how many stale deals they carry and the total stale amount. (Do not write outreach text.)
cost $0.2369 · 139s · in 92,232 / out 26,622 tok
✓ stale_recall_ge_80✓ grouped_by_owner✓ bryce_top_amount✓ cole_stale_amt✓ dana_stale_amt✗ stale_count

✓ Correct Answer (ground truth)

Plain-English answer: 65 open deals are stale; the largest is Deal-2D1F1B at $240,000, with Bryce Harmon carrying the most stale dollars at $626,243.
The answer in one line: jake_amt = 626,243; jenn_amt = 261,645; kevin_amt = 252,905.03; top_amount = 240,000; stale_count = 65; top_alias = Deal-2D1F1B
jake_amt626,243
jenn_amt261,645
kevin_amt252,905.03
stale_count65
top_amount240,000
top_aliasDeal-2D1F1B
graded checksstale_recall_ge_80 · grouped_by_owner · bryce_top_amount · cole_stale_amt · dana_stale_amt · stale_count

Model's actual answer

show the model's full answer
Snapshot: 2026-09-05.
Rule used: last_contact = max(last_email, last_call, last_meeting) from engagements_by_deal_90d.csv. days_since = 2026-09-05 minus last_contact. Stale = days_since > 7, i.e. last_contact on or before 2026-08-28. Deal last_contacted_field ignored.

Missing data: 2 open deals have no row in engagements_by_deal_90d.csv, so recency cannot be computed: Deal-3EED2C, Deal-57FF13.

STALE DEALS BY OWNER (amount descending within owner)

Bryce Harmon — 13 stale, total stale 626,243
- Deal-2D1F1B, DS1, 240000, 81 days. 2026-09-05 minus 2026-06-16 = 81
- Deal-66D1FC, DS1, 99000, 16 days. 2026-09-05 minus 2026-08-20 = 16
- Deal-950043, DS1, 70000, 19 days. 2026-09-05 minus 2026-08-17 = 19
- Deal-B23205, DS1, 45000, 16 days. 2026-09-05 minus 2026-08-20 = 16
- Deal-7BBDFA, DS3, 37440, 46 days. 2026-09-05 minus 2026-07-21 = 46
- Deal-332637, DS2, 36000, 9 days. 2026-09-05 minus 2026-08-27 = 9
- Deal-1BEEBF, DS1, 31500, 19 days. 2026-09-05 minus 2026-08-17 = 19
- Deal-C5658B, DS1, 23400, 16 days. 2026-09-05 minus 2026-08-20 = 16
- Deal-40522D, DS3, 21000, 19 days. 2026-09-05 minus 2026-08-17 = 19
- Deal-F0EBBB, DS3, 11400, 24 days. 2026-09-05 minus 2026-08-12 = 24
- Deal-E25A09, DS1, 6000, 9 days. 2026-09-05 minus 2026-08-27 = 9
- Deal-C9C286, DS2, 5502, 9 days. 2026-09-05 minus 2026-08-27 = 9
- Deal-012CB1, DS1, 1, 23 days. 2026-09-05 minus 2026-08-13 = 23
Arithmetic check: 240000+99000+70000+45000+37440+36000+31500+23400+21000+11400+6000+5502+1 = 626,243

Dana Mercer — 14 stale, total stale 261,645
- Deal-44EA29, DS2, 60000, 10 days. 2026-09-05 minus 2026-08-26 = 10
- Deal-E51FB7, DS2, 43875, 12 days. 2026-09-05 minus 2026-08-24 = 12
- Deal-B42F46, DS1, 27000, 19 days. 2026-09-05 minus 2026-08-17 = 19
- Deal-BA3DDC, DS3, 23400, 15 days. 2026-09-05 minus 2026-08-21 = 15
- Deal-9DDE86, DS2, 20000, 15 days. 2026-09-05 minus 2026-08-21 = 15
- Deal-215CCA, DS3, 18900, 17 days. 2026-09-05 minus 2026-08-19 = 17
- Deal-5EED42, DS3, 16250, 11 days. 2026-09-05 minus 2026-08-25 = 11
- Deal-57887A, DS2, 15000, 8 days. 2026-09-05 minus 2026-08-28 = 8
- Deal-B7EBD1, DS5, 9000, 16 days. 2026-09-05 minus 2026-08-20 = 16
- Deal-3974EB, DS4, 9000, 8 days. 2026-09-05 minus 2026-08-28 = 8
- Deal-F40F04, DS2, 8100, 15 days. 2026-09-05 minus 2026-08-21 = 15
- Deal-87DDD1, DS1, 5000, 19 days. 2026-09-05 minus 2026-08-17 = 19
- Deal-F336B6, DS3, 4200, 15 days. 2026-09-05 minus 2026-08-21 = 15
- Deal-0660B4, DS4, 1920, 16 days. 2026-09-05 minus 2026-08-20 = 16
Arithmetic check: 60000+43875+27000+23400+20000+18900+16250+15000+9000+9000+8100+5000+4200+1920 = 261,645

Alex Franklin — 18 stale, total stale 102,336
- Deal-CC08D1, DS1, 24000, 16 days. 2026-09-05 minus 2026-08-20 = 16
- Deal-E73427, DS3, 18000, 10 days. 2026-09-05 minus 2026-08-26 = 10
- Deal-885F45, DS2, 9300, 12 days. 2026-09-05 minus 2026-08-24 = 12
- Deal-C2FF3C, DS1, 8316, 10 days. 2026-09-05 minus 2026-08-26 = 10
- Deal-0D2F7A, DS3, 5100, 12 days. 2026-09-05 minus 2026-08-24 = 12
- Deal-6C60D4, DS3, 4800, 12 days. 2026-09-05 minus 2026-08-24 = 12
- Deal-13FEBD, DS2, 4680, 12 days. 2026-09-05 minus 2026-08-24 = 12
- Deal-9D0060, DS3, 3840, 12 days. 2026-09-05 minus 2026-08-24 = 12
- Deal-690476, DS2, 3600, 18 days. 2026-09-05 minus 2026-08-18 = 18
- Deal-C6D97A, DS4, 3240, 8 days. 2026-09-05 minus 2026-08-28 = 8
- Deal-EE195F, DS3, 3120, 8 days. 2026-09-05 minus 2026-08-28 = 8
- Deal-278DEC, DS3, 2700, 8 days. 2026-09-05 minus 2026-08-28 = 8
- Deal-635B8E, DS3, 2600, 18 days. 2026-09-05 minus 2026-08-18 = 18
- Deal-6883F3, DS1, 2400, 16 days. 2026-09-05 minus 2026-08-20 = 16
- Deal-4A13AD, DS3, 2160, 26 days. 2026-09-05 minus 2026-08-10 = 26
- Deal-F67D31, DS2, 1800, 8 days. 2026-09-05 minus 2026-08-28 = 8
- Deal-5FDCE4, DS3, 1600, 12 days. 2026-09-05 minus 2026-08-24 = 12
- Deal-BA571A, DS4, 1080, 18 days. 2026-09-05 minus 2026-08-18 = 18
Arithmetic check: 24000+18000+9300+8316+5100+4800+4680+3840+3600+3240+3120+2700+2600+2400+2160+1800+1600+1080 = 102,336

Cole Ingram — 18 stale, total stale 252,905.03
- Deal-D04904, DS2, 58529.25, 11 days. 2026-09-05 minus 2026-08-25 = 11
- Deal-B25F40, DS3, 40000, 8 days. 2026-09-05 minus 2026-08-28 = 8
- Deal-813836, DS2, 32175, 11 days. 2026-09-05 minus 2026-08-25 = 11
- Deal-1BA595, DS2, 31750, 11 days. 2026-09-05 minus 2026-08-25 = 11
- Deal-CFE1E8, DS3, 18000, 11 days. 2026-09-05 minus 2026-08-25 = 11
- Deal-99A240, DS2, 18900, 5 days? No — correction: Deal-99A240 last_email 2026-08-31 = 5 days, NOT stale. Excluded.
Actual ordered list used:
- Deal-D04904, DS2, 58529.25, 11 days
- Deal-B25F40, DS3, 40000, 8 days
- Deal-813836, DS2, 32175, 11 days
- Deal-1BA595, DS2, 31750, 11 days
- Deal-CFE1E8, DS3, 18000, 11 days
- Deal-CD47A6, DS2, 12168, 11 days. 2026-09-05 minus 2026-08-25 = 11
- Deal-627646, DS3, 11193, 11 days. 2026-09-05 minus 2026-08-25 = 11
- Deal-FF809F, DS2, 7781.2, 11 days. 2026-09-05 minus 2026-08-25 = 11
- Deal-AF932D, DS2, 7225.4, 11 days. 2026-09-05 minus 2026-08-25 = 11
- Deal-A71728, DS2, 6947.5, 11 days. 2026-09-05 minus 2026-08-25 = 11
- Deal-8BC9F5, DS2, 5616, 10 days. 2026-09-05 minus 2026-08-26 = 10
- Deal-175395, DS3, 4779.88, 11 days. 2026-09-05 minus 2026-08-25 = 11
- Deal-481E24, DS3, 4140, 10 days. 2026-09-05 minus 2026-08-26 = 10
- Deal-C7F9BF, DS2, 3360, 11 days. 2026-09-05 minus 2026-08-25 = 11
- Deal-2F3A66, DS3, 3334.8, 11 days. 2026-09-05 minus 2026-08-25 = 11
- Deal-342E96, DS2, 2700, 24 days. 2026-09-05 minus 2026-08-12 = 24
- Deal-E568D5, DS3, 1875, 11 days. 2026-09-05 minus 2026-08-25 = 11
- Deal-FD9F4E, DS5, 1330, 10 days. 2026-09-05 minus 2026-08-26 = 10
Arithmetic check: 58529.25+40000+32175+31750+18000+12168+11193+7781.2+7225.4+6947.5+5616+4779.88+4140+3360+3334.8+2700+1875+1330 = 252,905.03

Farid Osman — 0 stale, total stale 0

OWNER TOTALS
- Bryce Harmon: 13 stale, 626,243
- Dana Mercer: 14 stale, 261,645
- Alex Franklin: 18 stale, 102,336
- Cole Ingram: 18 stale, 252,905.03
- Farid Osman: 0 stale, 0
activity-mix-vs-outcomePASS 1.00
Plain-English question: Per rep, what did the last 30 days of emails, calls, and meetings look like next to the deals that advanced?
Prompt — what the model saw
The snapshot date is 2026-09-05. For each sales rep (owner), compute the last-30-day totals of emails, calls, and meetings from the engagements table, and the number of deals that entered DS2 in the last 30 days (t_ds2 within 30 days of the snapshot). Report per rep: the activity mix as percentages (emails/calls/meetings share of that rep's total activities), total activities per DS2 entry, and rank the reps by that efficiency ratio (lowest activities per DS2 entry = most efficient). Name the most efficient rep and the highest-volume rep, and note if they differ. Do not attribute cause.
cost $0.0567 · 83s · in 117 / out 12,006 tok
✓ alex_ds2_30d✓ alex_volume_high✓ efficient_named✓ mix_present✓ no_causal_claim

✓ Correct Answer (ground truth)

Plain-English answer: Alex Franklin is the standout signal with 18 deals entering DS2 in 30 days (next closest: Bryce Harmon with 4), alongside per-rep activity totals.
The answer in one line: alex_ds2_30d = 18; bryce_ds2_30d = 4; note = legacy alias justin_ds2=4 actually held Bryce Harmon count; Alex Franklin entered 18 deals into DS2 in the 30d window
alex_ds2_30d18
bryce_ds2_30d4
notelegacy alias justin_ds2=4 actually held Bryce Harmon count; Alex Franklin entered 18 deals into DS2 in the 30d window
graded checksalex_ds2_30d · alex_volume_high · efficient_named · mix_present · no_causal_claim

Model's actual answer

show the model's full answer
Snapshot date: 2026-09-05. DS2 window: t_ds2 2026-08-06 to 2026-09-05 inclusive.

Owner names from owners.csv:
119337721=Bryce Harmon, 84342457=Alex Franklin, 83155923=Dana Mercer, 83155924=Cole Ingram, 716654662=Farid Osman, 701163055=Elena Sinclair

DS2 entries in last 30 days:

- Bryce Harmon (4): Deal-25F752 (2026-08-10), Deal-CA7DC0 (2026-08-12), Deal-1CCE5C (2026-08-06), Deal-D73B89 (2026-09-03)
- Alex Franklin (18): Deal-EE195F (2026-08-06), Deal-D9A72E (2026-08-06), Deal-7FA0C3 (2026-08-07), Deal-E531A6 (2026-08-07), Deal-D1E6C2 (2026-08-11), Deal-36C33F (2026-08-11), Deal-317E6F (2026-08-12), Deal-4F775F (2026-08-17), Deal-F436DA (2026-08-19), Deal-CA5E44 (2026-08-24), Deal-46988D (2026-08-26), Deal-5296C9 (2026-08-28), Deal-898FC5 (2026-08-28), Deal-E73427 (2026-08-28), Deal-92D97D (2026-09-02), Deal-403845 (2026-09-02), Deal-1FC049 (2026-09-03), Deal-3EED2C (2026-09-03)
- Dana Mercer (1): Deal-57887A (2026-08-07)
- Cole Ingram (2): Deal-1BA595 (2026-08-12), Deal-42326B (2026-08-26)
- Farid Osman (1): Deal-499BF6 (2026-08-26)
- Elena Sinclair (0): none

Missing engagement rows in engagements_by_deal_90d.csv: Deal-3EED2C (Alex Franklin) and Deal-57FF13 (Elena Sinclair). Counted as 0 activities, noted explicitly.

Last-30-day activities (emails_30d + calls_30d + meetings_30d summed by owner via deals_open.csv):

Bryce Harmon:
Emails=162, Calls=0, Meetings=43. Total=162+0+43=205
Mix: 162/205=79.0% emails, 0/205=0.0% calls, 43/205=21.0% meetings
Per DS2: 205/4=51.25

Alex Franklin:
Emails=307, Calls=36, Meetings=41. Total=307+36+41=384
Mix: 307/384=79.9% emails, 36/384=9.4% calls, 41/384=10.7% meetings
Per DS2: 384/18=21.33

Dana Mercer:
Emails=84, Calls=18, Meetings=11. Total=84+18+11=113
Mix: 84/113=74.3% emails, 18/113=15.9% calls, 11/113=9.7% meetings
Per DS2: 113/1=113.0

Cole Ingram:
Emails=96, Calls=14, Meetings=1. Total=96+14+1=111
Mix: 96/111=86.5% emails, 14/111=12.6% calls, 1/111=0.9% meetings
Per DS2: 111/2=55.5

Farid Osman:
Emails=38, Calls=0, Meetings=34. Total=38+0+34=72
Mix: 38/72=52.8% emails, 0/72=0.0% calls, 34/72=47.2% meetings
Per DS2: 72/1=72.0

Elena Sinclair:
Emails=0, Calls=0, Meetings=0 (no engagement row for Deal-57FF13). Total=0
Mix: undefined (0 total). Per DS2: undefined (0/0, no DS2 entries)

Efficiency rank by activities per DS2 entry (lowest=most efficient):
1. Alex Franklin 21.33
2. Bryce Harmon 51.25
3. Cole Ingram 55.5
4. Farid Osman 72.0
5. Dana Mercer 113.0
Unranked: Elena Sinclair (no DS2 entries)

Most efficient rep: Alex Franklin (21.33 activities per DS2 entry)
Highest-volume rep: Alex Franklin (384 total activities)
They do not differ; same rep.
ae-qtd-scorecardPASS 1.00
Plain-English question: Build Alex Franklin's QTD scorecard: bookings versus quota, pipeline, and conversion.
Prompt — what the model saw
Build a QTD scorecard for the named AE as of 2026-09-05: bookings vs quota with attainment percent, new vs expansion split, active pipeline by stage with amount, rolling 90-day DS2-to-won rate, win and loss counts with top loss reason, activity volume by type in the last 30 days. Exclude any closed-won deal dated before the quarter. Close with three coaching observations grounded in the numbers.
cost $0.0928 · 99s · in 49,274 / out 4,264 tok
✓ bookings✓ quota✓ attainment✓ new_expansion_split✓ top_loss_reason✓ coaching_obs

✓ Correct Answer (ground truth)

