← back to all models ← RevenueBench home
nvidia

nvidia/nemotron-3.5-super-vl:free

Mean 0.949 · 33/40 perfect tests · $2.93 total · modalities in: text, image, video · 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 $0.2357 · 126s · in 108,708 / out 22,710 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+ = stage DS2/DS3/DS4/DS5. Non-compliant why-buys = empty, under 15 chars, or placeholder (tbd/n/a/see notes); LONG(n) counts as compliant substantive. No-DS1 = t_ds1 blank. Regressed = any earlier-stage timestamp later than a later-stage timestamp (equal same-day stamps are not regressed).

Why-buys non-compliance (DS2+ only):
Overall: 101/124 = 81.45% non-compliant (23 compliant).
By owner:
Bryce Harmon: 15/18 = 83.3%
Alex Franklin: 48/61 = 78.7%
Dana Mercer: 18/22 = 81.8%
Cole Ingram: 19/22 = 86.4%
Farid Osman: 1/1 = 100.0% (Deal-499BF6)
Elena Sinclair: no DS2+ deals.

Compliant (23, the only DS2+ deals with LONG why-buys): Deal-9AAE5F, Deal-6787C2, Deal-584EE5, Deal-FC22A3, Deal-93C8BF, Deal-885F45, Deal-F67D31, Deal-D7E999, Deal-92D97D, Deal-44EA29, Deal-D0BC96, Deal-8AD4A5, Deal-15D24F, Deal-1E2498, Deal-BE3D9D, Deal-E0B692, Deal-ED725A, Deal-530B50, Deal-C7F9BF, Deal-342E96, Deal-627646, Deal-7599B8, Deal-792D44. No placeholder text values found; all other DS2+ why_buys are blank.

No DS1 timestamp: 0 deals. Every one of the 156 open deals has a t_ds1 value.

Regressed timestamps: 0 deals. No deal has an earlier-stage timestamp later than a later-stage timestamp.

Three process fixes:
1. Gate DS2+ creation/advancement on why-buys >= 15 chars with placeholder blocklist; backfill the 101 blanks before forecast lock.
2. System-stamp stage entries on stage change only (no manual edits or pre-create stamps); audit anomalies such as t_ds1 predating create_date (e.g. Deal-403845, Deal-927338, Deal-DCA846, Deal-F67D31).
3. Strip forecast credit (no BEST_CASE/COMMIT) from DS2+ deals without why-buys and publish this hygiene scorecard weekly by owner.
owner-resolution0.83
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 $0.1307 · 64s · in 56,365 / out 13,495 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
Deals resolved: 156 of 156

Counts by owner_id:
- 119337721: 35 deals
- 84342457: 67 deals
- 83155923: 24 deals
- 83155924: 22 deals
- 716654662: 7 deals
- 701163055: 1 deal
35 + 67 + 24 + 22 + 7 + 1 = 156

Deals whose owner_id has no match in owners.csv: 0
List: none. All 6 owner_ids in deals_open.csv match owners.csv.

Owner ids that map to archived/deactivated owners:
- 1520255671, Gavin Porter, archived=true
- 77260721, Hugo Lindqvist, archived=true
No open deals are assigned to either archived id.

Total pipeline amount per resolved owner:

- Bryce Harmon (119337721), 35 deals: 1,054,144
- Alex Franklin (84342457), 67 deals: 624,310
- Dana Mercer (83155923), 24 deals: 341,195
- Cole Ingram (83155924), 22 deals: 288,161.43
- Farid Osman (716654662), 7 deals: 4,134 = 1249 + 1 + 1 + 1 + 2880 + 1 + 1
- Elena Sinclair (701163055), 1 deal: 2,100 = Deal-57FF13

Check total: 1,054,144 + 624,310 + 341,195 + 288,161.43 + 4,134 + 2,100 = 2,314,044.43
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 $0.2051 · 82s · in 105,856 / out 13,699 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
(a) Orphans: 30 of 67 gong rows have no match in deals_open.

67 - 37 matched = 30 orphaned.

Sample orphan aliases (all from gong file, absent from deals_open): Deal-8FA85D, Deal-8FC3F9, Deal-3B7945, Deal-42B265, Deal-9CCC42.

(b) Duplicate conversation keys: 0 rows.

0 of 67 rows have calls_90d > distinct_conversation_keys. All 67 rows have calls_90d = distinct_conversation_keys.

(c) DS3+ open deals with at least one logged call: 24 of 84 = 28.6%.

Denominator: DS3 60 + DS4 14 + DS5 10 = 84 open deals at DS3 or later.
Numerator: 24 of the 37 matched deal ids are DS3+; 13 matched are DS1/DS2 (Deal-F9A3C1, Deal-AF932D, Deal-523604, Deal-3795AD, Deal-F40F04, Deal-CA7DC0, Deal-A414F6, Deal-A71728, Deal-93C8BF, Deal-8FDCD2, Deal-117863, Deal-03BA69, Deal-4B0BEB).

24 / 84 = 0.2857 = 28.6%.

Note: gong_owner_id not joined, per instruction it is a Gong user id, not a HubSpot owner id.
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 $0.0331 · 32s · in 19,972 / out 1,902 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
-- CANNOT BUILD QUERY FROM CATALOG AS GIVEN: MISSING DATA.
-- No recognition/giving event table is listed (no table with company_id, giver_id, recognition_id/timestamp).
-- Therefore unique givers and recognition count for first calendar month cannot be derived without inventing a table/columns, which is not permitted.
-- Redemption source PRODUCTION.DEPRECATED_RECOGNITION.REDEMPTION_RECORDS_V2 is documented with rule STATE = 'succeeded' only,
-- but catalog gives no company key, user key, or timestamp columns to scope to per-company first calendar month.
-- First-month scoping keys are also undefined: PRODUCTION.CHARGEBEE.SUBSCRIPTIONS has CURRENT_TERM_START and CUSTOMER_ID
-- but no documented company join; PRODUCTION.PLG.COMPANY_COHORT_SUMMARY has M1_USERS/M1_GIVES/M1_REDEMPTIONS but no documented definitions
-- equating them to unique givers / recognition count / successful redemption count.
-- Avoided per notes: PRODUCTION.HUBSPOT.DEALS (STALE 2023-03), HUBSPOT_HUB_1973303.V2_LIVE.OBJECTS_DEALS (UNPOPULATED), PRODUCTION.HUBSPOT.GONG_HUBSPOT_MAP_FAST (RETIRED).
-- Business rule noted: do NOT apply deleted-givers exclusion filter to historical giving counts; no such filter applied here.
-- No FROM/JOIN issued because any FROM/JOIN would require inventing join keys not in catalog.
SELECT 'MISSING_SOURCE_TABLES' AS error;
```
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 $0.0344 · 47s · in 2,593 / out 6,663 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
CRM completeness audit — only data provided, no values invented.

Deals extract missing: no file provided. Completeness for owner, stage, amount, close date, why-buys cannot be computed. Pipeline amount at stake is unknown for all fixes.

1. Completeness percent per field

Companies: 34 rows provided.
- industry: 34/34 present = 100.0%
  Note: values un-normalized: Manufacturing, Retail, Finance, Healthcare, Technology, Computer Software not in CRM, plus variants `tech`, `Tech `, `health care`, `SaaS`. Complete but needs normalization.
- employee_count: 25/34 present = 73.5%
  Missing 9/34: C-EC3025, C-96039F, C-44EA29, C-D04904, C-B23205, C-60C75F, C-7BBDFA, C-50D386, C-93C8BF
- hq_country: 28/34 present = 82.4%
  Missing 6/34: C-2D1F1B, C-D73B89, C-44EA29, C-D04904, C-2C60E5, C-EE9FFB
  Note: values un-normalized: US / USA / United States / UK / Canada.

Contacts: 52 rows provided, only for C-2D1F1B through C-425E2A. No contacts provided for 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. Percentages below are 52 rows only.
- email: 52/52 non-empty = 100.0% present, but 4 invalid (see §3)
- title: 39/52 present = 75.0%
  Missing 13/52: 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: 37/52 present = 71.2%
  Missing 15/52: 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

2. Duplicate company clusters

2 clusters by shared domain:
Cluster A — domain acme-corp.com:
- C-0A092931: Technology, 500, US
- C-0A092932: tech, 510, USA
Proposed survivor: C-0A092931. Reason: tie-break earliest alias; both 100% complete. Merge C-0A092932 into C-0A092931. Resolve 500 vs 510 and US vs USA before merge — no source to choose, do not invent.

Cluster B — domain globex.io:
- C-0A092933: SaaS, 200, US
- C-0A092934: Technology, 200, US
Proposed survivor: C-0A092933. Reason: tie-break earliest alias; both 100% complete. Merge C-0A092934 into C-0A092933. Resolve SaaS vs Technology before merge — no source to choose, do not invent.

No other shared domains in companies.csv.

3. Invalid emails and domain mismatches

Invalid (missing domain part after @):
- CT-0010 (C-66D1FC): `user0@`
- CT-0080 (C-92D97D): `user0@`
- CT-0081 (C-92D97D): `user1@`
- CT-0192 (C-425E2A): `user2@`

Domain mismatch (valid format, domain != company domain):
- CT-0011 (C-66D1FC): `user1@other-domain.com` vs domain 66d1fc.com

4. Enrichment fill / disagreements

Enrichment covers 25/34 companies. No enrichment row for: ba969b.com, 332637.com, 93c8bf.com, ee9ffb.com, c9bb20.com, acme-corp.com (C-0A092931, C-0A092932), globex.io (C-0A092933, C-0A092934). Missing fields for those cannot be filled.

Fills possible (CRM missing, enrichment has value):
- C-EC3025 employee_count: CRM missing -> zi 400. Use zi.
- C-96039F employee_count: CRM missing -> zi 400. Use zi.
- C-44EA29 employee_count: CRM missing -> zi 400. Use zi.
- C-D04904 employee_count: CRM missing -> zi 400. Use zi.
- C-B23205 employee_count: CRM missing -> zi 400. Use zi.
- C-60C75F employee_count: CRM missing -> zi 400. Use zi.
- C-7BBDFA employee_count: CRM missing -> zi 400. Use zi.
- C-50D386 employee_count: CRM missing -> zi 400. Use zi.
No hq_country fills possible:
- C-2D1F1B, C-D73B89, C-44EA29, C-D04904, C-2C60E5 hq missing and zi hq also missing.
- C-EE9FFB hq missing and no enrichment row.
- C-93C8BF employee_count missing and no enrichment row.

Disagreements where both have values (recommendation: use zi for employee_count and hq_country canonicalization, keep CRM industry pending normalization decision — do not auto-overwrite industry taxonomy):
- C-66D1FC: industry CRM `tech` vs zi `Computer Software`; hq CRM `US` vs zi `United States`; emp 900=900 agree.
- C-950043: hq CRM `US` vs zi `United States`; Retail 120 agree.
- C-EC3025: industry CRM `Technology` vs zi `Computer Software`; hq CRM `USA` vs zi `United States`.
- C-96039F: hq CRM `USA` vs zi `United States`; Finance agree.
- C-44EA29: industry CRM `tech` vs zi `Computer Software`.
- C-92D97D: industry CRM `Technology` vs zi `Computer Software`; emp 50=50, Canada agree.
- C-D04904: industry CRM `Technology` vs zi `Computer Software`.
- C-77A95A: industry CRM `Technology` vs zi `Computer Software`; hq CRM `US` vs zi `United States`.