Plain-English answer: 75% attainment ($150,000 on a $200,000 quota), $113,500 new versus $36,500 expansion, pipeline by stage, and the rolling DS2-to-won rate.
The answer in one line: quota = 200000; bookings = 150000; new_bookings = 113500; expansion_bookings = 36500; open_deals_count = 125; attainment_pct = 75; owner = Alex Franklin (+12 more below)
quota200,000
attainment_pct75
bookings150,000
expansion_bookings36,500
expansion_count3
losses_qtd27
new_bookings113,500
new_count5
open_deals_count125
wins_qtd8
activity_30d_totalsemails_30d=807; calls_30d=112; meetings_30d=128; notes_30d=50
allowed_new18 items — e.g. Deal-A1C3E5, Deal-B7D2F4, Deal-C9E1A6, Deal-D4B8C2
ds2_to_wonwindow_start=2026-06-07; won_in_window=8; closed_in_window=35; rate=0.2286
ownerAlex Franklin
pipeline_by_stage{"DS1": {"count": 20, "amount": 284621}, "DS2": {"count": 28, "amount": 353760}, "DS3": {"count": 67, "amount": 552705}, "DS4": {"count": 5, "amount": 23574}, "DS5": {"count": 5, "amount": 45730}}
prior_quarter_excludeddeal_alias=Deal-B3E6F1; close_date=2026-06-20; amount=24000
quarter2026-Q3
snapshot_date2026-09-05
top_loss_reasonreason=Lost- Timing (1 year or more); count=13
graded checksbookings · quota · attainment · new_expansion_split · top_loss_reason · coaching_obs

Model's actual answer

show the model's full answer
QTD SCORECARD — Alex Franklin — as of 2026-09-05 — 2026-Q3

1. BOOKINGS VS QUOTA
Quota (quota.csv): 200,000
Excluded pre-quarter win: Deal-B3E6F1, 24,000, closed 2026-06-20
QTD wins included (close_date 2026-07-01 to 2026-09-05):
Deal-A1C3E5 40,000 + Deal-F2C7D8 20,000 + Deal-B7D2F4 35,000 + Deal-C9E1A6 21,000 + Deal-A8B4D6 12,000 + Deal-D4B8C2 11,000 + Deal-E6F3A9 6,500 + Deal-C5D9E2 4,500 = 150,000
Attainment: 150,000 / 200,000 = 75.0%
Remaining: 200,000 - 150,000 = 50,000

2. NEW VS EXPANSION (QTD wins only)
New: Deal-A1C3E5 40,000 + Deal-B7D2F4 35,000 + Deal-C9E1A6 21,000 + Deal-D4B8C2 11,000 + Deal-E6F3A9 6,500 = 113,500
Expansion: Deal-F2C7D8 20,000 + Deal-A8B4D6 12,000 + Deal-C5D9E2 4,500 = 36,500
Check: 113,500 + 36,500 = 150,000
Mix: 113,500 / 150,000 = 75.7% new; 36,500 / 150,000 = 24.3% expansion

3. ACTIVE PIPELINE BY STAGE (status = open, 125 deals)
DS1: 20 deals, 284,621
DS2: 28 deals, 353,760
DS3: 67 deals, 552,705
DS4: 5 deals, 23,574
DS5: 5 deals, 45,730
Total: 284,621 + 353,760 + 552,705 + 23,574 + 45,730 = 1,260,390
Late-stage (DS4+DS5): 23,574 + 45,730 = 69,304

4. ROLLING 90-DAY DS2-TO-WON RATE
Method: entered_ds2 from 2026-06-07 to 2026-09-05 (as-of minus 90 days), won / all entered in window.
Cohort: 111 entered; 8 won, 27 lost, 76 still open.
Rate: 8 / 111 = 7.2%
Closed-only rate for reference: 8 / (8 + 27) = 8 / 35 = 22.9%
Won in cohort: Deal-A1C3E5, Deal-F2C7D8, Deal-B7D2F4, Deal-C9E1A6, Deal-A8B4D6, Deal-D4B8C2, Deal-E6F3A9, Deal-C5D9E2.

5. WINS AND LOSSES
QTD wins: 8 (listed above)
QTD losses (close_date 2026-07-01 to 2026-09-05): 27
Top loss reason: Lost- Timing (1 year or more): 13 of 27 = 48.1%
Full QTD loss mix: Timing 13, MIA 5, Competitor 5, Lost DM 2, Feature Request 1, Lost- Does not fit ICP (write in notes) 1. Check: 13+5+5+2+1+1 = 27.

6. ACTIVITY VOLUME, LAST 30 DAYS (ae_engagements.csv summed across all 161 deals)
Emails: 807
Calls: 112
Meetings: 128
Notes: 50
Total touches: 807 + 112 + 128 + 50 = 1,097

COACHING OBSERVATIONS
1. Fix timing qualification: 13 of 27 QTD losses (48.1%) are Lost- Timing (1 year or more). With a 7.2% DS2-to-won rate and 76 of the 111 recent DS2 entrants still open, tighten DS2 entry on timeline and next step to stop early-stage buildup from decaying.
2. Advance late stage to cover the gap: only 50,000 remains to quota, but DS4+DS5 totals 69,304 across 10 deals (1.39x coverage). DS3 holds 552,705 across 67 deals — prioritize pulling a few DS3s forward rather than adding DS1/DS2 volume.
3. Rebalance effort toward live deals: 807 emails vs 112 calls (7.2 to 1) with 27 QTD losses including 5 MIA and 5 Competitor. Shift calls/meetings to DS4/DS5 and competitive deals; email alone is not saving MIA or competitive losses.
multithreading-gapPASS 1.00
Plain-English question: Which open deals are single-threaded or under-threaded?
Prompt — what the model saw
Find every open deal that is single-threaded (fewer than 2 active contacts) or under-threaded (fewer than 3, or all contacts in one persona). Active means engaged in the last 60 days and not marked former. Personas: economic buyer, champion, HR admin, IT security, finance. For each flagged deal: amount, stage, active contact count, personas present, personas missing, the most valuable persona to add given the stage, and any on-file unengaged contact at that company who fits; otherwise say none on file.
cost $0.0171 · 83s · in 100 / out 3,233 tok
✓ flagged_recall✓ persona_language✓ single_thread_term✓ on_file_fit

✓ Correct Answer (ground truth)

Plain-English answer: Deals with fewer than 2 active contacts (single-threaded) or fewer than 3, or all in one persona (under-threaded), each flagged with the missing persona.
The answer in one line: active_window_start = 2026-07-07
active_window_start2026-07-07
allowed_new59 items — e.g. C-077A0E, C-0D15DF, C-1BDFE0, C-2AE3AA
best_persona_ruleDS2/DS3: economic buyer > IT security > finance > HR admin > champion; DS4/DS5: economic buyer > finance > IT security > HR admin > champion; first persona not present among active contacts
flag_ruleflag if active_contacts < 2 (single-threaded) or active_contacts < 3 or all active contacts share one persona (under-threaded); active = engaged within 60 days and not former
flaggeddeal_alias=Deal-36C33F; amount=15000; stage=DS2; active_count=1; reason=single-threaded; best_persona_to_add=economic buyer | deal_alias=Deal-50D386; amount=36000; stage=DS2; active_count=2; reason=under-threaded; best_persona_to_add=economic buyer | deal_alias=Deal-5408B0; amount=14850; stage=DS4; active_count=2; reason=under-threaded; best_persona_to_add=economic buyer | deal_alias=Deal-5BFE3B; amount=18000; stage=DS2; active_count=2; reason=under-threaded; best_persona_to_add=economic buyer | deal_alias=Deal-885F45; amount=9300; stage=DS2; active_count=2; reason=under-threaded; best_persona_to_add=IT security | deal_alias=Deal-92D97D; amount=60000; stage=DS2; active_count=1; reason=single-threaded; best_persona_to_add=economic buyer … (+5 more)
healthy_not_flaggedDeal-4B0BEB, Deal-84DBA6, Deal-D348E1
persona_universeeconomic buyer, champion, HR admin, IT security, finance
graded checksflagged_recall · persona_language · single_thread_term · on_file_fit

Model's actual answer

show the model's full answer
Data gaps stated first: deal_contacts.csv and unengaged_contacts.csv contain no amount, stage, or open/closed status. All deals below are assumed open as listed. Amount, stage, and stage-based most-valuable-persona cannot be determined — missing.

Active definition used: is_former=false AND last_engaged_date >= 2026-07-05.
Arithmetic for cutoff: max last_engaged_date on file = 2026-09-03. 2026-09-03 minus 60 days = 2026-07-05.
Result: 2 date-inactive: CT-A902AE (2026-06-01), CT-913581 (2026-06-20). 3 former-inactive: CT-F2C1AE, CT-405B45, CT-86B22F. All others active.

Flagged deals (11):

1. Deal-EC3025 / C-FDD0C7
Active count: 1 = 1 active (CT-047C54 champion 2026-09-02) + 0 (CT-F2C1AE former excluded)
Reason: single-threaded (<2)
Personas present: champion
Personas missing: economic buyer, HR admin, IT security, finance
Most valuable to add given stage: unknown — stage missing
Unengaged fit on file: CT-6827DB, Chief People Officer, economic buyer

2. Deal-92D97D / C-E23238
Active count: 1 = 1 active (CT-01F5B4 HR admin 2026-08-28) + 0 (CT-A902AE 2026-06-01 < 2026-07-05 excluded)
Reason: single-threaded (<2)
Present: HR admin
Missing: economic buyer, champion, IT security, finance
Stage-based next persona: unknown — stage missing
Unengaged fit: none on file

3. Deal-50D386 / C-EB10E4
Active count: 2 = CT-AA41B2 champion 2026-09-01 + CT-B9C35B HR admin 2026-08-25
Reason: under-threaded (<3)
Present: champion, HR admin
Missing: economic buyer, IT security, finance
Stage-based next persona: unknown — stage missing
Unengaged fit: CT-A1C4B3, Chief People Officer, economic buyer

4. Deal-D0D6B5 / C-32918E
Active count: 3 = CT-87CED4 + CT-DE6D7C + CT-FD70B2, all champion, all >=2026-07-05
Reason: under-threaded (all contacts in one persona)
Present: champion
Missing: economic buyer, HR admin, IT security, finance
Stage-based next persona: unknown — stage missing
Unengaged fit: CT-1FA4DB, Chief People Officer, economic buyer

5. Deal-5BFE3B / C-535D36
Active count: 2 = CT-57123B champion 2026-08-31 + CT-5CE757 champion 2026-08-12
Reason: under-threaded (<3, single persona)
Present: champion
Missing: economic buyer, HR admin, IT security, finance
Stage-based next persona: unknown — stage missing
Unengaged fit: none on file

6. Deal-36C33F / C-077A0E
Active count: 1 = 1 active (CT-4FE556 IT security 2026-08-15) + 0 (CT-405B45 former, CT-86B22F former excluded)
Reason: single-threaded (<2)
Present: IT security
Missing: economic buyer, champion, HR admin, finance
Stage-based next persona: unknown — stage missing
Unengaged fit: CT-1DB73E, Chief People Officer, economic buyer

7. Deal-885F45 / C-5E8EFB
Active count: 2 = CT-51C81E economic buyer 2026-08-26 + CT-D9A0E8 champion 2026-08-11
Reason: under-threaded (<3)
Present: economic buyer, champion
Missing: HR admin, IT security, finance
Stage-based next persona: unknown — stage missing
Unengaged fit: CT-B3F25D, IT Security Lead, IT security

8. Deal-FCBE5B / C-737030
Active count: 1 = CT-4A5317 champion 2026-08-29
Reason: single-threaded (<2)
Present: champion
Missing: economic buyer, HR admin, IT security, finance
Stage-based next persona: unknown — stage missing
Unengaged fit: none on file

9. Deal-5408B0 / C-2AE3AA
Active count: 2 = CT-D33AE4 champion 2026-09-01 + CT-8742FD HR admin 2026-08-18
Reason: under-threaded (<3)
Present: champion, HR admin
Missing: economic buyer, IT security, finance
Stage-based next persona: unknown — stage missing
Unengaged fit: CT-07FA76, Chief People Officer, economic buyer

10. Deal-C6D97A / C-5A8FC2
Active count: 3 = CT-223DDC + CT-B03555 + CT-4E8A2B, all champion, all >=2026-07-05
Reason: under-threaded (all contacts in one persona)
Present: champion
Missing: economic buyer, HR admin, IT security, finance
Stage-based next persona: unknown — stage missing
Unengaged fit: none on file

11. Deal-F9A08A / C-0D15DF
Active count: 1 = 1 active (CT-931B10 champion 2026-09-03) + 0 (CT-913581 2026-06-20 < 2026-07-05 excluded)
Reason: single-threaded (<2)
Present: champion
Missing: economic buyer, HR admin, IT security, finance
Stage-based next persona: unknown — stage missing
Unengaged fit: CT-697541, Chief People Officer, economic buyer

Not flagged (meet >=3 active contacts across >=2 personas):
Deal-84DBA6 (3 active: champion, economic buyer, IT security), Deal-4B0BEB (4 active: champion, economic buyer, HR admin, finance), Deal-D348E1 (5 active: champion, economic buyer, IT security, finance, HR admin).
talk-track-from-transcriptsPASS 1.00
Plain-English question: From this rep's last 10 calls: how do they open, handle objections, and how often do they lock a next step?
Prompt — what the model saw
From this rep's last 10 calls: what they lead with in the first five minutes, how they handle the three most common objections, how often a concrete next step is agreed (rate), and every competitor a prospect raised. Quote at most one line per finding and only lines that appear in the transcripts. End with two coaching notes.
cost $0.0209 · 80s · in 2,631 / out 3,457 tok
✓ objection_count✓ next_step_rate✓ competitors✓ coaching✓ quote_used

✓ Correct Answer (ground truth)

Plain-English answer: 8 of 10 calls open with the same customer-win story; objection handling, next-step agreement rate, and every competitor raised, with quotes.
The answer in one line: n_transcripts = 10; objection_count = 3; rep = Alex Franklin (+3 more below)
n_transcripts10
objection_count3
allowed_new13 items — e.g. TT-001, TT-002, TT-003, TT-004
competitor_quotesAwardco=We're also in late talks with Awardco — their rewards catalog looks bigger than yours.; Kudos=How are you different from Kudos? Our CEO used them at her last company.
competitors_prospect_raisedAwardco, Kudos
next_stepagreed=7; total=10; rate=0.7
objectionsobjection=budget; count=4; quote=Honestly, budget is locked until next fiscal year — I can't add a new line item right now.; transcript_id=TT-001 | objection=timing; count=3; quote=This is good, but can we revisit it next quarter? Open enrollment starts in October and we're underwater.; transcript_id=TT-002 | objection=in-house; count=3; quote=We already do recognition with a spreadsheet and quarterly gift cards — why would we change?; transcript_id=TT-004
opener_themetheme=opens with a customer recognition win story (400-person retailer, 18% turnover reduction); count=8; total=10; quote=Quick one to kick off: a 400-person retailer we work with cut regretted turnover 18% in two quarters after automating milestone awards, and I wanted to walk you through exactly how they did it.; transcript_id=TT-001
repAlex Franklin
rep_raised_competitors_excludedWorkhuman
graded checksobjection_count · next_step_rate · competitors · coaching · quote_used

Model's actual answer

show the model's full answer
Opener in first 5 minutes: 8/10 calls = 80% use the same retailer story. Deals Deal-D348E1, Deal-5408B0, Deal-547B2B, Deal-C61CF7, Deal-60C2C2, Deal-EDC141, Deal-D9A12F, Deal-84DBA6. Other 2/10: Deal-403845, Deal-1E2498.
Quote: "Quick one to kick off: a 400-person retailer we work with cut regretted turnover 18% in two quarters after automating milestone awards, and I wanted to walk you through exactly how they did it."

Objection 1 - budget locked: 4/10 calls = 40% in Deal-D348E1, Deal-547B2B, Deal-60C2C2, Deal-84DBA6. Handling used in 3/4:
Quote: "Totally fair. Most teams fund this out of turnover savings — that retailer saved about $210k in avoided backfills, which is how their finance team signed off."

Objection 2 - revisit next quarter / open enrollment: 3/10 calls = 30% in Deal-5408B0, Deal-C61CF7, Deal-D9A12F. Handling 3/3 with pilot offer:
Quote: "Makes sense. What if we scope a 90-day pilot with one department so you have internal data before next quarter's planning?"

Objection 3 - spreadsheet + gift cards: 3/10 calls = 30% in Deal-403845, Deal-EDC141, Deal-1E2498. Handling 3/3 with automation/analytics:
Quote: "Spreadsheets work until they scale — the difference is automation: milestones fire without HR lifting a finger, and you get analytics on who is being recognized."

Next step agreed: 7/10 = 70%. Agreed in Deal-D348E1, Deal-5408B0, Deal-547B2B, Deal-C61CF7, Deal-60C2C2, Deal-D9A12F, Deal-1E2498. Not agreed in Deal-403845, Deal-EDC141, Deal-84DBA6.
Quote: "Yes, Thursday at 2pm works — send the invite and I'll bring our HRIS manager."

Competitor raised by prospect 1 - Awardco in Deal-547B2B:
Quote: "We're also in late talks with Awardco — their rewards catalog looks bigger than yours."

Competitor raised by prospect 2 - Kudos in Deal-EDC141:
Quote: "How are you different from Kudos? Our CEO used them at her last company."

Coaching notes:
1. Close the stacked budget + committee case like Deal-84DBA6 with the same tested responses used elsewhere instead of ending without a proposal.
2. Replace accept-the-stall endings in Deal-403845 and Deal-EDC141 with the pilot offer and working-session ask that produced 7/10 agreement.
reporting-analytics 5 tests
q3-weighted-forecastPASS 1.00
Plain-English question: Build the Q3 2026 weighted forecast from the open pipeline, and show the math deal by deal.
Prompt — what the model saw
Below are the open deals in the default sales pipeline with a close date between 2026-07-01 and 2026-10-15, pulled from the CRM warehouse on 2026-09-05. Stages: DS1 (discovery) through DS5 (contract). Build the Q3 2026 forecast (quarter = 2026-07-01 to 2026-09-30). Weighting rule: 100 percent of COMMIT plus 35 percent of BEST_CASE. PIPELINE deals count zero. Only deals with a close date inside the quarter count. Report: COMMIT total, BEST_CASE total, weighted forecast, count of deals in each category inside the quarter, the deals you excluded for being outside the quarter (count and total amount), and the top 5 BEST_CASE deals by amount inside the quarter. Show arithmetic. Then, in a final '## Data quality' section of no more than four sentences, name the data quality problems in this extract that would make the forecast unreliable if it were run unattended.
cost $0.0927 · 83s · in 52,915 / out 5,555 tok
✓ commit_total_44729✓ best_case_total_203565✓ weighted_115976.75✓ commit_count_7✓ best_case_count_24✓ excluded_count_32✓ excluded_amount_227575✓ top5_aliases✓ flags_blank_owner✓ flags_missing_why_buys

✓ Correct Answer (ground truth)

Plain-English answer: A stage-weighted Q3 forecast number computed from the open pipeline, with per-stage math that reconciles to the deal data.
The answer in one line: excluded_amount = 227575; best_case_total = 203565; weighted_forecast = 115,976.75; commit_total = 44729; excluded_out_of_quarter = 32; best_case_count = 24; flags = blank owner column + empty why_buys fields must be surfaced (+2 more below)
excluded_amount227,575
best_case_count24
best_case_total203,565
commit_count7
commit_total44,729
excluded_out_of_quarter32
weighted_forecast115,976.75
flagsblank owner column + empty why_buys fields must be surfaced
top5_best_caseDeal-2D7423, Deal-25F752, Deal-E53952, Deal-5EED42, Deal-FA32A0
graded checkscommit_total_44729 · best_case_total_203565 · weighted_115976.75 · commit_count_7 · best_case_count_24 · excluded_count_32 · excluded_amount_227575 · top5_aliases · flags_blank_owner · flags_missing_why_buys

Model's actual answer

show the model's full answer
Q3 2026 forecast (quarter = 2026-07-01 to 2026-09-30, inclusive)

Rule: 100% of COMMIT + 35% of BEST_CASE. PIPELINE = 0. Only close_date inside quarter counts.

Deals inside quarter: 54
- COMMIT: 7 deals
- BEST_CASE: 24 deals
- PIPELINE: 23 deals

COMMIT total: 44,729
11,200 (Deal-547B2B) + 9,000 (Deal-B7EBD1) + 9,000 (Deal-403845) + 6,360 (Deal-A2B47C) + 5,400 (Deal-2465CE) + 2,520 (Deal-A5E80A) + 1,249 (Deal-499BF6) = 44,729

BEST_CASE total: 203,565
38,935 + 24,000 + 19,656 + 16,250 + 11,116 + 10,800 + 10,500 + 9,890 + 9,720 + 9,000 + 7,200 + 3,840 + 3,780 + 3,600 + 3,240 + 3,150 + 3,120 + 3,060 + 2,916 + 2,760 + 2,484 + 2,100 + 1,920 + 528 = 203,565

Weighted forecast:
44,729 + (0.35 x 203,565) = 44,729 + 71,247.75 = 115,976.75

Excluded for close_date outside quarter: 32 deals, total amount 227,575
All have close_date 2026-10-01 to 2026-10-15. This includes 1 COMMIT (Deal-D348E1, 13,770), 9 BEST_CASE, and 22 PIPELINE.

Top 5 BEST_CASE deals inside quarter by amount:
1. Deal-2D7423 — 38,935 — 2026-09-30
2. Deal-25F752 — 24,000 — 2026-09-25
3. Deal-E53952 — 19,656 — 2026-09-30
4. Deal-5EED42 — 16,250 — 2026-09-30
5. Deal-FA32A0 — 11,116 — 2026-09-25

## Data quality
Owner is blank on 85 of 86 deals (only Deal-C9C286 has an owner), and why_buys_chars is 0 on most deals, so qualification and ownership cannot be checked. Stage and forecast_category disagree: Deal-A5E80A is DS1 COMMIT, Deal-499BF6 is DS2 COMMIT, Deal-6787C2 is DS4 PIPELINE, and excluded Deal-C61CF7 is DS5 BEST_CASE. Close dates are stale or stacked: several still-open deals have close dates before the 2026-09-05 pull (e.g. Deal-333EBB on 2026-08-28), many cluster exactly on 2026-09-30, and one amount uses cents (Deal-42326B, 2480.4) while all others are whole dollars.
aha-moment-2x20.83
Plain-English question: Do companies that hit 5+ givers and one redemption in month one actually retain better at 24 months?
Prompt — what the model saw
Test the activation hypothesis on the company cohort below: companies with 5+ unique givers (m1_users >= 5) AND 1+ successful redemption (m1_redemptions >= 1) in their first calendar month retain better at 24 months than those with one signal or neither. Every company in this extract is already 25+ months old, so current_status = 'active' means retained at 24 months. Report the full 2x2 (cohort size and 24-month retention rate for: both signals, givers-only, redemption-only, neither), state how many companies were excluded from the denominator and why (if none, say so), name the single signal with the largest retention lift, and state what this does and does not prove.
cost $0.0935 · 82s · in 31,056 / out 11,474 tok
✓ both_66✓ givers_47✓ redemp_31✓ neither_40✓ excluded_0✗ largest_lift_givers

✓ Correct Answer (ground truth)

Plain-English answer: The four cohort cells are graded against computed 24-month retention; the numbers come from the scorer's cohort table, not opinion.
The answer in one line: both_5plus_givers_and_redemption = 66.0% (31 of 47)
both_5plus_givers_and_redemption66.0% (31 of 47)
exclusionsnone — claim bounded as correlation, not causation
givers_only46.9% (23 of 49)
largest_single_signal_liftunique givers
neither40.0% (38 of 95)
redemption_only31.0% (9 of 29)
graded checksboth_66 · givers_47 · redemp_31 · neither_40 · excluded_0 · largest_lift_givers

Model's actual answer

show the model's full answer
Hypothesis holds in this extract: both-signals retains highest.

2x2 (retained = current_status = 'active'):

Both signals (m1_users >= 5 AND m1_redemptions >= 1): n = 47, retained = 31, rate = 31/47 = 66.0%

Givers-only (m1_users >= 5 AND m1_redemptions = 0): n = 49, retained = 23, rate = 23/49 = 46.9%

Redemption-only (m1_users < 5 AND m1_redemptions >= 1): n = 29, retained = 9, rate = 9/29 = 31.0%

Neither (m1_users < 5 AND m1_redemptions = 0): n = 95, retained = 38, rate = 38/95 = 40.0%

Check: 47 + 49 + 29 + 95 = 220 total. 31 + 23 + 9 + 38 = 101 active. Overall = 101/220 = 45.9%.

Excluded from denominator: 0. No companies excluded. All 220 rows have non-missing m1_users and m1_redemptions, and per prompt all are 25+ months old.

Single signal with largest retention lift: m1_users >= 5.

Arithmetic vs neither baseline (38/95 = 40.0%):
Givers-only lift = 23/49 - 38/95 = 46.9% - 40.0% = +6.9pp
Redemption-only lift = 9/29 - 38/95 = 31.0% - 40.0% = -9.0pp
Givers-only exceeds redemption-only by 46.9% - 31.0% = +15.9pp.

Marginal check gives same ranking:
Any-givers: (31+23)/(47+49) = 54/96 = 56.3% vs no-givers: (9+38)/(29+95) = 47/124 = 37.9%, lift = +18.4pp
Any-redemption: (31+9)/(47+29) = 40/76 = 52.6% vs no-redemption: (23+38)/(49+95) = 61/144 = 42.4%, lift = +10.3pp

What this does and does not prove:
Does prove: in this 220-company extract, first-month both-signals companies had a higher observed 24-month retention rate than either single-signal group or neither.
Does not prove: causation, that inducing 5+ givers or a redemption would raise retention, or that the gap is not driven by confounders absent from this test (e.g. company size, tier, industry, intent). It is an observational association in this cohort only.
arr-rollforward-reconciliation0.80
Plain-English question: Does CRM ARR match billing ARR — and if not, exactly where is the variance?
Prompt — what the model saw
Reconcile ARR between CRM company records and billing subscriptions as of 2026-09-05. Billing ARR is MRR x 12. Report both totals, the variance, and a decomposition into buckets (status mismatch, rounding, missing records, other) that sums exactly to the variance. List each mismatched account with a suggested owner. Business rule: any subscription with a term other than 12 months must have cf_agreement_end_date populated; list violations.
cost $0.0402 · 83s · in 6,077 / out 6,240 tok
✓ billing_total✓ crm_total✗ variance✓ buckets_sum✓ violations_listed

✓ Correct Answer (ground truth)

Plain-English answer: Billing $604,739.28 vs CRM $603,581.76: a $1,157.52 variance decomposed into status-mismatch, rounding, and missing-record buckets.
The answer in one line: n_companies = 40; n_mismatched_accounts = 7; as_of = 2026-09-05 (+4 more below)
n_companies40
n_mismatched_accounts7
as_of2026-09-05
billing_arr_total604739.28
bucket_sum_equals_variance1
buckets{"status_mismatch": {"amount": "-13158.48", "accounts": [{"company_alias": "C-0C8323BF", "billing_arr": "0.00", "hubspot_arr": "4905.24", "diff": "-4905.24", "suggested_owner": "Dana Mercer"}, {"compa
crm_arr_total603581.76
ruleterm_months != 12 requires cf_agreement_end_date
variance1157.52
variance_definitionbilling_arr_total - crm_arr_total (billing ARR = sum of MRR x 12 over status=active subscriptions)
violationssubscription_id=SUB-0002; company_alias=C-1794A52C; term_months=24 | subscription_id=SUB-0019; company_alias=C-22170CA1; term_months=36
graded checksbilling_total · crm_total · variance · buckets_sum · violations_listed

Model's actual answer

show the model's full answer
As of 2026-09-05, Billing ARR = MRR x 12, all rows included:

Billing total (39 subscriptions):
617,897.76

CRM total (39 company records):
603,581.76

Variance (CRM - Billing):
603,581.76 - 617,897.76 = -14,316.00
Billing exceeds CRM by 14,316.00.

Decomposition (CRM - Billing basis, sums to -14,316.00):

1. Missing records: -11,952.00
   C-21629AA4 (billing-only): 0 - 28,449.24 = -28,449.24
     2,370.77 x 12 = 28,449.24
   C-0D5BBE3A (CRM-only): 16,497.24 - 0 = +16,497.24
   Net: -28,449.24 + 16,497.24 = -11,952.00

2. Other (active matched, amount differs): -2,364.00
   C-0D66DF9E: 23,200.00 - 23,184.00 = +16.00
     1,932.00 x 12 = 23,184.00
   C-0F7269D7: 24,396.00 - 26,796.00 = -2,400.00
     2,233.00 x 12 = 26,796.00
   C-14D70CE0: 18,200.00 - 18,180.00 = +20.00
     1,515.00 x 12 = 18,180.00
   Net: 16.00 - 2,400.00 + 20.00 = -2,364.00

3. Status mismatch: 0.00
   C-0C8323BF (cancelled): 4,905.24 - 4,905.24 = 0.00
     408.77 x 12 = 4,905.24
   C-0DC4FB8C (cancelled): 8,253.24 - 8,253.24 = 0.00
     687.77 x 12 = 8,253.24
   Amount variance 0, status inconsistent - CRM carries 13,158.48 of cancelled ARR.
   4,905.24 + 8,253.24 = 13,158.48

4. Rounding: 0.00
   All other 34 overlapping accounts match exactly to the cent.

Check: -11,952.00 + -2,364.00 + 0.00 + 0.00 = -14,316.00

Mismatched accounts - suggested functional owner (owner data not provided in files):

C-21629AA4 - CRM Admin / RevOps: create CRM company or void SUB-0004
C-0D5BBE3A - Billing Ops / RevOps: create/correct subscription or remove CRM ARR 16,497.24
C-0F7269D7 - Account Owner / RevOps: correct CRM 24,396.00 vs billing 26,796.00, diff -2,400.00
C-14D70CE0 - Account Owner / RevOps: correct CRM 18,200.00 vs billing 18,180.00, diff +20.00
C-0D66DF9E - Account Owner / RevOps: correct CRM 23,200.00 vs billing 23,184.00, diff +16.00
C-0C8323BF - Account Owner / CRM Admin: cancelled SUB-000E, close CRM 4,905.24
C-0DC4FB8C - Account Owner / CRM Admin: cancelled SUB-000F, close CRM 8,253.24

Business rule violations - term_months != 12 with blank cf_agreement_end_date:

SUB-0002, C-1794A52C, 24 months, blank
SUB-0019, C-22170CA1, 36 months, blank
kvm-month-over-monthPASS 1.00
Plain-English question: How did the four core KVMs move in August versus July?
Prompt — what the model saw
Report the four core KVMs for 2026-08 against 2026-07: giving rate, redemptions per user, 1:1 meetings engagement, pulse check engagement. For each: value, prior value, absolute and relative change, direction. Name the KVM with the largest relative move and the segment (plan_tier or size_band) driving it if the data supports that; otherwise say the data does not. Under 200 words plus one table.
cost $0.0638 · 62s · in 29,349 / out 4,864 tok
✓ four_kvms✓ biggest_mover_named✓ direction_correct✓ segment_named✓ word_cap

✓ Correct Answer (ground truth)

Plain-English answer: Giving rate 60.27% (up 0.07%), redemptions per user 1.7302 (up 0.01%), with 1:1 meetings and pulse engagement each up fractionally — direction reported for all four.
The answer in one line: n_company_rows_per_month = 30; aggregation = simple mean of company-level values per month
n_company_rows_per_month30
aggregationsimple mean of company-level values per month
biggest_moverpulse_engagement
driving_segmentsize_band=enterprise; 2026-07=0.55; 2026-08=0.2743; rel_change_pct=-50.13
kvms{"giving_rate": {"2026-07": 0.6023, "2026-08": 0.6027, "abs_change": 0.0004, "rel_change_pct": 0.07, "direction": "up"}, "redemptions_per_user": {"2026-07": 1.73, "2026-08": 1.7302, "abs_change": 0.00
segment_detail{"smb": {"2026-07": 0.6588, "2026-08": 0.6573, "rel_change_pct": -0.23}, "mid_market": {"2026-07": 0.593, "2026-08": 0.5942, "rel_change_pct": 0.2}, "enterprise": {"2026-07": 0.55, "2026-08": 0.2743,
graded checksfour_kvms · biggest_mover_named · direction_correct · segment_named · word_cap

Model's actual answer

show the model's full answer
Method: unweighted mean across 30 companies. Sums: giving 18.0814/30 (Jul 18.0689/30); redemptions 51.9049/30 (Jul 51.8995/30); 1:1 13.4153/30 (Jul 13.4066/30); pulse 15.2583/30 (Jul 18.0176/30).

| KVM | 2026-08 | 2026-07 | Abs. change | Rel. change | Direction |
|---|---|---|---|---|---|
| Giving rate | 0.6027 | 0.6023 | +0.0004 | +0.07% | up / flat |
| Redemptions per user | 1.7302 | 1.7300 | +0.0002 | +0.01% | up / flat |
| 1:1 meetings engagement | 0.4472 | 0.4469 | +0.0003 | +0.06% | up / flat |
| Pulse check engagement | 0.5086 | 0.6006 | -0.0920 | -15.31% | down |

Largest relative move: pulse check engagement, -15.31%.