- C-AA8DDA: industry CRM `Technology` vs zi `Computer Software`.
- C-B23205: hq CRM `US` vs zi `United States`.
- C-E51FB7: hq CRM `USA` vs zi `United States`.
- C-D0662E: hq CRM `US` vs zi `United States`.
- C-B25F40: industry CRM `Technology` vs zi `Computer Software`.
- C-60C75F: industry CRM `tech` vs zi `Computer Software`.
- C-425E2A: industry CRM `Tech ` vs zi `Computer Software`; hq CRM `USA` vs zi `United States`.
- C-2D7423: hq CRM `USA` vs zi `United States`.
Full agreement: C-2D1F1B, C-C6FE92, C-D73B89, C-31ED2A, C-63A874, C-2C60E5, C-B97B4E, C-7BBDFA (industry), C-50D386 (industry).

5. 10 fixes with most pipeline at stake

Pipeline amount unavailable — deals file missing, amount at stake = unknown for all. Ranked below by records blocked / downstream risk, not amount:
1. Resolve Cluster A (C-0A092931 / C-0A092932) — amount unknown.
2. Resolve Cluster B (C-0A092933 / C-0A092934) — amount unknown.
3. Fix CT-0010 invalid email — amount unknown.
4. Fix CT-0011 domain mismatch — amount unknown.
5. Fix CT-0080 + CT-0081 invalid emails (C-92D97D left with 1 valid contact CT-0082) — amount unknown.
6. Fix CT-0192 invalid email — amount unknown.
7. Fill 8 employee_counts from zi: C-EC3025, C-96039F, C-44EA29, C-D04904, C-B23205, C-60C75F, C-7BBDFA, C-50D386 — amount unknown.
8. Normalize hq_country US/USA/United States (affects 18 rows) — amount unknown.
9. Normalize industry tech/Tech /Technology/Computer Software/health care (affects 13 rows) — amount unknown.
10. Backfill titles/personas for C-AA8DDA (all 3 titles missing) and C-92D97D / C-60C75F (2+ personas missing each) — amount unknown.
deal-intelligence 5 tests
closed-lost-classification0.80
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 $0.0627 · 88s · in 4,625 / out 12,720 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
Classify every deal from closed_lost_6mo.csv. Rule used: primary category from free-text first, tag second. Side: Bonusly = text cites Bonusly shortfall on price/product/evaluation; buyer = timing/no-decision/budget-approval/buyer preference; unknown = MIA/other with no reason + vague competitor with no detail.

Full list deal_alias: category / side

Deal-DB0AAC: timing / buyer - pause, timeline to reconnect
Deal-F7F635: competitor / unknown - another direction, no detail
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
Deal-831B7B: timing / buyer - look again new year
Deal-F97C37: competitor / Bonusly - other vendor more diversified offerings
Deal-13E9CF: no decision / buyer - R&R deprioritized, not budget
Deal-39E25C: timing / buyer - reconnect next year
Deal-7ED004: pricing / buyer - did not get budget approval
Deal-21B045: other / unknown - MIA
Deal-B3ABED: timing / buyer - revisit Q2 next year for 2028 budget
Deal-422BA6: competitor / Bonusly - chose competitor, ADP TotalSource partner, integrations
Deal-ED9AE7: no decision / buyer - Timing, budget, authority, no approval
Deal-988493: other / unknown - mia
Deal-381C8C: competitor / unknown - not moving forward, no detail
Deal-F308CA: other / unknown - no contact since intro, ignored outreach
Deal-F1E8A6: competitor / unknown - not moving forward, no detail
Deal-B6AC09: timing / buyer - revisiting in 2027
Deal-70F704: other / unknown - narrow anniversary-awards use + 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 - on hold until 2027, other priorities
Deal-E74A73: no decision / buyer - test manually before investing
Deal-DDAB52: competitor / Bonusly - Rippl, more at same cost, exchange rate
Deal-ACE061: competitor / unknown - feel HeyTaco, different direction
Deal-BB78F3: timing / buyer - interested end goal, plant action items first
Deal-D48E0B: other / unknown - MIA
Deal-15DA99: timing / buyer - bring back 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: competitor / unknown - different direction, no detail
Deal-E0441F: other / unknown - stale inherited, no contact
Deal-7CB44D: other / unknown - no meaningful contact since demo
Deal-0F96AA: competitor / Bonusly - lost RFP, no finalist demo
Deal-1BCA50: competitor / buyer - budget + stakeholder down path with another vendor
Deal-7CC678: competitor / unknown - nothing specific
Deal-FAC17C: no decision / buyer - could not get Executive IT Director approval
Deal-242273: product gap / Bonusly - digitize points currency + onsite spend differentiator
Deal-50E5D8: no decision / buyer - pause, reach out if changes
Deal-A2C349: competitor / buyer - stick with Awardco + surveying
Deal-9F176A: timing / buyer - pause, pick up end of year
Deal-7B2236: pricing / Bonusly - budget + simpler and cheaper
Deal-AFA56C: other / unknown - unresponsive
Deal-C7156E: competitor / unknown - selected another vendor, no detail
Deal-C33D91: pricing / buyer - budget cuts, not approved
Deal-9048EB: product gap / Bonusly - bad fit, desired setup, multiple feature gaps
Deal-5E64CE: no decision / buyer - Nectar agreement through Oct 2027, exit fee
Deal-8A0992: competitor / buyer - Canadian provider aligns
Deal-D0C698: competitor / buyer - past Kudos user 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 / unknown - another direction, no detail
Deal-5AD03E: product gap / Bonusly - wanted more 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 months
Deal-BF2A98: competitor / buyer - deployed HiThrive
Deal-2A292B: no decision / buyer - build simple internally
Deal-D1AABF: other / unknown - No response
Deal-FEDBCB: no decision / buyer - reconnect end of year, not engaged
Deal-1E7DA9: competitor / unknown - selected another platform, no detail
Deal-2BBA21: other / unknown - no contact, ignored nudges
Deal-286F9C: competitor / Bonusly - 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 importance
Deal-55867E: no decision / buyer - will not move forward at this time, no timeline
Deal-DAFB82: pricing / buyer - priorities need budget, not budgeted until 2028
Deal-2FEDDB: no decision / buyer - unsure timing to get moving