Driver: size_band=enterprise (-50.13%: 0.5500 to 0.2743). All 10 enterprise companies fell ~0.26-0.29 each, e.g. C-0B2895EF 0.5619 to 0.2864, C-0B2213A9 0.5548 to 0.2801, C-0D6CC8E3 0.5552 to 0.2733. smb (-0.22%) and mid_market (+0.21%) were flat. All rows plan_tier=tier_three, so no plan_tier distinction.
rewards-ytd-sectionPASS 1.00
Plain-English question: Produce the redemption section of the weekly rewards report through August.
Prompt — what the model saw
Produce the redemption section of the weekly rewards report through the last completed month (2026-08): redemption count, spend, unique redeemers, redemptions per redeemer, provider mix as percent of spend, top 5 countries by redemptions. Say which month is the last completed month. Provider shares must sum to 100.
cost $0.2209 · 128s · in 100,684 / out 19,596 tok
✓ count✓ spend✓ unique_redeemers✓ month_named✓ provider_mix✓ top_country

✓ Correct Answer (ground truth)

Plain-English answer: 378 redemptions, $27,846 spend, 235 unique redeemers at 1.61 each, custom rewards at 39% of spend, US leading all countries.
The answer in one line: redemption_count = 378; unique_redeemers = 235; redemptions_per_redeemer = 1.61; total_spend_usd = 27846.00
redemption_count378
redemptions_per_redeemer1.61
unique_redeemers235
provider_mix_pct_of_spendTangoCard=11.6; Tremendous=30.54; custom=39.05; Snappy=18.81
top5_countries_by_countcountry=US; count=244 | country=CA; count=24 | country=AU; count=21 | country=GB; count=17 | country=NL; count=17
total_spend_usd27846.00
graded checkscount · spend · unique_redeemers · month_named · provider_mix · top_country

Model's actual answer

show the model's full answer
Last completed month: 2026-08. All 378 rows are 2026-01 to 2026-08, max redeemed_at 2026-08-31T11:53:00, 0 rows after 2026-08.

Redemptions YTD through 2026-08:
- Redemption count: 378 (45 + 36 + 50 + 52 + 43 + 46 + 58 + 48 for Jan through Aug)
- Spend: $27,846.00
- Unique redeemers (user_key): 235
- Redemptions per redeemer: 378 / 235 = 1.6085 = 1.61

Provider mix, percent of spend:
- custom: $10,873.00 / $27,846.00 x 100 = 39.05%
- Tremendous: $8,505.00 / $27,846.00 x 100 = 30.54%
- Snappy: $5,238.00 / $27,846.00 x 100 = 18.81%
- TangoCard: $3,230.00 / $27,846.00 x 100 = 11.60%
- Sum: 39.05 + 30.54 + 18.81 + 11.60 = 100.00. Spend check: 10,873 + 8,505 + 5,238 + 3,230 = 27,846.

Top 5 countries by redemptions:
- US: 244
- CA: 24
- AU: 21
- GB: 17
- NL: 17 (tied with GB; next is SG with 12)
customer-success 5 tests
churn-save-eligibilityPASS 1.00
Plain-English question: Which at-risk accounts actually qualify for a churn-save offer, and which play fits each?
Prompt — what the model saw
Which at-risk accounts qualify for a churn-save offer under the documented eligibility rules, what amount is at stake per account and in total, and which play fits each (usage revival, executive touch, commercial concession)? Cite the signal that justifies each play. List accounts that look at risk but do not qualify and why.
cost $0.0172 · 64s · in 1,224 / out 2,996 tok
✓ eligible_set✓ total_at_stake✓ plays_cited✓ noneligible_named✓ rules_applied

✓ Correct Answer (ground truth)

Plain-English answer: Only accounts meeting all three rules qualify — e.g. C-0F6C0F34 at $49,707 (executive touch) and C-0B827671 at $25,365 (usage revival) — with amount and play per account.
The answer in one line: n_accounts = 30; snapshot_date = 2026-09-05
n_accounts30
eligibleaccount_alias=C-0F6C0F34; amount_at_stake=49707.00; play=executive touch; justifying_signal=champion_active is false - no executive sponsor engaged | account_alias=C-0B827671; amount_at_stake=25365.00; play=usage revival; justifying_signal=usage_trend_3m=declining over the last 3 months | account_alias=C-0B360C78; amount_at_stake=35748.00; play=commercial concession; justifying_signal=usage stable/growing with seat utilization 75% - risk is commercial, not adoption | account_alias=C-0B0F1BAB; amount_at_stake=5494.00; play=executive touch; justifying_signal=champion_active is false - no executive sponsor engaged | account_alias=C-0CA21961; amount_at_stake=16829.00; play=usage revival; justifying_signal=seat utilization 26% is below 50% | account_alias=C-0E9C27D1; amount_at_stake=41235.00; play=commercial concession; justifying_signal=usage stable/growing with seat utilization 85% - risk is commercial, not adoption … (+2 more)
non_eligible_at_riskaccount_alias=C-0BC71BDD; health_score=55 | account_alias=C-0BA71F12; health_score=52 | account_alias=C-0F6694C3; health_score=43 | account_alias=C-0BE96399; health_score=54 | account_alias=C-0F876796; health_score=47 | account_alias=C-0FCCD2DF; health_score=43 … (+1 more)
ruleshealth_score < 60, churn_save_eligible_amount > 0, renewal within 120 days of snapshot
snapshot_date2026-09-05
total_amount_at_stake224601.00
graded checkseligible_set · total_at_stake · plays_cited · noneligible_named · rules_applied

Model's actual answer

show the model's full answer
Qualified accounts must pass all 3 rules: R1 health_score < 60, R2 churn_save_eligible_amount > 0, R3 renewal_date within 120 days of 2026-09-05 (i.e. on or before 2027-01-03).

8 accounts qualify:

1. C-0F6C0F34 — $49,707.00 — renewal 2026-10-03 (28 days after snapshot), health 51
Play: executive touch — Signal: champion_active=false

2. C-0B827671 — $25,365.00 — renewal 2026-11-14 (70 days), health 56
Play: usage revival — Signal: usage_trend_3m=declining, seats_used 113/202 = 55.9%

3. C-0B360C78 — $35,748.00 — renewal 2026-10-28 (53 days), health 57
Play: commercial concession — Signal: usage_trend_3m=growing, 246/327 = 75.2% used, champion_active=true; risk is health score, not usage or champion

4. C-0B0F1BAB — $5,494.00 — renewal 2026-09-23 (18 days), health 38
Play: executive touch — Signal: champion_active=false, health 38 (lowest in set)

5. C-0CA21961 — $16,829.00 — renewal 2026-12-28 (114 days), health 58
Play: usage revival — Signal: seats_used 84/325 = 25.8%, usage_trend_3m=flat

6. C-0E9C27D1 — $41,235.00 — renewal 2026-09-24 (19 days), health 39
Play: commercial concession — Signal: 134/157 = 85.4% used, champion_active=true, usage_trend_3m=flat; risk is health 39, not adoption

7. C-0CEF69FD — $32,621.00 — renewal 2026-11-21 (77 days), health 53
Play: executive touch — Signal: champion_active=false

8. C-0D3278C7 — $17,602.00 — renewal 2026-11-12 (68 days), health 54
Play: usage revival — Signal: usage_trend_3m=declining, seats_used 126/380 = 33.2%

Total at stake:
49,707 + 25,365 + 35,748 + 5,494 + 16,829 + 41,235 + 32,621 + 17,602 = $224,601.00

At-risk (R1 health < 60) but NOT qualified — 7 accounts:

- C-0BC71BDD — fails R2: churn_save_eligible_amount = 0.00
- C-0BA71F12 — fails R3: renewal 2027-04-11 = 218 days after snapshot, over 120
- C-0F6694C3 — fails R2 (0.00) and R3: renewal 2027-03-21 = 197 days, over 120
- C-0BE96399 — fails R2: churn_save_eligible_amount = 0.00
- C-0F876796 — fails R3: renewal 2027-02-06 = 154 days after snapshot, over 120
- C-0FCCD2DF — fails R2 (0.00) and R3: renewal 2027-04-23 = 230 days, over 120
- C-10A56B0F — fails R2: churn_save_eligible_amount = 0.00
expansion-kitPASS 1.00
Plain-English question: Build the expansion kit for the customer who just replied to our outreach.
Prompt — what the model saw
A customer replied to outreach (reply included). Build the expansion kit: seat coverage (licensed over headcount), two lines on usage health, headroom in seats and ARR at the current per-seat rate, who replied and whether they can buy, the right buyer from our contacts, and a reply email under 150 words that moves toward the right person without being pushy and cites one real usage fact.
cost $0.0082 · 59s · in 395 / out 1,109 tok
✓ coverage_pct✓ headroom_arr✓ right_buyer✓ replier_not_buyer✓ usage_fact✓ email_under_150

✓ Correct Answer (ground truth)

Plain-English answer: 37.5% seat coverage, 250 headroom seats worth $15,000 ARR at $60 a seat, usage up 43.2% in six months — and the replier cannot buy; Dana R. (VP People) is the right buyer.
The answer in one line: headroom_seats = 250; coverage_pct = 37.5; company_alias = C-0DDFC9A7 (+3 more below)
headroom_seats250
coverage_pct37.5
company_aliasC-0DDFC9A7
headroom_arr15000.00
per_seat_annual_rate60.00
replierMaria S.
replier_can_buy0
right_buyername=Dana R.; title=VP People
usage_factsactive_users_2026_08=126; active_users_2026_03=88; growth_pct_6m=43.2; licensed_seat_utilization_pct=84
usage_health_linesMonthly active users grew from 88 (2026-03) to 126 (2026-08), +43.2% over 6 months., Last month 126 of 150 licensed seats were active (84.0% utilization), approaching the seat cap.
graded checkscoverage_pct · headroom_arr · right_buyer · replier_not_buyer · usage_fact · email_under_150

Model's actual answer

show the model's full answer
Expansion kit for C-0DDFC9A7

Seat coverage (licensed over headcount):
150 / 400 = 0.375 = 37.5%

Usage health:
1. Monthly active users rose every month Mar-Aug 2026: 88 > 95 > 102 > 110 > 118 > 126.
2. Aug utilization of licensed seats: 126 / 150 = 0.84 = 84%. Growth Mar-Aug: 126 - 88 = 38 users; 38 / 88 = 43.2% increase.

Headroom at current per-seat rate:
Per-seat rate: 9000.00 / 150 = $60.00
Seat headroom: 400 - 150 = 250 seats
ARR headroom: 250 x $60.00 = $15,000.00

Who replied and can they buy:
Maria S., People Operations Coordinator, replied 2026-09-02. Cannot buy - states: budget and seat expansion sit with Dana R.

Right buyer from contacts:
Dana R., VP People, last engaged 2026-05-18.

Reply email (98 words):

Subject: Re: Growing your team's recognition program

Hi Maria,

Thank you for sharing this - glad the team loves Bonusly.

Monthly active users reaching 126 in August is great momentum, and happy to share usage numbers for Dana.

Yes, an introduction to Dana R. would be helpful. I will keep it brief and share the usage trend she asked about, plus seat options. No pressure for a decision, just useful context.

Would you like to intro us, or should I reach out directly and mention you?

Thanks again,
Cole
onboarding-statusPASS 1.00
Plain-English question: What is done and what is missing in this customer's onboarding before the mid-onboarding call?
Prompt — what the model saw
Prep the CSM for the mid-onboarding call: what is complete (integrations connected, allowance set, admins added, first recognition given, first redemption), what is not, early engagement signals, and the three things to cover on the call. Mark nothing complete without a data field that shows it.
cost $0.0081 · 59s · in 400 / out 1,097 tok
✓ complete_items✓ incomplete_items✓ three_items✓ grounded

✓ Correct Answer (ground truth)

Plain-English answer: 25 days live: Slack connected, allowance set, admins added — but the HRIS integration is not connected, with early engagement signals and three call priorities.
The answer in one line: days_live = 25; company_alias = C-0D284E42
days_live25
call_itemsConnect the HRIS integration (integration_hris is empty) to automate user provisioning and offboarding., Get to first redemption (first_redemption_at is empty): walk admins through the rewards catalog and confirm allowance funding., Build the giving habit: daily active givers averaged 4.3 in week 1 vs 13.0 last week - agree on manager nudges and a recognition cadence.
checklist{"slack_integration_connected": {"complete": true, "field": "integration_slack", "value": "2026-08-12"}, "hris_integration_connected": {"complete": false, "field": "integration_hris", "value": ""}, "a
company_aliasC-0D284E42
engagement_signalsavg_active_givers_week1=4.3; avg_active_givers_last_week=13; latest_active_givers=15; days_with_activity=25
graded checkscomplete_items · incomplete_items · three_items · grounded

Model's actual answer

show the model's full answer
C-0D284E42 mid-onboarding prep

Complete (with data field):
- Integration Slack connected: integration_slack = 2026-08-12
- Allowance set: allowance_set = 2026-08-13
- Admins added: admins_added = 2
- First recognition given: first_recognition_at = 2026-08-15 14:22

Not complete:
- Integration HRIS: integration_hris = [blank]
- First redemption: first_redemption_at = [blank]

Early engagement signals (onboarding_usage.csv, 2026-08-11 to 2026-09-04, 25 days):
- Active givers start 3 on 2026-08-11, end 15 on 2026-09-04
- Change: 15 - 3 = 12; 15 / 3 = 5.0x
- Sum = 214; average = 214 / 25 = 8.56 active givers/day
- First 7 days (2026-08-11 to 2026-08-17): 3+3+4+4+5+4+7 = 30; 30 / 7 = 4.29/day
- Last 7 days (2026-08-29 to 2026-09-04): 11+13+11+13+13+15+15 = 91; 91 / 7 = 13.0/day
- Peak 15 reached 2026-09-03 and 2026-09-04. Trend is up with minor dips (e.g. 13 to 11 on 2026-08-30 to 2026-08-31).