Deal-64B19A: competitor / buyer - likely stayed with Motivosity
Deal-3F86A0: other / unknown - unresponsive
Deal-096750: other / unknown - no meaningful contact, ignored revive
Deal-F325A5: no decision / buyer - layoffs, leadership change, no longer priority
Deal-ABD14C: no decision / buyer - not interested
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 - does not fit UI, not UK focused
Deal-DC77FE: product gap / Bonusly - more customization, label points as dollars, price not factor
Deal-5885B9: other / unknown - MIA

Summary counts, n=90:
timing 18
competitor 23 (includes Deal-DDAB52)
no decision 15
pricing 5
product gap 6
other 23
champion left 0
Arithmetic: 18+23+15+5+6+23+0 = 90

Side split:
buyer 46
unknown 32
Bonusly 12
Arithmetic: 46+32+12 = 90
Buyer = all 18 timing + all 15 no decision + 5 pricing budget-approval/cuts/priorities (Deal-7ED004, Deal-C33D91, Deal-DAFB82, Deal-8A119B, plus budget-path competitor Deal-1BCA50 counted in competitor) + 8 competitor incumbent/preference (Deal-1BCA50, Deal-A2C349, Deal-8A0992, Deal-D0C698, Deal-47F1A1, Deal-BF2A98, Deal-369281, Deal-9FCD0D, Deal-64B19A - actually 9, plus approval nodec cases). Full buyer list of 46 in per-deal lines above. Bonusly = 6 product gap + 5 competitor with Bonusly shortfall (Deal-F97C37, Deal-422BA6, Deal-DDAB52, Deal-0F96AA, Deal-286F9C) + 1 pricing cheaper (Deal-7B2236) = 12. Unknown = 23 other + 9 vague competitor (Deal-F7F635, Deal-381C8C, Deal-F1E8A6, Deal-ACE061, Deal-2D2F8D, Deal-7CC678, Deal-C7156E, Deal-EECC02, Deal-1E7DA9) = 32.

Tag vs text disagreement: 6 deals where tag clearly points one way and text another:
Deal-70F704 - tag Lost DM, text narrow anniversary use + MIA
Deal-8E27DA - tag Feature Request, text swag-only, did not want R&R
Deal-9048EB - tag MIA, text bad fit + multiple feature gaps
Deal-3618CC - tag Lost DM, text Wanted Surveys
Deal-5AD03E - tag Competitor, text wanted defined budget access, no competitor named
Deal-55867E - tag Lost- Timing, text will not move forward, no timeline given

Two patterns worth acting on:
1 Dated 2027/2028 nurture backlog. 18 timing losses name early 2027, new year, Q2 next year / 2028. Examples: Deal-91A056, Deal-831B7B, Deal-39E25C, Deal-B6AC09, Deal-E6E80A, Deal-B038F0, Deal-175756, Deal-15DA99, Deal-F4AF5D, Deal-DAFB82 (2028), Deal-B3ABED (Q2 next year / 2028). Act: timestamped reconnect queue, no new pipeline needed.
2 Ghosting + beatable incumbent/adjacent gaps. 23 other/MIA (Deal-AC944F, Deal-214060, Deal-21B045, Deal-988493, Deal-F308CA, Deal-4664E1, Deal-D48E0B, Deal-7CB44D and 15 more unresponsive/no-contact) plus competitor stays (Deal-A2C349 Awardco, Deal-47F1A1 WorkTango, Deal-64B19A Motivosity, Deal-BF2A98 HiThrive, Deal-369281 Paylocity, Deal-D0C698 Kudos, Deal-5E64CE Nectar lock to Oct 2027) and cited gaps (Deal-3618CC Surveys, Deal-DC77FE customization points-as-dollars, Deal-242273 digitize points + onsite spend, Deal-5AD03E budget access, Deal-422BA6 ADP TotalSource integration). Act: tighten intro-to-next-step to cut ghosts, and package surveys/customization/budget-access/ADP answers vs incumbents.
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 $0.0963 · 57s · in 43,103 / out 7,367 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": 32, "WATCH": 55, "REVIVE": 42, "RISKY": 6}, "tier_examples": {"LOCK": ["Deal-D348E1", "Deal-C26D20", "Deal-403845"], "ACTION": ["Deal-25F752", "Deal-C6FE92", "Deal-499BF6"], "BUILD": ["Deal-D73B89", "Deal-927338", "Deal-CA5E44"], "WATCH": ["Deal-E53952", "Deal-5408B0", "Deal-9AAE5F"], "REVIVE": ["Deal-2D1F1B", "Deal-950043", "Deal-7BBDFA"], "RISKY": ["Deal-547B2B", "Deal-B7EBD1", "Deal-A2B47C"]}, "risky_deals": ["Deal-547B2B", "Deal-B7EBD1", "Deal-A2B47C", "Deal-2465CE", "Deal-584EE5", "Deal-FD9F4E"], "lock_violations": 0, "pipeline_shape": "156 deals: 55 with meetings_30d>0 vs 101 with zero; 3+6+18+32+55+42=156. Weight sits in early/mid PIPELINE WATCH/REVIVE while close-end relies on 3 LOCK plus 18 ACTION and 6 COMMIT-no-meeting RISKY deals."}
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 $0.0168 · 27s · in 1,860 / out 2,735 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
Arithmetic:
- Transcripts processed: 6 (TX-001 through TX-006)
- Prospect-stated budget numbers: 3 of 6 — $40,000 (TX-001) + $25,000 (TX-002) + $12,000 (TX-005) = $77,000
- Competitor prospect-raised: 3 of 6 (TX-001, TX-003, TX-005)
- Explicitly agreed next steps: 5 of 6 (all except TX-004)

JSON:
[
  {
    "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": ["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": "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": ["security review took three months for our last vendor — that's my hesitation", "procurement cycle runs six to eight weeks minimum"],
    "confidence": "medium"
  },
  {
    "transcript_id": "TX-005",
    "deal_alias": "Deal-F8767A",
    "why_buys": ["automate service milestones", "give us analytics on recognition equity across departments"],
    "pain_points": ["night-shift teams feel invisible — their engagement scores run 20 points lower", "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", "exec team is skeptical after a failed rollout two years ago"],
    "confidence": "high"
  },
  {
    "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", "our COO usually prefers building things in-house"],
    "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": ["comparing this against just doing it internally", "our COO usually prefers building things in-house"],
    "confidence": "high"
  }
]
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 $0.0125 · 28s · in 1,175 / out 1,924 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, DS5/COMMIT, close 2026-09-11
Why close: Slack 2026-09-04 Alex Franklin: redlines clean, signing page out, VP People signing tomorrow.
Left: signature.

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

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

Excluded: Deal-2465CE shows DS5/COMMIT $5,400 in CRM but Slack 2026-09-04 Dana Mercer: champion left, procurement froze vendors, blocked until re-staff, Q4 now.

Arithmetic: 11,200 + 9,000 + 6,360 = 26,560 at-risk-close total.
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 $0.0303 · 23s · in 19,732 / out 1,331 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 assessed: 5. Real gap: 2, Plan gate: 1, Rollout/enablement: 1, Rep-only (excluded): 1. 2+1+1+1=5.

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

2. 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."
Classification: real gap. Product docs: HRIS: "Workday, BambooHR, Gusto, Rippling (Pro and above)." "ADP Workforce Now integrations are NOT currently listed as supported."
Deal: Deal-D0D6B5. Amount: missing — not in data provided.

3. Quote: "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. Product docs: "Custom report builder | — | — | yes" (Enterprise only).
Deal: Deal-CFE7F4. Amount: missing — not in data provided.

4. 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."
Classification: rollout/enablement issue. Product docs: "Slack and Microsoft Teams integration | yes | yes | yes" (all plans).
Deal: Deal-84DBA6. Amount: missing — not in data provided.

5. TG-005 / Deal-36C33F: excluded — no prospect gap. Only rep states lack of native mobile app; prospect line is "Good to know. The web version should be fine for our office staff for now." Rep language does not count as prospect voice.

Summary (real gaps only):
- Deal-EC3025 — SCIM user provisioning — Amount: missing
- Deal-D0D6B5 — ADP Workforce Now integration — Amount: missing
Total at-risk amount for real gaps: cannot be calculated — amounts not in data provided.
rep-performance 5 tests
stale-pipeline-by-rep0.67
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 $0.1874 · 105s · in 73,740 / out 21,735 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, using only dates <= 2026-09-05. Future meeting dates excluded from recency. Stale = 2026-09-05 - last_contact > 7 days, i.e. last_contact <= 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 (Alex Franklin, DS2, 7200)
- Deal-57FF13 (Elena Sinclair, DS1, 2100)

Stale deals, by owner, amount descending. Days = 2026-09-05 minus last_contact.

Bryce Harmon:
- Deal-2D1F1B, DS1, 240000, 81 days (2026-06-16)
- Deal-66D1FC, DS1, 99000, 16 days (2026-08-20)
- Deal-950043, DS1, 70000, 19 days (2026-08-17)
- Deal-B23205, DS1, 45000, 16 days (2026-08-20)
- Deal-7BBDFA, DS3, 37440, 46 days (2026-07-21)
- Deal-332637, DS2, 36000, 9 days (2026-08-27)
- Deal-1BEEBF, DS1, 31500, 19 days (2026-08-17)
- Deal-A414F6, DS1, 25200, 19 days (2026-08-17; future 2026-09-10 meeting ignored)
- Deal-C5658B, DS1, 23400, 16 days (2026-08-20)
- Deal-40522D, DS3, 21000, 19 days (2026-08-17)
- Deal-C1FA6D, DS1, 18000, 16 days (2026-08-20; future 2026-09-15 meeting ignored)
- Deal-01E193, DS1, 12600, 8 days (2026-08-28; future 2026-09-09 meeting ignored)
- Deal-F0EBBB, DS3, 11400, 24 days (2026-08-12)
- Deal-927338, DS1, 10920, 18 days (2026-08-18; future 2026-09-17 meeting ignored)
- Deal-E25A09, DS1, 6000, 9 days (2026-08-27)
- Deal-C9C286, DS2, 5502, 9 days (2026-08-27)
- Deal-012CB1, DS1, 1, 23 days (2026-08-13)
- Deal-3795AD, DS2, 1, 8 days (2026-08-28; future 2026-10-02 meeting ignored)

Dana Mercer:
- Deal-44EA29, DS2, 60000, 10 days (2026-08-26)
- Deal-E51FB7, DS2, 43875, 12 days (2026-08-24)
- Deal-B42F46, DS1, 27000, 19 days (2026-08-17)
- Deal-BA3DDC, DS3, 23400, 15 days (2026-08-21)
- Deal-9DDE86, DS2, 20000, 15 days (2026-08-21)
- Deal-215CCA, DS3, 18900, 17 days (2026-08-19)
- Deal-5EED42, DS3, 16250, 11 days (2026-08-25)
- Deal-57887A, DS2, 15000, 8 days (2026-08-28)
- Deal-944310, DS4, 10500, 33 days (2026-08-03; future 2026-09-15 meeting ignored)
- Deal-B7EBD1, DS5, 9000, 16 days (2026-08-20)
- Deal-3974EB, DS4, 9000, 8 days (2026-08-28)
- Deal-F40F04, DS2, 8100, 15 days (2026-08-21)
- Deal-7599B8, DS3, 7350, 18 days (2026-08-18; future 2026-09-10 meeting ignored)
- Deal-87DDD1, DS1, 5000, 19 days (2026-08-17)
- Deal-F336B6, DS3, 4200, 15 days (2026-08-21)
- Deal-0660B4, DS4, 1920, 16 days (2026-08-20)

Alex Franklin:
- Deal-CC08D1, DS1, 24000, 16 days (2026-08-20)
- Deal-E73427, DS3, 18000, 10 days (2026-08-26)
- Deal-885F45, DS2, 9300, 12 days (2026-08-24)
- Deal-C2FF3C, DS1, 8316, 10 days (2026-08-26)
- Deal-0D2F7A, DS3, 5100, 12 days (2026-08-24)
- Deal-6C60D4, DS3, 4800, 12 days (2026-08-24)
- Deal-13FEBD, DS2, 4680, 12 days (2026-08-24)
- Deal-819506, DS1, 4400, 8 days (2026-08-28; future 2026-09-09 meeting ignored)
- Deal-9D0060, DS3, 3840, 12 days (2026-08-24)
- Deal-690476, DS2, 3600, 18 days (2026-08-18)
- Deal-C6D97A, DS4, 3240, 8 days (2026-08-28)
- Deal-EE195F, DS3, 3120, 8 days (2026-08-28)
- Deal-278DEC, DS3, 2700, 8 days (2026-08-28)
- Deal-635B8E, DS3, 2600, 18 days (2026-08-18)
- Deal-6883F3, DS1, 2400, 16 days (2026-08-20)
- Deal-4A13AD, DS3, 2160, 26 days (2026-08-10)
- Deal-F67D31, DS2, 1800, 8 days (2026-08-28)
- Deal-5FDCE4, DS3, 1600, 12 days (2026-08-24)
- Deal-BA571A, DS4, 1080, 18 days (2026-08-18)

Cole Ingram:
- Deal-D04904, DS2, 58529.25, 11 days (2026-08-25)
- Deal-B25F40, DS3, 40000, 8 days (2026-08-28)
- Deal-813836, DS2, 32175, 11 days (2026-08-25)
- Deal-1BA595, DS2, 31750, 11 days (2026-08-25)
- Deal-CFE1E8, DS3, 18000, 11 days (2026-08-25)
- Deal-CD47A6, DS2, 12168, 11 days (2026-08-25)
- Deal-627646, DS3, 11193, 11 days (2026-08-25)
- Deal-FF809F, DS2, 7781.2, 11 days (2026-08-25)
- Deal-AF932D, DS2, 7225.4, 11 days (2026-08-25)
- Deal-A71728, DS2, 6947.5, 11 days (2026-08-25)
- Deal-8BC9F5, DS2, 5616, 10 days (2026-08-26)
- Deal-175395, DS3, 4779.88, 11 days (2026-08-25)
- Deal-481E24, DS3, 4140, 10 days (2026-08-26)
- Deal-C7F9BF, DS2, 3360, 11 days (2026-08-25)
- Deal-2F3A66, DS3, 3334.8, 11 days (2026-08-25)
- Deal-342E96, DS2, 2700, 24 days (2026-08-12)
- Deal-E568D5, DS3, 1875, 11 days (2026-08-25)