Three things to cover on the call:
1. Connect HRIS — integration_hris is blank; confirm owner and date.
2. Drive first redemption — first_redemption_at is blank despite first recognition on 2026-08-15; walk through redemption.
3. Hold giver momentum — 9 to 15 givers in last 2 weeks; agree next expansion target and admin coverage with 2 admins currently.
renewal-risk-conflicting-dates0.75
Plain-English question: Two systems disagree on renewal dates — which do you trust per account, and who is actually renewing inside 90 days?
Prompt — what the model saw
Produce a 90-day renewal risk brief. Two systems hold renewal dates and disagree on some accounts; decide which to trust per account and say why (multi-year contracts are known to be wrong in ChurnZero). For every renewal: company, CSM, ARR, date used, seat utilization, 3-month usage trend, risk rating with one sentence of evidence. Flag every disagreement. Close with total ARR renewing and ARR at risk.
cost $0.0319 · 102s · in 4,830 / out 5,383 tok
✗ total_renewing✓ arr_at_risk✓ disagreements_flagged✓ trust_rule

✓ Correct Answer (ground truth)

Plain-English answer: Chargebee wins per account (multi-year contracts are known wrong in ChurnZero), with each trusted date, the reason, and a 90-day-window flag.
The answer in one line: n_accounts = 20; n_disagreements = 5; snapshot_date = 2026-09-05 (+2 more below)
n_accounts20
n_disagreements5
accounts20 items — e.g. account_alias=C-0B144C78; csm=Cole Ingram; arr=30899.00; trusted_renewal_date=2026-11-02; trusted_source_why=systems agree (annual term); in_90d_window=True; dates_disagree=False; seat_utilization_pct=75.4; usage_3m_ratio=1.03; risk=low; evidence=3-month usage ratio 1.03 (last3 avg 103 vs prior3 100), seat utilization 75% | account_alias=C-0B20DB64; csm=Dana Mercer; arr=21770.00; trusted_renewal_date=2026-10-07; trusted_source_why=systems agree (annual term); in_90d_window=True; dates_disagree=False; seat_utilization_pct=56.6; usage_3m_ratio=1; risk=medium; evidence=3-month usage ratio 1.00 (last3 avg 295 vs prior3 295), seat utilization 57% | account_alias=C-0B344485; csm=Elena Sinclair; arr=64384.00; trusted_renewal_date=2026-11-16; trusted_source_why=systems agree (annual term); in_90d_window=True; dates_disagree=False; seat_utilization_pct=78; usage_3m_ratio=1.04; risk=low; evidence=3-month usage ratio 1.04 (last3 avg 241 vs prior3 231), seat utilization 78% | account_alias=C-0B369871; csm=Dana Mercer; arr=85128.00; trusted_renewal_date=2026-10-29; trusted_source_why=systems agree (annual term); in_90d_window=True; dates_disagree=False; seat_utilization_pct=75.1; usage_3m_ratio=1.04; risk=low; evidence=3-month usage ratio 1.04 (last3 avg 330 vs prior3 316), seat utilization 75%
arr_at_risk_90d359409.00
disagreementsaccount_alias=C-0B7D2C30; cz_renewal_date=2026-09-10; cb_renewal_date=2026-09-15; is_multi_year=True; trusted=2026-09-15 | account_alias=C-0BBE3E60; cz_renewal_date=2027-09-26; cb_renewal_date=2026-09-26; is_multi_year=True; trusted=2026-09-26 | account_alias=C-0BCDB8C2; cz_renewal_date=2027-09-18; cb_renewal_date=2026-09-18; is_multi_year=True; trusted=2026-09-18 | account_alias=C-0D2AB865; cz_renewal_date=2026-09-10; cb_renewal_date=2026-09-22; is_multi_year=True; trusted=2026-09-22 | account_alias=C-0F5D2323; cz_renewal_date=2026-09-10; cb_renewal_date=2026-09-29; is_multi_year=True; trusted=2026-09-29
snapshot_date2026-09-05
total_arr_renewing_90d1048715.00
trust_rulemulti-year contracts: Chargebee is authoritative (ChurnZero known wrong); otherwise systems agree or Chargebee wins
window2026-09-05 to 2026-12-04
graded checkstotal_renewing · arr_at_risk · disagreements_flagged · trust_rule

Model's actual answer

show the model's full answer
90-day renewal risk brief

Assumption: no as-of date in files. Using 2026-10-20 as today. 90-day window = 2026-10-20 to 2027-01-18.

Trust rule: multi-year contracts are known wrong in ChurnZero, so trust Chargebee (cb_renewal_date) for all is_multi_year=true accounts. For 12-month accounts both systems agree, so either source, date used is the agreed date.

Disagreements flagged — all 5 are multi-year, all trusted to Chargebee:

- C-0B7D2C30: CZ 2026-09-10 vs CB 2026-09-15 (5 days). Trust CB 2026-09-15. Outside window, past.
- C-0BCDB8C2: CZ 2027-09-18 vs CB 2026-09-18 (365 days). Trust CB 2026-09-18. Outside window, past.
- C-0D2AB865: CZ 2026-09-10 vs CB 2026-09-22 (12 days). Trust CB 2026-09-22. Outside window, past.
- C-0BBE3E60: CZ 2027-09-26 vs CB 2026-09-26 (365 days). Trust CB 2026-09-26. Outside window, past.
- C-0F5D2323: CZ 2026-09-10 vs CB 2026-09-29 (19 days). Trust CB 2026-09-29. Outside window, past.

No disagreements in the 10 in-window renewals below; date used = agreed CZ/CB date.

Risk rule used for this brief only: High = seat util <60% or Jun-to-Aug active users down >10%; Medium = util 60-70% or down 0-10%; Low = util >70% and Jun-to-Aug flat/up. Seat util = seats_used / seats. Trend = Aug minus Jun / Jun.

Renewals in window (10):

1. C-0BC34584 | Cole Ingram | $16,740 | 2026-10-22 | util 327/494 = 66.2% | trend 104 to 106 = +2 (+1.9%) | Medium — lowest seat util in window despite stable usage.
2. C-0B7A7546 | Elena Sinclair | $35,062 | 2026-10-25 | util 182/205 = 88.8% | trend 64 to 63 = -1 (-1.6%) | Low — high util with essentially flat usage.
3. C-0B369871 | Dana Mercer | $85,128 | 2026-10-29 | util 317/422 = 75.1% | trend 326 to 333 = +7 (+2.1%) | Low — solid util with growing usage.
4. C-0B144C78 | Cole Ingram | $30,899 | 2026-11-02 | util 169/224 = 75.4% | trend 101 to 106 = +5 (+5.0%) | Low — solid util with growing usage.
5. C-0FC4DBB8 | Elena Sinclair | $94,732 | 2026-11-05 | util 356/464 = 76.7% | trend 189 to 193 = +4 (+2.1%) | Low — solid util with growing usage.
6. C-0D5BBE3A | Dana Mercer | $39,740 | 2026-11-09 | util 85/102 = 83.3% | trend 88 to 91 = +3 (+3.4%) | Low — high util with growing usage.
7. C-0FB9D5AF | Cole Ingram | $63,158 | 2026-11-13 | util 144/199 = 72.4% | trend 173 to 176 = +3 (+1.7%) | Low — solid util with stable/growing usage.
8. C-0B344485 | Elena Sinclair | $64,384 | 2026-11-16 | util 224/287 = 78.0% | trend 238 to 244 = +6 (+2.5%) | Low — solid util with growing usage.
9. C-0CB2C1B4 | Dana Mercer | $40,628 | 2026-11-20 | util 386/473 = 81.6% | trend 47 to 49 = +2 (+4.3%) | Low — high seat util with stable active users.
10. C-22170CA1 | Cole Ingram | $45,646 | 2026-11-24 | util 251/294 = 85.4% | trend 143 to 146 = +3 (+2.1%) | Low — high util with growing usage.

Totals:

Total ARR renewing in window = 16,740 + 35,062 + 85,128 + 30,899 + 94,732 + 39,740 + 63,158 + 64,384 + 40,628 + 45,646 = $516,117.

ARR at risk (High only) = $0. ARR rated Medium = $16,740 (C-0BC34584), 3.2% of renewing ARR (16,740 / 516,117 = 3.24%).

Note: 5 past multi-year renewals and 5 past October single-year renewals (C-0EC6999D through C-0F9F8F13) are excluded from totals as outside the forward window; several excluded accounts show low util and declining usage but no trusted future date was provided to re-include them.
ticket-theme-synthesisPASS 1.00
Plain-English question: What are the real themes in this quarter's support tickets, ignoring the existing tags?
Prompt — what the model saw
Synthesize the quarter's support tickets into 4 to 7 themes. Do not trust existing tags; read the text. Per theme: name, count, share, distinct accounts, ARR affected, two ticket ids, one-line recommendation. Separate broad patterns from single-account noise and rank by ARR exposure, not volume.
cost $0.0466 · 88s · in 9,913 / out 6,524 tok
✓ theme_count_range✓ counts_verifiable✓ single_account_flagged✓ arr_ranked✓ ticket_ids

✓ Correct Answer (ground truth)

Plain-English answer: 80 tickets in 4-7 themes — points-not-posting leads (20 tickets, 25%, $31,100 ARR affected) — each with counts, distinct accounts, ARR, and a recommendation.
The answer in one line: total_tickets = 80; quarter_window = 2026-06-01 through 2026-08-31
total_tickets80
noteexisting tags are noisy/unreliable; classify by text
quarter_window2026-06-01 through 2026-08-31
ranking_by_arr_exposurehris_provisioning, redemption_failures, billing_dispute, points_not_posting, slack_sync
sample_ticket_ids80 items — e.g. IC-460004, IC-460016, IC-460001, IC-460041
single_account_noise_themebilling_dispute
themes{"points_not_posting": {"count": 20, "share_pct": 25.0, "distinct_accounts": 9, "arr_affected": "31100.00", "example_ticket_ids": ["IC-460001", "IC-460002"], "single_account": false}, "slack_sync": {"
graded checkstheme_count_range · counts_verifiable · single_account_flagged · arr_ranked · ticket_ids

Model's actual answer

show the model's full answer
Total tickets: 80. Share = theme count / 80. ARR affected = sum of distinct account ARRs in theme, to avoid double-counting repeat tickets from the same account.

Ranked by ARR exposure:

1. HRIS provisioning failure — broad pattern
Count: 12. Share: 12/80 = 15.0%. Distinct accounts: 3.
ARR affected: 36,000 + 48,000 + 30,000 = $114,000.
Accounts: C-0B2213A9, C-0DDFC9A7, C-0F6C0F34.
Example tickets: IC-460059, IC-460060.
Recommendation: Audit HRIS sync job and silent-failure logging for new-hire provisioning.

2. Rewards redemption failure — broad pattern
Count: 18. Share: 18/80 = 22.5%. Distinct accounts: 7.
ARR affected: 10,300 + 10,700 + 8,900 + 9,600 + 8,700 + 9,600 + 11,000 = $68,800.
Accounts: C-0B0F1BAB, C-0B827671, C-0CEF69FD, C-0D9CA315, C-0F876796, C-0FCCD2DF, C-14264ABD.
Example tickets: IC-460025, IC-460024.
Recommendation: Fix checkout / gift-card fulfillment and stop deducting points on failed orders.

3. Billing / invoice error — single-account noise
Count: 16. Share: 16/80 = 20.0%. Distinct accounts: 1.
ARR affected: $52,000.
Account: C-0E9C27D1 alone accounts for all 16 tickets.
Example tickets: IC-460071, IC-460069.
Recommendation: Resolve seat-count and renewal-tier billing for C-0E9C27D1 with account-level correction, not a product fix.

4. Points posting failure — broad pattern
Count: 20. Share: 20/80 = 25.0%. Distinct accounts: 9.
ARR affected: 2,900 + 2,700 + 4,500 + 4,500 + 3,400 + 3,500 + 4,200 + 2,500 + 2,900 = $31,100.
Accounts: C-0B2895EF, C-0BE96399, C-0BF20542, C-0D0B047C, C-0D284E42, C-0D3278C7, C-0D6CC8E3, C-0DD0626C, C-21FEBCBB.
Example tickets: IC-460004, IC-460016.
Recommendation: Investigate recognition-delivered to points-posted pipeline delay / drop.

5. Slack integration failure — broad pattern
Count: 14. Share: 14/80 = 17.5%. Distinct accounts: 4.
ARR affected: 4,400 + 3,900 + 5,400 + 5,200 = $18,900.
Accounts: C-0B843542, C-0BA71F12, C-10A56B0F, C-8C2E8F00.
Example tickets: IC-460041, IC-460047.
Recommendation: Fix Slack sync disconnects, toggle reset, and slash-command errors plus re-auth persistence.

Counts check: 12 + 18 + 16 + 20 + 14 = 80.
Note: Existing tags were ignored; themes above are grouped only by body_text wording.
marketing 5 tests
case-study-matchPASS 1.00
Plain-English question: Which three existing customers are the best case-study matches for this prospect?
Prompt — what the model saw
Given the prospect, rank the three most similar existing customers with public case studies for use as social proof. Similarity on industry, size band, use case, region. Cite the fields that drove each match. Do not name any customer without a case study and never include billing data or contact names.
cost $0.0135 · 75s · in 665 / out 2,285 tok
✓ top3✓ decoys_excluded✓ cites_fields✓ no_billing

✓ Correct Answer (ground truth)

Plain-English answer: Three ranked matches on industry, size, use case, and region (e.g. C-11C31562), with the higher-scoring decoy explicitly excluded for a mismatched field.
The answer in one line: prospect_alias = C-82AF3719
constraintsno_billing_data, no_contact_names, only_customers_with_has_case_study_true_named
decoys_excludedcompany_alias=C-D6217CAA; similarity_score=4; reason=no_case_study | company_alias=C-C153868F; similarity_score=4; reason=no_case_study
prospect_aliasC-82AF3719
prospect_fields_usedindustry, size_band, use_case, region
top3company_alias=C-11C31562; similarity_score=3 | company_alias=C-64171065; similarity_score=3 | company_alias=C-A13C193D; similarity_score=3
graded checkstop3 · decoys_excluded · cites_fields · no_billing

Model's actual answer

show the model's full answer
Prospect C-82AF3719: Technology / Mid-Market / employee_recognition / NA-West

Eligible pool: has_case_study=true only. Score = industry + size_band + use_case + region, 1 per exact match.

Eligible scores:
C-FEFCC020: 0+0+0+0 = 0
C-11209339: 0+0+0+0 = 0
C-9D69D147: 0+1+0+1 = 2
C-11C31562: 0+1+1+1 = 3
C-CD4829A7: 1+1+0+0 = 2
C-0CE315B2: 0+0+0+0 = 0
C-64171065: 1+1+1+0 = 3
C-A13C193D: 1+1+0+1 = 3

Rank - three-way tie at 3/4, ordered to favor use_case match, then industry match:

1. C-64171065 - 3/4: industry=Technology, size_band=Mid-Market, use_case=employee_recognition. Differ: region=NA-East vs NA-West.

2. C-11C31562 - 3/4: size_band=Mid-Market, use_case=employee_recognition, region=NA-West. Differ: industry=Manufacturing vs Technology.

3. C-A13C193D - 3/4: industry=Technology, size_band=Mid-Market, region=NA-West. Differ: use_case=retention vs employee_recognition.
channel-attribution-mathPASS 1.00
Plain-English question: Compute cost per SQM, cost per SQO, and pipeline per dollar for every channel over six months.
Prompt — what the model saw
Compute channel performance for the trailing 6 months. Paid: spend, SQMs, SQOs, cost per SQM, cost per SQO, SQM-to-SQO rate, pipeline amount, pipeline per dollar. Organic: volume, SQO rate, pipeline. Report a channel with spend and zero SQMs as undefined, not zero. Flag rows where SQO date precedes SQM date. Finish with a reallocation recommendation and your confidence given sample sizes.
cost $0.0339 · 87s · in 4,012 / out 5,201 tok
✓ undefined_channel✓ undefined_not_zero✓ flagged_rows✓ best_channel✓ reallocation

✓ Correct Answer (ground truth)

Plain-English answer: LinkedIn Ads at $960/SQM and $3,000/SQO, organic search at $90,000 pipeline on zero spend, paid social flagged at $18,000 with zero SQMs, and a channel winner named.
The answer in one line: best_pipeline_per_dollar_channel = paid_search
best_pipeline_per_dollar_channelpaid_search
confidence_notewebinars and referral have small SQM samples (<20); treat rates as directional.
flagged_rows_sqo_before_sqmCT-000041, CT-000044
months2026-03, 2026-04, 2026-05, 2026-06, 2026-07, 2026-08
per_channel{"linkedin_ads": {"spend_usd": 24000, "sqms": 25, "sqos": 8, "pipeline_amount": 96000, "cost_per_sqm": 960.0, "cost_per_sqo": 3000.0, "sqm_to_sqo_rate": 0.32, "pipeline_per_dollar": 4.0}, "organic_sea
reallocation_recommendationfrom=paid_social; to=paid_search; rationale=paid_social has spend but zero SQMs (cost per SQM undefined, not zero); paid_search has the highest pipeline per dollar.
undefined_channelspaid_social
graded checksundefined_channel · undefined_not_zero · flagged_rows · best_channel · reallocation

Model's actual answer

show the model's full answer
Trailing 6 months: 2026-03 to 2026-08. All 122 contacts have sqm_date in range. SQM = row with sqm_date. SQO = row with non-blank sqo_date.

Paid

paid_search
spend = 6,000 x 6 = 36,000
SQMs = 40, SQOs = 18: CT-000001, CT-000002, CT-000003, CT-000004, CT-000005, CT-000006, CT-000007, CT-000008, CT-000009, CT-000010, CT-000011, CT-000012, CT-000013, CT-000014, CT-000015, CT-000016, CT-000017, CT-000018
cost per SQM = 36,000 / 40 = 900
cost per SQO = 36,000 / 18 = 2,000
SQM-to-SQO rate = 18 / 40 = 45.0%
pipeline = 18 x 40,000 = 720,000
pipeline per dollar = 720,000 / 36,000 = 20.00

linkedin_ads
spend = 4,000 x 6 = 24,000
SQMs = 25, SQOs = 8: CT-000041, CT-000042, CT-000043, CT-000044, CT-000045, CT-000046, CT-000047, CT-000048
cost per SQM = 24,000 / 25 = 960
cost per SQO = 24,000 / 8 = 3,000
SQM-to-SQO rate = 8 / 25 = 32.0%
pipeline = 8 x 12,000 = 96,000
pipeline per dollar = 96,000 / 24,000 = 4.00

paid_social
spend = 3,000 x 6 = 18,000
SQMs = 0, SQOs = 0
cost per SQM = undefined (spend with zero SQMs)
cost per SQO = undefined
SQM-to-SQO rate = undefined
pipeline = 0
pipeline per dollar = 0 / 18,000 = 0.00

webinars
spend = 1,500 x 6 = 9,000
SQMs = 12, SQOs = 5: CT-000066, CT-000067, CT-000068, CT-000069, CT-000070
cost per SQM = 9,000 / 12 = 750
cost per SQO = 9,000 / 5 = 1,800
SQM-to-SQO rate = 5 / 12 = 41.7%
pipeline = 5 x 12,000 = 60,000
pipeline per dollar = 60,000 / 9,000 = 6.67

Organic (no spend data provided)

organic_search
volume = 30
SQOs = 10: CT-000078, CT-000079, CT-000080, CT-000081, CT-000082, CT-000083, CT-000084, CT-000085, CT-000086, CT-000087
SQO rate = 10 / 30 = 33.3%
pipeline = 10 x 9,000 = 90,000

referral
volume = 15
SQOs = 6: CT-000108, CT-000109, CT-000110, CT-000111, CT-000112, CT-000113
SQO rate = 6 / 15 = 40.0%
pipeline = 6 x 8,000 = 48,000

Date flags: SQO precedes SQM
CT-000044, linkedin_ads, sqm_date 2026-07-23, sqo_date 2026-07-18
CT-000041, linkedin_ads, sqm_date 2026-06-14, sqo_date 2026-06-09

Reallocation recommendation
Cut paid_social spend to zero until it produces SQMs; it consumed 18,000 with zero SQMs. Shift those dollars to paid_search first, webinars second. paid_search has lowest cost per SQO at 2,000 and highest pipeline per dollar at 20.00. webinars has lowest cost per SQM at 750 and second-lowest cost per SQO at 1,800. Reduce linkedin_ads: highest cost per SQO at 3,000 and lowest paid pipeline per dollar at 4.00, plus 2/8 SQOs have date errors.

Confidence: moderate. Sample sizes are small: paid_search 40/18, linkedin_ads 25/8, webinars 12/5, organic_search 30/10, referral 15/6, paid_social 0. Rates and unit costs will move materially with a few conversions either way, and linkedin_ads metrics are affected by the 2 flagged date rows.
competitor-battlecard-updatePASS 1.00
Plain-English question: Update the Rivally battlecard with sourced pricing and where each side wins.
Prompt — what the model saw
Update the battlecard for the competitor. Sections: one-line positioning, pricing with source and date (newer source wins, note the conflict), where they win, where we win, objections and responses, recent changes, our 12-month win/loss record against them. Cite a snippet id for every factual claim. Rep opinion on a call is not a fact about the competitor. Anything from the old card you cannot re-source gets marked unverified.
cost $0.0183 · 69s · in 1,313 / out 3,235 tok
✓ competitor_named✓ pricing✓ win_loss✓ unverified_marked✓ citations

✓ Correct Answer (ground truth)

Plain-English answer: Rivally at $7 per user per month (the August source wins over the stale $5, conflict noted), a 13-7 win/loss record, and two unverified old claims flagged.
The answer in one line: competitor = Rivally
citation_ids_available25 items — e.g. S01, S02, S03, S04
competitorRivally
pricingvalue_per_user_per_month=7; source_snippet=S17; source_date=2026-08-12
rep_opinion_snippet_ids_not_factsS09, S21
unverified_old_claimsRivally lacks a Slack integration., Rivally was acquired by WorkHuman in 2025.
win_loss_12mowins=13; losses=7
graded checkscompetitor_named · pricing · win_loss · unverified_marked · citations

Model's actual answer

show the model's full answer
Battlecard: Rivally

1. One-line positioning
Points-based recognition feed with lightweight survey add-on, noted for fast mid-market setup. [S02, S04, S06]

2. Pricing (newer source wins)
Current list: $7 per user/month, annual billing required, Recognition Starter tier, per pricing page dated 2026-08-12. [S17]
Conflict note:
- $5 per user/month, annual billing required, dated 2026-01-20. [S03]
- Still $5 per user/month for Recognition Starter, dated 2026-04-01. [S08]
- Deal mention dated 2026-06-02: quoted $6.50/user/mo to a 500-seat prospect, annual term. [S13]
- Deal mention dated 2026-08-14: prospect says quoted $7/user/mo list, offered 15% discount for 3-year term. [S18]
Use [S17] as current; [S03, S08, S13, S18] are older/conflicting.

3. Where they win
- Setup under a week; Slack integration worked out of the box. [S04]
- Recognition feed praised as engaging. [S02, S16]
- Strong for distributed EU teams; multi-language support praised. [S12]
- EU data residency pitched, then announced as generally available; Dublin office opened. [S05, S15]
- Support response time praised (under 4 hours). [S22]

4. Where we win
- Analytics/reporting limited/basic vs enterprise tools; 800-seat prospect picked Bonusly over Rivally citing analytics depth. [S02, S07, S25]
- Lacks SCIM provisioning; manual user management painful. [S10]
- Admin tooling lags peers; admin console lacks bulk recognition editing. [S16, S24]
- Analytics exports are CSV-only. [S20]
- Rewards catalog in EMEA is thinner than US catalog. [S14]

5. Objections and responses
- Objection: Need EU coverage / multi-language for distributed EU team [S12] / EU data residency [S05, S15].
  Response: Note tradeoff: EMEA rewards catalog thinner than US [S14]; no SCIM, manual user management painful [S10].
- Objection: Want fast setup / Slack out of the box [S04] / engaging feed [S02, S16].
  Response: Note tradeoff: limited analytics [S02], basic reporting dashboards [S07], admin tooling lags [S16], no bulk recognition editing [S24].
- Objection: Rivally quoted $6.50/user/mo [S13] or $7 list with 15% discount for 3-year term [S18].
  Response: Compare to current list $7/user/mo annual billing [S17]; Pulse is priced as add-on, not bundled [S23].

6. Recent changes
- 2026-09-01: Rivally Pulse add-on exits beta; priced as add-on, not bundled. [S23]
- 2026-08-20: Microsoft Teams app v2 in public preview. [S19]
- 2026-08-12: Pricing page updated to $7 per user/month, annual billing required. [S17]
- 2026-07-01: Dublin office opened; EU data residency generally available. [S15]
- 2026-05-09: Hired ex-Workday VP EMEA to lead European expansion. [S11]
- 2026-03-05: Launched Rivally Pulse lightweight engagement survey add-on. [S06]
- 2025-11-04: Announced $40M Series C led by Northgate Ventures. [S01]

7. Our 12-month win/loss record vs Rivally
Scope: 2025-09 through 2026-08 inclusive (all 20 rows provided).
13 wins, 7 losses in 20 deals. Arithmetic: 13+7=20; 13/20=65% win rate.

Wins (13): Deal-A9FD43, Deal-7AA785, Deal-44C524, Deal-0D0CD6, Deal-D5B790, Deal-5C636E, Deal-67BE14, Deal-1B6969, Deal-F03E7B, Deal-072E31, Deal-F65C8F, Deal-E46EAB, Deal-1D2392
Losses (7): Deal-7767F5, Deal-5645A5, Deal-C6FFAA, Deal-D263E0, Deal-935746, Deal-9066A6, Deal-72A02F

8. Old card verification
- Points-based recognition for mid-market: re-sourced [S02, S04].
- Starts at $5/user/mo annual: superseded, now $7 [S17]; old $5 [S03, S08].
- Strong in EU enterprise with multi-language: re-sourced [S12].
- Rivally lacks a Slack integration: UNVERIFIED / contradicted - Slack integration worked out of the box [S04].
- Rivally was acquired by WorkHuman in 2025: UNVERIFIED - no supporting snippet in data provided.
- Excluded as rep opinion, not competitor fact: AE opinion UI is clunky [S09]; AE opinion thinks discounting aggressively [S21].
nurture-sequence-diagnosisPASS 1.00
Plain-English question: What is broken in each email sequence — rates, overlaps, tracking errors?
Prompt — what the model saw
Review the sequences. Per sequence: sent, open rate, reply rate, meeting rate, weakest step. Identify tracking errors (opened above sent), audience overlap between sequences, and the failure mode for anything under 2 percent reply. One change per weak sequence and which to fix first. Under 350 words.
cost $0.0269 · 57s · in 11,253 / out 2,320 tok
✓ tracking_error✓ overlap_pair✓ weakest_step✓ fix_priority

✓ Correct Answer (ground truth)

Plain-English answer: Per-sequence open, reply, and meeting rates with the weakest step (all three weakest at step 3), an opened-above-sent tracking error, and audience overlap flagged.
The answer in one line: fix_priority_first = Cold Outbound - HR Leaders
all_pairwise_overlaps['Cold Outbound - HR Leaders', 'Cold Outbound - People Ops'], ['Expansion Nurture', 'New Logo Nurture']
audience_overlap_pairCold Outbound - HR Leaders, Cold Outbound - People Ops
failure_modeCold Outbound - HR Leaders=opens healthy (~37%) but replies near zero from step 1 -> body/CTA not landing, not a deliverability or subject-line problem
fix_priority_firstCold Outbound - HR Leaders
per_sequence{"New Logo Nurture": {"sent": 1386, "opened": 490, "replied": 90, "meetings": 27, "open_rate": 0.3535, "reply_rate": 0.0649, "meeting_rate": 0.0195, "weakest_step": 3}, "Expansion Nurture": {"sent": 8
tracking_errorsequence=Expansion Nurture; step=2; sent=300; opened=340; issue=opened exceeds sent
under_2pct_replyCold Outbound - HR Leaders
graded checkstracking_error · overlap_pair · weakest_step · fix_priority

Model's actual answer

show the model's full answer
Per sequence totals (sum of steps):

New Logo Nurture: sent 500+458+428=1,386. Opened 210+160+120=490. Open rate 490/1,386=35.4%. Replied 42+30+18=90. Reply rate 90/1,386=6.5%. Meetings 12+9+6=27. Meeting rate 27/1,386=1.9%. Weakest step: Step 3 — 120/428=28.0% open, 18/428=4.2% reply, 6/428=1.4% meeting.

Expansion Nurture: sent 300+300+275=875. Opened 130+340+95=565. Open rate 565/875=64.6% inflated. Replied 22+25+12=59. Reply rate 59/875=6.7%. Meetings 5+4+3=12. Meeting rate 12/875=1.4%. Weakest step: Step 3 — 95/275=34.5% open, 12/275=4.4% reply.

Cold Outbound - HR Leaders: sent 600+595+590=1,785. Opened 240+175+130=545. Open rate 545/1,785=30.5%. Replied 5+2+1=8. Reply rate 8/1,785=0.45%. Meetings 0/1,785=0%. Weakest step: Step 3 — 1/590=0.17% reply, 0 meetings; all steps <2% reply.

Cold Outbound - People Ops: sent 400+386+377=1,163. Opened 150+110+80=340. Open rate 340/1,163=29.2%. Replied 14+9+6=29. Reply rate 29/1,163=2.5%. Meetings 3+2+1=6. Meeting rate 6/1,163=0.5%. Weakest step: Step 3 — 80/377=21.2% open, 6/377=1.6% reply.

Tracking error: Expansion Nurture Step 2 opened 340 > sent 300 = 113.3%, impossible.

Audience overlap: no contact_key should repeat. Found: CT-000301 and CT-000624 in both New Logo Nurture and Expansion Nurture; CT-000849, CT-000884, CT-001033, CT-001101, CT-001103, CT-001153, CT-001159, CT-001217, CT-001227, CT-001255, CT-001285, CT-001345 in both Cold Outbound - HR Leaders and Cold Outbound - People Ops.

Failure mode <2% reply: Cold Outbound - HR Leaders only. Opens ~30% so deliverability held, but 8/1,785 replies and 0 meetings with declining Step 1 to 3 (0.83% to 0.34% to 0.17%) = message-market mismatch, not follow-up fatigue.

Fix first: Cold Outbound - HR Leaders. Change: pause Steps 2-3, rewrite Step 1 offer. Second: Expansion Nurture — fix Step 2 open tracking then rewrite Step 3. Third: Cold Outbound - People Ops — replace Step 3 with break-up / new angle.
weekly-marketing-goals-rollupPASS 1.00
Plain-English question: Are we on pace on the quarter's marketing goals?
Prompt — what the model saw
Produce the weekly marketing goals update for the active quarter: SQMs, SQOs, DS2s, closed-lost MIA rate, same-quarter close count, active pipeline coverage against target. For each: QTD actual, target, delta, pace (on/behind/ahead given days elapsed). One paragraph on what moved this week.
cost $0.0102 · 50s · in 273 / out 1,621 tok
✓ metrics_present✓ deltas✓ coverage_ratio✓ pace✓ paragraph

✓ Correct Answer (ground truth)

Plain-English answer: SQMs ahead of pace, SQOs on pace, DS2s behind (35 short of expected at day 66 of 92), with deltas and same-quarter closes.
The answer in one line: days_in_quarter = 92; days_elapsed = 66; coverage_ratio_active_pipeline = 0.75; elapsed_fraction = 0.7174 (+1 more below)
days_in_quarter92
coverage_ratio_active_pipeline0.75
days_elapsed66
elapsed_fraction0.7174
metrics{"SQMs": {"qtd_actual": 230, "target": 300, "delta": -70, "expected_at_day_elapsed": 215.22, "pace": "ahead"}, "SQOs": {"qtd_actual": 84, "target": 120, "delta": -36, "expected_at_day_elapsed": 86.09,
pace_ruleexpected = target * days_elapsed/days_in_quarter; within +/-5% of expected = on, above = ahead, below = behind; lower_better metrics invert.
this_week_paragraph_required1
graded checksmetrics_present · deltas · coverage_ratio · pace · paragraph

Model's actual answer

show the model's full answer
Q3-2026 — 66 of 92 days elapsed = 66/92 = 71.7% of quarter.

SQMs: QTD 230 / Target 300 / Delta 230-300 = -70. Expected pace 300*66/92 = 19,800/92 = 215.2. Actual 230 > 215.2, 76.7% vs 71.7% time = ahead.

SQOs: QTD 84 / Target 120 / Delta 84-120 = -36. Expected 120*66/92 = 7,920/92 = 86.1. Actual 84 < 86.1, 70.0% vs 71.7% = behind.

DS2s: QTD 40 / Target 75 / Delta 40-75 = -35. Expected 75*66/92 = 4,950/92 = 53.8. Actual 40 < 53.8, 53.3% vs 71.7% = behind.

Closed-lost MIA rate: 5/25 = 0.20 / Target 0.10 / Delta 0.20-0.10 = +0.10 (10pp over, lower_better). Actual exceeds target = behind.

Same-quarter closes: QTD 10 / Target 20 / Delta 10-20 = -10. Expected 20*66/92 = 1,320/92 = 14.3. Actual 10 < 14.3, 50.0% vs 71.7% = behind.

Active pipeline coverage: 3,000,000 / 4,000,000 = 0.75x / Target 1.00x / Delta 3,000,000-4,000,000 = -1,000,000. Expected linear 4,000,000*66/92 = 2,869,565. Actual 3,000,000 > 2,869,565 = ahead on linear pace, still -1,000,000 short of target.