- Deal-FD9F4E, DS5, 1330, 10 days (2026-08-26)

Farid Osman:
- Deal-8BA24E, DS1, 2880, 8 days (2026-08-28; future 2026-09-15 meeting ignored)
- Deal-8FDCD2, DS1, 1, 15 days (2026-08-21; future 2026-09-15 meeting ignored)

Totals:
- Bryce Harmon: 18 stale deals, 692964 total. 240000+99000+70000+45000+37440+36000+31500+25200+23400+21000+18000+12600+11400+10920+6000+5502+1+1 = 692964
- Dana Mercer: 16 stale deals, 279495 total. 60000+43875+27000+23400+20000+18900+16250+15000+10500+9000+9000+8100+7350+5000+4200+1920 = 279495
- Alex Franklin: 19 stale deals, 106736 total (excluding Deal-3EED2C with missing engagement data). 24000+18000+9300+8316+5100+4800+4680+4400+3840+3600+3240+3120+2700+2600+2400+2160+1800+1600+1080 = 106736
- Cole Ingram: 18 stale deals, 252905.03 total. 58529.25+40000+32175+31750+18000+12168+11193+7781.2+7225.4+6947.5+5616+4779.88+4140+3360+3334.8+2700+1875+1330 = 252905.03
- Farid Osman: 2 stale deals, 2881 total. 2880+1 = 2881
- Elena Sinclair: 0 determinable stale deals; sole open deal Deal-57FF13 has no engagement row.
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 $0.5079 · 141s · in 276,793 / out 26,353 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: 2026-09-05. DS2 window: t_ds2 2026-08-06 to 2026-09-05 inclusive.

Per rep last-30-day activities summed from engagements_by_deal_90d.csv over that rep's deals in deals_open.csv:

Bryce Harmon (119337721):
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.
DS2 entries (4): Deal-25F752 (2026-08-10), Deal-CA7DC0 (2026-08-12), Deal-1CCE5C (2026-08-06), Deal-D73B89 (2026-09-03).
Activities per DS2 = 205/4 = 51.25.

Dana Mercer (83155923):
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.
DS2 entries (1): Deal-57887A (2026-08-07).
Activities per DS2 = 113/1 = 113.0.

Alex Franklin (84342457):
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.
DS2 entries (18): Deal-403845 (2026-09-02), Deal-1FC049 (2026-09-03), Deal-3EED2C (2026-09-03), Deal-7FA0C3 (2026-08-07), Deal-E531A6 (2026-08-07), Deal-5296C9 (2026-08-28), Deal-36C33F (2026-08-11), Deal-EE195F (2026-08-06), Deal-F436DA (2026-08-19), Deal-317E6F (2026-08-12), Deal-D1E6C2 (2026-08-11), Deal-D9A72E (2026-08-06), Deal-CA5E44 (2026-08-24), Deal-4F775F (2026-08-17), Deal-898FC5 (2026-08-28), Deal-46988D (2026-08-26), Deal-E73427 (2026-08-28), Deal-92D97D (2026-09-02).
Activities per DS2 = 384/18 = 21.33.
Missing data: Deal-3EED2C has no row in engagements_by_deal_90d.csv, so its activities are counted as 0 in the totals above.

Cole Ingram (83155924):
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.
DS2 entries (2): Deal-42326B (2026-08-26), Deal-1BA595 (2026-08-12).
Activities per DS2 = 111/2 = 55.5.

Farid Osman (716654662):
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.
DS2 entries (1): Deal-499BF6 (2026-08-26).
Activities per DS2 = 72/1 = 72.0.

Elena Sinclair (701163055):
Emails 0, Calls 0, Meetings 0. Total = 0. DS2 entries (0): none.
Activities per DS2 = undefined (0/0). Missing data: Deal-57FF13 has no row in engagements_by_deal_90d.csv.

Efficiency rank (lowest activities per DS2 = most efficient):
1. Alex Franklin — 21.33
2. Bryce Harmon — 51.25
3. Cole Ingram — 55.50
4. Farid Osman — 72.00
5. Dana Mercer — 113.00
Elena Sinclair — unranked, no DS2 entries.

Most efficient rep: Alex Franklin.
Highest-volume rep: Alex Franklin (384 total activities).
They do not differ — they are the same rep.

⚠️ File-mutation verifier: 1 file edit(s) FAILED this turn despite any wording above that may suggest otherwise. Run `git status` or `read_file` to confirm what actually landed.
  • `/Users/amaniphipps/.hermes/cache/scratch/deals_open.csv` — [write_file] Refusing to overwrite `/Users/amaniphipps/.hermes/cache/scratch/deals_open.csv`: `/Users/amaniphipps/.hermes/cache/scratch/deals_open.csv` exists but this task has not seen its full c…
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 $0.1678 · 97s · in 83,414 / out 13,312 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, quota snapshot 2026-09-05)

1. Bookings vs quota
Quota: 200,000. Bookings QTD: 150,000. Attainment: 150,000 / 200,000 = 75.0%. Remaining: 50,000.
Arithmetic: 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.
Excluded: Deal-B3E6F1 24,000 closed 2026-06-20 (before quarter).

2. New vs expansion split (QTD won only)
New: 113,500 (5 deals). Expansion: 36,500 (3 deals).
New arithmetic: 40,000 (Deal-A1C3E5) + 35,000 (Deal-B7D2F4) + 21,000 (Deal-C9E1A6) + 11,000 (Deal-D4B8C2) + 6,500 (Deal-E6F3A9) = 113,500.
Expansion arithmetic: 20,000 (Deal-F2C7D8) + 12,000 (Deal-A8B4D6) + 4,500 (Deal-C5D9E2) = 36,500.

3. Active pipeline by stage (all open, 125 deals)
DS1: 284,621 (20 deals)
DS2: 353,760 (28 deals)
DS3: 552,705 (67 deals)
DS4: 23,574 (5 deals)
DS5: 45,730 (5 deals)
Total: 284,621 + 353,760 + 552,705 + 23,574 + 45,730 = 1,260,390.

4. Rolling 90-day DS2-to-won rate (window 2026-06-07 to 2026-09-05, resolved DS2 entries only)
8 won / (8 won + 27 lost) = 8 / 35 = 22.9%.
Method: numerator = QTD won with entered_ds2 in window (all 8 qualify, entered 2026-06-22 to 2026-08-10). Denominator = won + lost with entered_ds2 in window (all 27 lost qualify, entered 2026-06-12 to 2026-08-08). Open deals still in pipeline are excluded; DS1 open deals with blank entered_ds2 cannot enter the rate — data missing for those.

5. Wins and losses (QTD, close_date in quarter and <= 2026-09-05)
Wins: 8. Losses: 27.
Top loss reason: Lost- Timing (1 year or more), 13 of 27 (48.1%).
Full loss-reason count: Lost- Timing (1 year or more) 13, MIA 5, Competitor 5, Lost DM 2, Feature Request 1, Lost- Does not fit ICP (write in notes) 1. Total 13+5+5+2+1+1 = 27. Loss amount QTD: 329,272.

6. Activity volume, last 30 days (sum of per-deal 30d counters across all 161 deal rows)
Emails: 807. Calls: 112. Meetings: 128. Notes: 50. Total touches: 807 + 112 + 128 + 50 = 1,097.

Coaching observations
1. Timing kills nearly half of losses. 13 of 27 losses are Lost- Timing (1 year or more). Tighten DS2 entry on urgency and timeline; 22.9% DS2-to-won on resolved entries leaves little room for slip.
2. Pipeline is wide but early. DS1+DS2 = 638,381 (50.6% of 1,260,390); DS4+DS5 = 69,304 (23,574 + 45,730). Total coverage of the 50,000 remainder is 25.2x, but late-stage covers it only 1.39x (69,304 / 50,000). Pull DS3 deals forward; DS3 holds 552,705 across 67 deals.
3. Wins get meetings, losses do not. QTD wins average 23/8 = 2.9 meetings per deal (Deal-A1C3E5 4, Deal-F2C7D8 1, Deal-B7D2F4 2, Deal-C9E1A6 4, Deal-A8B4D6 3, Deal-D4B8C2 3, Deal-E6F3A9 4, Deal-C5D9E2 2); losses average 13/27 = 0.5. Shift mix from email (807 of 1,097 touches) toward live meetings on DS2/DS3 deals.
multithreading-gap0.50
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 $0.0350 · 28s · in 20,782 / out 2,111 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
Missing data — cannot complete as asked.

Missing: deal open/closed status, amount, and stage for every deal_alias. No deal master file was provided. Active as-of date was also not provided; using 2026-10-19 as as-of:

Arithmetic: 2026-10-19 minus 60 days = 2026-08-20. Active = last_engaged_date >= 2026-08-20 and is_former = false.

Provisional active-contact counts (not filtered to open, since open status is missing):

- Deal-EC3025: 1 active — CT-047C54 champion. Excluded: CT-F2C1AE is_former=true.
- Deal-92D97D: 1 active — CT-01F5B4 HR admin. Excluded: CT-A902AE 2026-06-01 < 2026-08-20.
- Deal-50D386: 2 active — champion, HR admin.
- Deal-D0D6B5: 1 active — CT-87CED4 champion. Excluded: CT-DE6D7C 2026-08-19 and CT-FD70B2 2026-08-07 < 2026-08-20.
- Deal-5BFE3B: 1 active — CT-57123B champion. Excluded: CT-5CE757 2026-08-12 < 2026-08-20.
- Deal-84DBA6: 3 active — champion, economic buyer, IT security.
- Deal-36C33F: 0 active — CT-4FE556 2026-08-15 < 2026-08-20; others is_former=true.
- Deal-4B0BEB: 3 active — champion, economic buyer, HR admin. Excluded: CT-3E135F 2026-08-09 < 2026-08-20.
- Deal-885F45: 1 active — CT-51C81E economic buyer. Excluded: CT-D9A0E8 2026-08-11 < 2026-08-20.
- Deal-FCBE5B: 1 active — CT-4A5317 champion.
- Deal-5408B0: 1 active — CT-D33AE4 champion. Excluded: CT-8742FD 2026-08-18 < 2026-08-20.
- Deal-D348E1: 4 active — champion, economic buyer, IT security, finance. Excluded: CT-BEDF5E 2026-08-19 < 2026-08-20.
- Deal-C6D97A: 2 active — both champion (CT-223DDC, CT-4E8A2B). Excluded: CT-4E8A2B 2026-08-05 < 2026-08-20. Single-persona.
- Deal-F9A08A: 1 active — CT-931B10 champion. Excluded: CT-913581 2026-06-20 < 2026-08-20.

Cannot report for flagged deals: amount, stage, personas missing, most valuable persona to add given the stage, because amount/stage/open status were not provided. Provide deal master to finish.
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 $0.0173 · 33s · in 17 / out 3,301 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 five minutes: 8/10 calls open with the identical retailer story. 8 ÷ 10 = 80%. Deals: Deal-D348E1, Deal-5408B0, Deal-547B2B, Deal-C61CF7, Deal-60C2C2, Deal-EDC141, Deal-D9A12F, Deal-84DBA6. Others: 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: Deal-D348E1, Deal-547B2B, Deal-60C2C2, Deal-84DBA6): reframes to turnover savings. 4 ÷ 10 = 40%.
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 / underwater (3/10: Deal-5408B0, Deal-C61CF7, Deal-D9A12F): proposes 90-day pilot. 3 ÷ 10 = 30%.
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 status quo (3/10: Deal-403845, Deal-EDC141, Deal-1E2498): counters with scale/automation/analytics. 3 ÷ 10 = 30%.
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."

Concrete next step agreed rate: 7 agreed ÷ 10 calls = 0.70 = 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."

Competitors raised by prospects: 2 total — Awardco in Deal-547B2B, Kudos in Deal-EDC141.

Coaching note 1: Replace the repeated opener in 8/10 calls with deal-specific openers like those used in Deal-403845 and Deal-1E2498, to avoid sounding scripted.
Coaching note 2: Add a fallback next step for committee / no-urgency stalls in Deal-403845, Deal-EDC141, and Deal-84DBA6, where no working session was secured.
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 $0.0832 · 42s · in 48,201 / out 5,395 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 (close_date 2026-07-01 to 2026-09-30 inclusive)

Inside quarter counts:
COMMIT: 7 deals
BEST_CASE: 24 deals
PIPELINE: 23 deals (counts 0)
Total inside: 54 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 (Deal-2D7423) + 24,000 (Deal-25F752) + 19,656 (Deal-E53952) + 16,250 (Deal-5EED42) + 11,116 (Deal-FA32A0) + 10,800 (Deal-FC22A3) + 10,500 (Deal-944310) + 9,890 (Deal-5195DB) + 9,720 (Deal-180D02) + 9,000 (Deal-3974EB) + 7,200 (Deal-5D8CEE) + 3,840 (Deal-9D0060) + 3,780 (Deal-46988D) + 3,600 (Deal-357C30) + 3,240 (Deal-C6D97A) + 3,150 (Deal-DAF1D9) + 3,120 (Deal-EE195F) + 3,060 (Deal-55164C) + 2,916 (Deal-001FF4) + 2,760 (Deal-7B3B0F) + 2,484 (Deal-F9A08A) + 2,100 (Deal-8952F0) + 1,920 (Deal-1FC049) + 528 (Deal-87412C) = 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:
Count: 32 deals (1 COMMIT + 9 BEST_CASE + 22 PIPELINE)
Total amount: 227,575
13,770 COMMIT (Deal-D348E1) + 28,240 BEST_CASE + 185,565 PIPELINE = 227,575

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
Forecast_category conflicts with stage: COMMIT appears in DS1 (Deal-A5E80A) and DS2 (Deal-499BF6), BEST_CASE appears in DS5 (Deal-C61CF7), and PIPELINE appears in DS4 (Deal-6787C2). Owner is blank on 85 of 86 rows (only Deal-C9C286 has an owner), why_buys_chars is 0 on most rows, and one amount has decimal precision (Deal-42326B, 2480.4). Close dates show heavy quarter-end clustering plus stale past-due opens as of the 2026-09-05 pull (e.g. Deal-333EBB due 2026-08-28, Deal-57FF13 due 2026-09-02, Deal-7A2454 due 2026-09-04), so unattended date filtering would overstate Q3.
aha-moment-2x2PASS 1.00