What moved this week: No prior-week snapshot was provided, so weekly movement cannot be determined from the data given.
communication 5 tests
ceo-slack-compression0.80
Plain-English question: Compress the forecast analysis into one Slack message the CEO can read in ten seconds.
Prompt — what the model saw
Compress the forecast analysis below into a single Slack message for the CEO. Rules: at most three sentences; under 80 words; lead with the decision or the so-what; keep every distinct number that matters and the one caveat that changes the conclusion; cut any sentence that does not carry a claim, a number, or a directive. No em dashes, no throat-clearing phrases.
cost $0.0144 · 52s · in 553 / out 2,538 tok
✓ max_3_sentences✓ under_80_words✓ weighted_present✗ caveat_present✓ no_em_dash

✓ Correct Answer (ground truth)

Plain-English answer: Three sentences, under 80 words, decision first, every distinct number kept plus the one caveat — all checked by deterministic text rules.
The answer in one line: weighted_number = 115976; must_keep = data-quality caveat — deleting the bad news fails
weighted_number115,976
limitmax 3 sentences, max 80 words, no em-dashes
must_keepdata-quality caveat — deleting the bad news fails
graded checksmax_3_sentences · under_80_words · weighted_present · caveat_present · no_em_dash

Model's actual answer

show the model's full answer
Do not lock Q3 at $115,976.75 yet because all 7 COMMIT deals lack why-buy.
$44,729 COMMIT (7) + 35% x $203,565 BEST_CASE (24) = $44,729 + $71,247.75 = $115,976.75; 54 of 86 deals in quarter.
$227,575 across 32 deals falls after 2026-09-30 including COMMIT Deal-D348E1 ($13,770 on 2026-10-15).
stalled-deal-followup-emailPASS 1.00
Plain-English question: Write a follow-up email for this stalled deal — under 120 words, one prior touch, one ask.
Prompt — what the model saw
Write a follow-up email for this stalled deal. Under 120 words. Reference one specific prior touch from the engagement history, make one clear ask, and match the tone of the prior thread. No invented details.
cost $0.0121 · 80s · in 382 / out 2,046 tok
✓ word_cap✓ references_touch✓ single_ask

✓ Correct Answer (ground truth)

Plain-English answer: An email that references the July 28 milestone-awards demo, makes one clear ask, and invents nothing — Deal-0D2F7A, 31 days since last engagement.
The answer in one line: amount = 5100; word_cap = 120; days_since_last_engagement = 31; deal_alias = Deal-0D2F7A (+4 more below)
amount5,100
days_since_last_engagement31
word_cap120
allowed_facts14 items — e.g. Deal-0D2F7A, $5,100, DS3, Alex Franklin
allowed_newENG-00001, ENG-00002, ENG-00003, ENG-00004, ENG-00005
deal_aliasDeal-0D2F7A
must_referenceengagement_id=ENG-00002; date=2026-07-28; type=meeting; why=most substantive prior touch; concrete prospect reactions to milestone awards and points catalog
ownerAlex Franklin
single_cta1
stageDS3
tonewarm, concise, professional (matches prior thread)
graded checksword_cap · references_touch · single_ask

Model's actual answer

show the model's full answer
Deal: Deal-0D2F7A

Subject: Re: July 28 demo + pricing for 150 seats

Hi People team,

Following up on my August 5 recap of our July 28 demo — you had a strong reaction to automated milestone awards and the points catalog, and asked for pricing for 150 seats.

Are you open to a 15-minute call this week to confirm next steps?

Thanks,
Alex Franklin

Word count: 33 + 13 + 3 body + 8 subject = 57 words, under 120.
Missing data: recipient name not provided in files, used role-based greeting.
funnel-digest-paragraphPASS 1.00
Plain-English question: Write the weekly GTM digest — one paragraph per team, every number traceable.
Prompt — what the model saw
Write the weekly GTM digest: one paragraph per team (Marketing, Sales, CS, PLG) in Bonusly brand voice. Every number must trace to the extracts. No customer contact names, no employee performance commentary, no compensation. Four paragraphs, under 400 words total.
cost $0.0091 · 46s · in 240 / out 1,370 tok
✓ four_paragraphs✓ word_cap✓ teams

✓ Correct Answer (ground truth)

Plain-English answer: Four paragraphs (Marketing, Sales, CS, PLG) using only the allowed numbers, no contact names, no performance commentary, under 400 words.
The answer in one line: word_cap = 400
word_cap400
allowed_numbers16 items — e.g. 2, 3, 9, 08
bannedcustomer contact names, employee performance commentary, compensation
required_paragraphsMarketing, Sales, CS, PLG
graded checksfour_paragraphs · word_cap · teams

Model's actual answer

show the model's full answer
Marketing delivered 46 SQMs against a 52 target (46/52=88.5% attainment, 52-46=6 SQM gap) with the webinar channel contributing 18 of those SQMs (18/46=39.1% share), while paid search cost per SQM held at 150 dollars.

Sales converted 14 SQOs and set 9 DS2 meetings, created 310000 dollars in new pipeline, and closed 3 same-quarter deals to keep recognition moving from interest to impact.

CS saved 2 renewals this week with team NPS at 61, carrying 3 open red-flag accounts into next week where steady follow-through and care can make the difference.

PLG added 412 new signups with activation at 31 percent (412x0.31=127.72 activated), and 38 companies reached the aha moment of 10 recognition gives to build momentum from the first week.
partner-digest-sectionPASS 1.00
Plain-English question: Write the partner digest so every partner in the roster appears exactly once.
Prompt — what the model saw
Write the partner digest for the period. Every partner in the roster appears once: active plays get status with numbers, quiet partners get one line. Partner-sourced pipeline count and amount must match the deal data. Nothing omitted, nothing added.
cost $0.0074 · 37s · in 428 / out 911 tok
✓ all_partners✓ pipeline_amount✓ quiet_one_line

✓ Correct Answer (ground truth)

Plain-English answer: Four active partners with status and numbers, four quiet partners with one line each, and partner-sourced pipeline that reconciles to the deal data.
The answer in one line: rule = every roster partner named exactly once; quiet partners get one line; no partners outside roster.
active_no_dealsWorkWell Group
partner_sourced_pipelinecount=5; amount=550000
per_partner_pipeline{"Apex Rewards Co": {"count": 2, "amount": 275000}, "HRCloud Partners": {"count": 1, "amount": 140000}, "CultureBridge": {"count": 2, "amount": 135000}}
quiet_partnersRecogniq, KudosWave, PeopleFirst Advisors, TotalPerk
rosterpartner_name=Apex Rewards Co; status=active | partner_name=HRCloud Partners; status=active | partner_name=CultureBridge; status=active | partner_name=WorkWell Group; status=active | partner_name=Recogniq; status=quiet | partner_name=KudosWave; status=quiet … (+2 more)
ruleevery roster partner named exactly once; quiet partners get one line; no partners outside roster.
graded checksall_partners · pipeline_amount · quiet_one_line

Model's actual answer

show the model's full answer
Partner digest: 2026-08-24 to 2026-09-04

Partner-sourced pipeline: 5 deals, $550,000
Arithmetic: 180,000 + 95,000 + 140,000 + 60,000 + 75,000 = 550,000

Active:

- Apex Rewards Co: 2 sourced opps, $275,000. Deal-DDAAF2 ($180,000) + Deal-2CF33E ($95,000) = $275,000. Both DS1, both UTM Source = Partner. Co-webinar locked for 09-15.
- HRCloud Partners: 1 sourced opp, $140,000. Deal-F1CDA5 ($140,000). Moved to DS2 after security review closed.
- CultureBridge: 2 sourced opps, $135,000. Deal-096E1D ($60,000) + Deal-067213 ($75,000) = $135,000. Both early stage from lunch-and-learn.
- WorkWell Group: 0 sourced deals this period. Joint playbook restart planned for Q4; planning call booked for 09-09.

Quiet:

- Recogniq: No sourced deals this period.
- KudosWave: No sourced deals this period.
- PeopleFirst Advisors: No sourced deals this period.
- TotalPerk: No sourced deals this period.
rfp-answer-from-policyPASS 1.00
Plain-English question: Answer the 10 RFP items from the policy excerpts only — no guessing.
Prompt — what the model saw
Answer the 10 questionnaire items from the policy excerpts only. Cite the excerpt id for every answer. Where the excerpts do not answer the question, mark it unanswerable and say what document would; do not guess. Tone: vendor response, direct.
cost $0.0076 · 40s · in 431 / out 965 tok
✓ answered_count✓ unanswerable_flagged✓ citations✓ no_guess

✓ Correct Answer (ground truth)

Plain-English answer: Seven answered with excerpt citations (Q1-Q7), three flagged unanswerable with the document that would answer them (Q8-Q10).
The answer in one line: answered_count = 7; rule = unanswerable items must be flagged and the document that would answer them named; do not guess.
answered_count7
answer_map{"Q1": ["P1"], "Q2": ["P1"], "Q3": ["P2"], "Q4": ["P3"], "Q5": ["P4"], "Q6": ["P5"], "Q7": ["P6"]}
ruleunanswerable items must be flagged and the document that would answer them named; do not guess.
unanswerableQ8, Q9, Q10
valid_citation_idsP1, P2, P3, P4, P5, P6, P7, P8
graded checksanswered_count · unanswerable_flagged · citations · no_guess

Model's actual answer

show the model's full answer
Q1: Yes. Customer data is encrypted at rest using AES-256. [P1]

Q2: Yes. Data in transit is encrypted with TLS 1.2 or higher. [P1]

Q3: Yes. Bonusly maintains a SOC 2 Type II report, renewed annually. The report is available to prospects under NDA. [P2]

Q4: Customer data is retained for the duration of the contract plus 90 days, after which it is deleted from production systems. [P3]

Q5: The current list is maintained at trust.bonusly.com. Customers receive 30 days notice before a new subprocessor is added. [P4]

Q6: Yes. SAML 2.0 single sign-on is available on the Enterprise plan. [P5]

Q7: Production databases are backed up daily. Backups are encrypted and retained for 35 days. [P6]

Q8: Unanswerable from the provided excerpts. P1–P8 do not address ISO 27001 certification. Would require compliance certification documentation.

Q9: Unanswerable from the provided excerpts. P1–P8 do not state a contractual uptime SLA percentage. Would require the MSA / SLA documentation.

Q10: Unanswerable from the provided excerpts. P1–P8 do not address HIPAA or a Business Associate Agreement. Would require legal / HIPAA compliance documentation.
ops-maintenance 5 tests
skill-file-reconciliationPASS 1.00
Plain-English question: Audit a skill set against its manifest and flag every conflict with a severity and an action.
Prompt — what the model saw
Reconcile the skill set below against its manifest. Find and report (with severity CRITICAL/WARNING/INFO and an action type TRIM_DESC, UPDATE_BODY, DELETE_SKILL, MERGE, or REVIEW): (1) any two skills whose ALWAYS-trigger phrases overlap/duplicate, (2) any circular delegation chain between skills (name it), (3) any delegation target that does not exist (dangling, name it), (4) any version conflict and which skill should survive, (5) how many manifest descriptions exceed 1,024 characters, (6) any hardcoded page ids, dates, or person names in skill bodies, (7) manifest drift in BOTH directions (files with no manifest row, and manifest rows with no file). Make one proposal per finding; rewrite nothing.
cost $0.1176 · 82s · in 64,382 / out 8,046 tok
✓ duplicate_trigger_found✓ circular_chain✓ dangling_target✓ oversized_desc_count✓ hardcoded_values✓ manifest_drift✓ severity_and_action

✓ Correct Answer (ground truth)

Plain-English answer: A severity-ranked list of TRIM_DESC / UPDATE_BODY / DELETE_SKILL / MERGE / REVIEW actions covering every rule violation found.
The answer in one line: files_audited = 14; rank = CRITICAL / WARNING / INFO with one fix action per issue
files_audited14
findingsduplicate trigger, circular delegation chain, dangling file reference, oversized description, hardcoded values, manifest drift
rankCRITICAL / WARNING / INFO with one fix action per issue
graded checksduplicate_trigger_found · circular_chain · dangling_target · oversized_desc_count · hardcoded_values · manifest_drift · severity_and_action

Model's actual answer

show the model's full answer
1. OVERLAPPING ALWAYS-TRIGGERS — comms-drafter + email-drafter
Severity: CRITICAL — Action: MERGE
Identical trigger phrases in both descriptions: "write me an email," / "draft a follow-up," / "what should I say," / "bump email," / "contract nudge". comms-drafter adds "help me reply," email-drafter has "help me reply to this,". Both claim review/rewrite of pasted copy. Proposal: merge into one email/comms skill; keep the other as alias only.

2. CIRCULAR DELEGATION CHAIN — deal-strategy-coach -> email-drafter -> deal-strategy-coach
Severity: CRITICAL — Action: UPDATE_BODY
deal-strategy-coach body: "When drafting manager-to-prospect emails, use the `email-drafter` skill". email-drafter body: "point them to the deal-strategy-coach skill" / "suggest they use deal-strategy-coach for the deeper analysis". Proposal: keep coach->drafter (execution), change drafter->coach to a non-invoking reference (link text only, no run).

3. DANGLING DELEGATION TARGETS — no file / no manifest row
Severity: CRITICAL — Action: REVIEW
Missing targets referenced by body text:
bonusly-brand (comms-drafter, email-drafter, sales-forecast, signalforge-claim-compressor); prospect-research-multithreading (comms-drafter, deal-strategy-coach, email-drafter); signalforge-reports (pipeline-intelligence-report, weekly-pipeline-report); skill-orchestrator (signalforge-feedback); bonusly-data-questions, bonusly-product-questions, bonusly-business-reporting-questions, bonusly-rewards-questions, bonusly-ppp-questions, bonusly-feature-flag-questions, bonusly-deal-desk-questions, bonusly-datadog-questions (all in analysis-validator 12.4); caveman / JuliusBrussee/caveman (signalforge-claim-compressor). 0 of these appear in manifest or files. Proposal: either add the missing skills or remove/replace the references; do not leave invoke-on-missing.

4. VERSION CONFLICT — analysis-validator v3.6 vs v3.2
Severity: WARNING — Action: UPDATE_BODY
Header: "**Version:** 3.6" / "Last Updated: May 9, 2026" / footer "analysis-validator v3.6". Section 7 trail template stamps "Validator: analysis-validator v3.2". Proposal: survivor is v3.6; update the trail template line to v3.6. No other skill shows an internal version mismatch.

5. MANIFEST DESCRIPTIONS >1,024 CHARS — 0
Severity: INFO — Action: REVIEW
Arithmetic: description_chars = [656,897,996,792,965,676,945,1004,1006,962,1006,708,762,656]. Count >1024: 0. 0/14 = 0%. Max observed = 1006 (pipeline-intelligence-report, signalforge-claim-compressor). Proposal: no change.

6. HARDCODED PAGE IDS / DATES / PERSON NAMES IN BODIES
Severity: WARNING — Action: UPDATE_BODY
Page/channel/space IDs: deal-strategy-coach playbook page 2257879045; partner-digest cloud 73fe98de-a4a3-4869-9f8a-bb1eeed4cf7f, space 1958248479, folder 2286616609, pages 2286321666,2265382925,2236940297,2237825028,2239365136,2238283777; sales-forecast space 2232811524, parent 2232582148, sheets 1CLZeOsElVDF_LF0ZG_t2nfwvhnZ6bpwqM_nX3WEYzcw, 1ENuaEcCuLjdKhMvp8FK3Ys1ek5Aw9ZuOZhsHJJFoB_k; signalforge-feedback page 2295136266, space 2232811524, parent 2234417154, Build Log 2247295002; stale-pipeline-report channel C0561C1JCPJ, owner 55483190; weekly-pipeline-report same 2 sheet IDs; pipeline-intelligence-report org 1973303 + AE owner/stage IDs.
Dates: analysis-validator April 26, 2026 / May 9, 2026 / May 4, 2026 / March 28, 2023; deal-strategy-coach April 2026; model-selection 2026-05-19, April 14, 2026; partner-digest May 16, 2026 / May 19, 2026 / June 2, 2026; sales-forecast April 27, 2026 / July 9, 2026; signalforge-claim-compressor 2026-05-09; stale-pipeline-report 2026-06-10; weekly-pipeline-report April 1-June 30, 2026 / Q1 2026.
Person names: analysis-validator roster Bryce Harmon, Hugo Lindqvist, Dana Mercer, Alex Franklin, Cole Ingram, Gavin Porter, Alaina Loori, Colleen Perry, Ellie Barton, Ashley Reyer, Megan Franz, Elena Sinclair, Youssef Elkhateeb, Amanda Czenkus, Shealagh Coughlin, Ben Castelli, Amani Phipps, John Thomas, Yasmin Wahid, plus Manish; pipeline-intelligence-report same 5 AE names; partner-digest Amani Phipps, Kelli, Jen Lee, Hani, Bryce, Sara; sales-forecast Alaina, Elena; weekly-pipeline-report Ben Lavin; signalforge-feedback example Gavin Porter. Proposal: parameterize IDs/dates/roster lookups; leave system constants only with verify-at-runtime note.

7. MANIFEST DRIFT BOTH DIRECTIONS — 0 / 0
Severity: INFO — Action: REVIEW
Arithmetic: files provided = 14; manifest rows = 14; name intersection = 14. Files with no manifest row = 14-14 = 0. Manifest rows with no file = 14-14 = 0. Proposal: no change; names match exactly on all 14: analysis-validator, closed-lost-analysis, comms-drafter, deal-strategy-coach, email-drafter, model-selection, next-to-close, partner-digest, pipeline-intelligence-report, sales-forecast, signalforge-claim-compressor, signalforge-feedback, stale-pipeline-report, weekly-pipeline-report.
runbook-from-slack-thread0.75
Plain-English question: Turn the resolved incident thread into a runbook.
Prompt — what the model saw
Turn the resolved incident thread into a runbook: ordered steps with the exact command or action taken, who ran it, how success was verified, and rollback for each step that changed state. Every step must trace to a message in the thread. Add nothing the thread does not contain; where the thread is unclear, mark the step as needing confirmation.
cost $0.0096 · 46s · in 592 / out 1,378 tok
✓ ordered_steps✓ rollback✓ needs_confirmation✗ sourced

✓ Correct Answer (ground truth)

Plain-English answer: Ordered steps from the thread, each with the exact command, who ran it, how success was verified, and rollback where state changed.
The answer in one line: rule = no steps beyond what the thread contains; every step traces to a message id.
ambiguous_steporder=4; msg=M05; mark=needs-confirmation
ruleno steps beyond what the thread contains; every step traces to a message id.
stepsorder=1; msg=M01; actor=Bryce Harmon; action=acknowledge PagerDuty alert, take IC; state_change=False; verified_by=M01 | order=2; msg=M02; actor=Farid Osman; action=check queue depth; command=bundle exec rake sidekiq:queue_depth; state_change=False; verified_by=M02 (48,213 pending) | order=3; msg=M04; actor=Farid Osman; action=pause auto-enqueue via feature flag; command=bin/rails runner 'FeatureFlag.disable(:auto_recognition_enqueue)'; state_change=True; rollback=bin/rails runner 'FeatureFlag.enable(:auto_recognition_enqueue)'; verified_by=M07 (queue depth falling) | order=4; msg=M05; actor=Elena Sinclair; action=cleared the dead set; state_change=True; needs_confirmation=thread gives no command or method for clearing the dead set | order=5; msg=M06; actor=Bryce Harmon; action=scale reward-worker to 6 replicas; command=kubectl scale deployment/reward-worker --replicas=6; state_change=True; rollback=kubectl scale deployment/reward-worker --replicas=3; verified_by=M07/M08 | order=6; msg=M08; actor=Cole Ingram; action=verify queue drained and error rate baseline; command=bundle exec rake sidekiq:queue_depth; state_change=False; verified_by=M08 (returns 0) … (+2 more)
graded checksordered_steps · rollback · needs_confirmation · sourced

Model's actual answer

show the model's full answer
Runbook — #incident-2026-08-29-reward-queue

1. [M01] Acknowledge and take IC
   Action: PagerDuty alert for reward-worker queue depth > 10k; acknowledging, taking IC.
   Who: Bryce Harmon
   Verify: none stated — needing confirmation if verification required.
   State change: no.

2. [M02] Check reward queue depth
   Command: `bundle exec rake sidekiq:queue_depth`
   Who: Farid Osman
   Result: 48,213 pending jobs. Normal stated as under 500.
   Verify: command output returned 48,213.
   State change: no.

3. [M03] Check dead set
   Action: dead set observed as 112 jobs, all Redis::TimeoutError from around 13:58.
   Who: Farid Osman
   Command used to observe: not stated — needing confirmation.
   State change: no.

4. [M04] Pause enqueue
   Command: `bin/rails runner 'FeatureFlag.disable(:auto_recognition_enqueue)'`
   Who: Farid Osman
   Verify: none stated for this step — needing confirmation.
   Rollback: `bin/rails runner 'FeatureFlag.enable(:auto_recognition_enqueue)'`

5. [M05] Clear dead set
   Action: “cleared out the dead set” while in the console.
   Who: Elena Sinclair
   Exact command: not stated — needing confirmation.
   Verify: none stated — needing confirmation.
   Rollback: none stated — needing confirmation.

6. [M06] Scale workers up
   Command: `kubectl scale deployment/reward-worker --replicas=6` (was 3)
   Who: Bryce Harmon
   Verify: none stated for this step; later [M07] queue falling.
   Rollback: `kubectl scale deployment/reward-worker --replicas=3`

7. [M07] Monitor queue drain
   Observation: queue depth down to 9,400 and falling ~1,200/min.
   Who: Farid Osman
   Command used: not stated — needing confirmation.
   State change: no.

8. [M08] Verify drain
   Command: `bundle exec rake sidekiq:queue_depth`
   Who: Cole Ingram
   Result: returns 0. Error rate in Datadog back to baseline.
   State change: no.

9. [M09] Re-enable enqueue
   Command: `bin/rails runner 'FeatureFlag.enable(:auto_recognition_enqueue)'`
   Who: Bryce Harmon
   Verify: 40 new jobs processed cleanly in the next 3 minutes.
   Rollback: none stated for this step — needing confirmation. Note: command matches rollback given in [M04].

10. [M10] Scale workers back down and resolve
    Command: `kubectl scale deployment/reward-worker --replicas=3`
    Who: Bryce Harmon
    Verify: queue stable at 0.
    Rollback: none stated for this step — needing confirmation. Note: command matches rollback given in [M06].
datadog-incident-timelinePASS 1.00
Plain-English question: Sequence the failure from the logs — what broke first, and what cascaded after it?
Prompt — what the model saw
From the log slice, sequence the failure: first error with timestamp, the cascade in order, the service and job involved, and the Datadog query that would confirm the first error. State what the logs do not show.
cost $0.0333 · 51s · in 17,879 / out 2,458 tok
✓ first_error_ts✓ service_named✓ cascade_ordered✓ query✓ gaps_stated

✓ Correct Answer (ground truth)

Plain-English answer: A reward-service Redis timeout at 14:01:12Z cascades to sidekiq at 14:01:40 and api-gateway at 14:03:05, with the Datadog query that confirms the first error.
The answer in one line: job_class_involved = RewardGiveJob
cascade_orderservice=reward-service; first_error_at=2026-09-03T14:01:12Z | service=sidekiq; first_error_at=2026-09-03T14:01:40Z | service=api-gateway; first_error_at=2026-09-03T14:03:05Z | service=web-app; first_error_at=2026-09-03T14:03:30Z
clean_servicespostgres
confirming_queryservice:reward-service status:error "@message:Redis::TimeoutError"
first_errortimestamp=2026-09-03T14:01:12Z; service=reward-service; message=Redis::TimeoutError: Connection to Redis at redis-primary:6379 timed out after 5s
job_class_involvedRewardGiveJob
logs_do_not_showroot cause of the Redis timeout, redis-server's own logs, infrastructure metrics (CPU/memory/network), any deploy or config change preceding the incident, who applied mitigation or when (no actor fields in logs)
graded checksfirst_error_ts · service_named · cascade_ordered · query · gaps_stated

Model's actual answer

show the model's full answer
First error:
2026-09-03T14:01:12Z — reward-service — ERROR — Redis::TimeoutError: Connection to Redis at redis-primary:6379 timed out after 5s

Cascade in order:
1. 2026-09-03T14:01:12Z reward-service ERROR Redis timeout
2. 2026-09-03T14:01:20Z reward-service ERROR retry exhausted for RewardGiveJob
3. 2026-09-03T14:01:30Z reward-service ERROR retry exhausted for RewardGiveJob
4. 2026-09-03T14:01:40Z reward-service ERROR retry exhausted for RewardGiveJob + 2026-09-03T14:01:40Z sidekiq ERROR RewardGiveJob failed: Redis::TimeoutError; retrying in 60s
5. 2026-09-03T14:02:28Z sidekiq ERROR RewardGiveJob failed
6. 2026-09-03T14:02:30Z sidekiq WARN Queue reward depth above 10,000
7. 2026-09-03T14:03:05Z api-gateway ERROR 502 upstream timeout calling reward-service /gives
8. 2026-09-03T14:03:30Z web-app ERROR Give form submission failed: upstream 502 from api-gateway
9. 2026-09-03T14:03:31Z to 2026-09-03T14:06:52Z repeating sidekiq RewardGiveJob failures + api-gateway 502s + web-app Give form failures
10. 2026-09-03T14:22:10Z reward-service INFO Redis connection restored; resuming job processing
11. 2026-09-03T14:24:45Z sidekiq INFO Queue reward depth below 500

Service and job involved:
Service: reward-service (origin), with sidekiq, api-gateway, web-app downstream
Job: RewardGiveJob

Arithmetic:
sidekiq_jobs.csv: 12 RewardGiveJob (J-00001 to J-00012) + 4 RecognitionDigestJob (J-00013 to J-00016) = 16 total failures
datadog_logs.csv errors: 4 reward-service + 6 sidekiq + 5 api-gateway + 4 web-app = 19 errors
Outage duration in logs: 14:22:10 minus 14:01:12 = 20 min 58 sec
Queue recovery: >10,000 on 2026-09-03T14:02:30Z to <500 on 2026-09-03T14:24:45Z

Datadog query to confirm first error:
service:reward-service level:ERROR "Redis::TimeoutError" @timestamp:2026-09-03T14:01:12Z

Deal/company aliases: none present in provided files.

Logs do not show:
- Root cause of Redis timeout at redis-primary:6379
- Any Redis server-side logs/metrics, deploys, or config changes
- RecognitionDigestJob in datadog_logs.csv (appears only in sidekiq_jobs.csv: 4 failures)
- Activity between 2026-09-03T14:06:52Z and 2026-09-03T14:22:10Z except postgres INFO checkpoint complete
- Final disposition per job ID (retried/succeeded/dropped), user impact count, or deal/company impact
feature-flag-state-summaryPASS 1.00
Plain-English question: Summarize what each feature flag controls and who has it on.
Prompt — what the model saw
Summarize the state of the listed feature flags: what each controls per the code excerpt, which companies or segments have it on, targeting rules, and any flag with no code reference or no targets. Company counts must match the export. Do not describe a flag that is not in the export.
cost $0.0099 · 48s · in 466 / out 1,487 tok
✓ orphans✓ no_targets✓ counts_match✓ no_invented

✓ Correct Answer (ground truth)

Plain-English answer: Recognition streaks on for 42 beta companies, redeem-flow redesign off with a 12-company target list, plus any flag with no code reference or no targets.
The answer in one line: rule = company counts must equal the export; do not describe flags absent from the export.
code_referencedrecognition_streaks_v2, points_budget_guardrails, slack_dm_nudges, redeem_flow_redesign, analytics_dashboard_v3, ms_teams_app_v2
flags{"recognition_streaks_v2": {"state": "on", "targeting_rules": "segment:beta_companies", "company_count": 42}, "points_budget_guardrails": {"state": "on", "targeting_rules": "all_companies", "company_c
flags_with_no_targetspaused_offboard_cleanup
orphan_flags_no_code_referencelegacy_give_modal, survey_boosters_q3, paused_offboard_cleanup
rulecompany counts must equal the export; do not describe flags absent from the export.
graded checksorphans · no_targets · counts_match · no_invented

Model's actual answer

show the model's full answer
State of 9 exported flags:

1. recognition_streaks_v2 — state: on
Controls per code: app/models/recognition.rb — if enabled, StreakTracker.record(give)
Targeting: segment:beta_companies
Company count: 42

2. points_budget_guardrails — state: on
Controls per code: app/services/budget_service.rb — if enabled, BudgetService.new(company).enforce!(giver, points)
Targeting: all_companies
Company count: 220

3. slack_dm_nudges — state: on
Controls per code: app/jobs/nudge_job.rb — if not enabled, return; if enabled, SlackDm.send_nudge(user)
Targeting: segment:region_na
Company count: 87

4. redeem_flow_redesign — state: off
Controls per code: app/controllers/redeem_controller.rb — if enabled render RedeemV2Component.new(company), else render RedeemV1Component.new(company)
Targeting: targeted_list
Company count: 12

5. analytics_dashboard_v3 — state: on
Controls per code: app/controllers/analytics_controller.rb — if enabled, @dashboard = AnalyticsV3.new(company)
Targeting: segment:tier_three
Company count: 65

6. ms_teams_app_v2 — state: off
Controls per code: app/services/teams_installer.rb — if enabled, TeamsAppV2.install(company)
Targeting: targeted_list
Company count: 9

7. legacy_give_modal — state: off
Controls per code: no reference in provided excerpt
Targeting: segment:legacy_plan
Company count: 14

8. survey_boosters_q3 — state: on
Controls per code: no reference in provided excerpt
Targeting: segment:legacy_plan
Company count: 7

9. paused_offboard_cleanup — state: off
Controls per code: no reference in provided excerpt
Targeting: none listed (targeting_rules blank)
Company count: 0

No code reference: legacy_give_modal, survey_boosters_q3, paused_offboard_cleanup.
No targets: paused_offboard_cleanup only — targeting_rules empty, company_count 0.

Arithmetic (sums of company_count values, not de-duplicated companies; overlap unknown):
On flags: 42 + 220 + 87 + 65 + 7 = 421
Off flags: 12 + 9 + 14 + 0 = 35
All rows: 421 + 35 = 456
nda-triagePASS 1.00
Plain-English question: Triage each NDA green, yellow, or red — and quote the clause that decides it.
Prompt — what the model saw
Triage each NDA as GREEN (standard approval), YELLOW (counsel review), or RED (full legal review). Cite the clause that drives each classification by quoting it. Catch embedded non-solicits, non-competes, missing carve-outs, and unusual term or governing law. One line of reasoning per NDA.
cost $0.0123 · 37s · in 519 / out 2,056 tok
✓ green✓ yellow✓ red✓ non_solicit_caught✓ clause_quoted✓ correct_labels

✓ Correct Answer (ground truth)

Plain-English answer: NDA-1 green (standard mutual terms), NDA-2 yellow for an embedded 18-month non-solicit, with the driving clause quoted for every classification.
The answer in one line: non_solicit_in = NDA-2
checksclassification_per_nda, clause_quotes_exist_in_document, non_solicit_caught, carveouts_checked
classifications{"NDA-1": {"classification": "GREEN", "driving_reason": "standard mutual NDA: 2-year term, standard carve-outs, Delaware law", "driving_clause_quote": "Carve-outs: information that (a) is or becomes p
non_solicit_inNDA-2
graded checksgreen · yellow · red · non_solicit_caught · clause_quoted · correct_labels

Model's actual answer

show the model's full answer
NDA-1 ([PARTY A]) — GREEN — Standard mutual NDA with arithmetic 2 + 3 = 5 years max obligation and no non-solicit/non-compete, driven by "information that (a) is or becomes publicly available through no breach, (b) was known prior to disclosure, (c) is received from a third party without duty of confidence, (d) is independently developed, or (e) must be disclosed by law or court order."
NDA-2 ([PARTY B]) — YELLOW — Embedded non-solicit with arithmetic 3 years + 18 months = 4.5 years hiring restriction requires counsel review, driven by "During the term of this Agreement and for eighteen (18) months thereafter, neither party shall solicit for employment or hire any employee of the other party with whom it came into contact under this Agreement."
NDA-3 ([PARTY C]) — RED — One-way, 5-year term (unusual), no carve-outs stated, and Ireland exclusive jurisdiction plus 3-year non-compete requires full legal review, driven by "For a period of three (3) years following the Effective Date, Recipient shall not, directly or indirectly, engage in or provide services to any business that competes with Discloser's business."