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 $0.1359 · 55s · in 69,659 / out 11,481 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'; denominator = all 220 rows):

- Both signals (m1_users >= 5 AND m1_redemptions >= 1): 31/47 = 66.0% retained
- Givers-only (m1_users >= 5 AND m1_redemptions = 0): 23/49 = 46.9% retained
- Redemption-only (m1_users < 5 AND m1_redemptions >= 1): 9/29 = 31.0% retained
- Neither (m1_users < 5 AND m1_redemptions = 0): 38/95 = 40.0% retained

Check: 47 + 49 + 29 + 95 = 220. Active: 31 + 23 + 9 + 38 = 101.

Excluded from denominator: 0. No rows excluded. All 220 rows have non-missing m1_users, m1_redemptions, and current_status.

Single signal with largest retention lift: 5+ unique givers.

- Givers >= 5: 54/96 = 56.3% vs givers < 5: 47/124 = 37.9%. Lift = 56.3 - 37.9 = 18.4pp.
- Redemption >= 1: 40/76 = 52.6% vs redemption = 0: 61/144 = 42.4%. Lift = 52.6 - 42.4 = 10.3pp.
- Givers lift (18.4pp) > redemption lift (10.3pp).

What this does and does not prove:

- Does prove: in this 2023 cohort extract (n=220), first-month both-signal companies have a 26.0pp higher observed 24-month retention rate than neither (66.0% vs 40.0%), and higher than either single-signal group.
- Does not prove: causation. It does not prove that causing 5+ givers or 1+ redemption will raise retention, does not adjust for confounders (e.g. product_tier, industry, company size), and does not explain why redemption-only (31.0%) retains below neither (40.0%) in this extract.
arr-rollforward-reconciliationPASS 1.00
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 $0.0614 · 44s · in 26,158 / out 5,317 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
ARR reconciliation as of 2026-09-05. Billing ARR = MRR x 12.

Totals:
CRM company_arr total = 603,581.76
Billing Active ARR (37 active subs) = 604,739.28
Billing All (39 subs incl. 2 cancelled) = 617,897.76

Arithmetic:
604,739.28 active = 617,897.76 all - 13,158.48 cancelled
13,158.48 cancelled = 408.77x12 (4,905.24) + 687.77x12 (8,253.24)
Variance (CRM - Billing Active) = 603,581.76 - 604,739.28 = -1,157.52

Decomposition of -1,157.52 (CRM - Active), sums exactly:
status mismatch: +13,158.48
  C-0C8323BF 4,905.24 + C-0DC4FB8C 8,253.24, cancelled in billing but still valued in CRM
missing records: -11,952.00
  billing-only C-21629AA4 -28,449.24 (2,370.77x12) + CRM-only C-0D5BBE3A +16,497.24
rounding: 0.00
  no 0.01-level differences found; all other matched accounts tie to the cent
other (active value mismatch): -2,364.00
  C-0F7269D7 -2,400.00 + C-0D66DF9E +16.00 + C-14D70CE0 +20.00

Check: 13,158.48 - 11,952.00 + 0.00 - 2,364.00 = -1,157.52

Mismatched accounts (owner data not provided in files; functional suggested owner below, not sourced):
1. C-0C8323BF - billing cancelled 4,905.24, CRM 4,905.24, diff 0 - suggested: RevOps / CRM Admin to zero CRM
2. C-0DC4FB8C - billing cancelled 8,253.24, CRM 8,253.24, diff 0 - suggested: RevOps / CRM Admin to zero CRM
3. C-21629AA4 (SUB-0004) - billing 28,449.24, no CRM record - suggested: RevOps / CRM Admin to create company record
4. C-0D5BBE3A - no billing, CRM 16,497.24 - suggested: Billing Ops to confirm subscription, else RevOps to remove CRM value
5. C-0F7269D7 (SUB-0006) - billing 26,796.00 (2,233.00x12), CRM 24,396.00, diff -2,400.00 - suggested: Billing Ops / AE to confirm correct ARR
6. C-0D66DF9E (SUB-0005) - billing 23,184.00 (1,932.00x12), CRM 23,200.00, diff +16.00 - suggested: RevOps to correct CRM
7. C-14D70CE0 (SUB-0008) - billing 18,180.00 (1,515.00x12), CRM 18,200.00, diff +20.00 - suggested: RevOps to correct CRM

All other active aliases tie exactly: billing MRRx12 = hubspot_arr.

Business rule violations (term !=12 requires cf_agreement_end_date):
SUB-0002 C-1794A52C, term 24, cf_agreement_end_date blank - VIOLATION
SUB-0019 C-22170CA1, term 36, cf_agreement_end_date blank - VIOLATION
SUB-000C C-0DB48281, term 24, 2027-11-30 - compliant
SUB-001A C-0FC4DBB8, term 36, 2027-11-30 - compliant
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 $0.0529 · 45s · in 11,822 / out 6,701 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: simple mean across 30 company_alias rows per month in kvm_monthly.csv.

| KVM | 2026-07 | 2026-08 | Abs. change | Rel. change | Direction |
|---|---|---|---|---|---|
| Giving rate | 0.60230 | 0.60271 | +0.00042 | +0.07% | flat/up |
| Redemptions per user | 1.72998 | 1.73016 | +0.00018 | +0.01% | flat |
| 1:1 engagement | 0.44689 | 0.44718 | +0.00029 | +0.06% | flat/up |
| Pulse engagement | 0.60059 | 0.50861 | -0.09198 | -15.31% | down |

Arithmetic: giving (0.60271-0.60230)=+0.00042; +0.00042/0.60230=+0.07%. Redemptions (1.73016-1.72998)=+0.00018; +0.00018/1.72998=+0.01%. 1:1 (0.44718-0.44689)=+0.00029; +0.00029/0.44689=+0.06%. Pulse (0.50861-0.60059)=-0.09198; -0.09198/0.60059=-15.31%.

Largest relative move: pulse check engagement, driven by size_band=enterprise. Enterprise mean 0.54998 to 0.27428 (-0.27570, -50.13%), vs smb 0.65879 to 0.65731 (-0.22%) and mid_market 0.59299 to 0.59424 (+0.21%). All 10 enterprise aliases fell ~50%, e.g. C-0B2895EF 0.5619 to 0.2864, C-0B2213A9 0.5548 to 0.2801, C-0D6CC8E3 0.5552 to 0.2733, C-0D0B047C 0.5398 to 0.2619. All rows are plan_tier=tier_three, so plan_tier does not differentiate.
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 $0.1601 · 65s · in 67,475 / out 17,157 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 2026-01-01 to 2026-08-31.

Redemptions YTD through 2026-08:
- Redemption count: 378
- Spend: $27,846.00
  Arithmetic: 3,230.00 TangoCard + 8,505.00 Tremendous + 10,873.00 custom + 5,238.00 Snappy = 27,846.00
- Unique redeemers (user_key): 235
- Redemptions per redeemer: 378 / 235 = 1.61

Provider mix, percent of spend (sums to 100.00):
- custom: 10,873.00 / 27,846.00 = 39.05%
- Tremendous: 8,505.00 / 27,846.00 = 30.54%
- Snappy: 5,238.00 / 27,846.00 = 18.81%
- TangoCard: 3,230.00 / 27,846.00 = 11.60%
- Check: 39.05 + 30.54 + 18.81 + 11.60 = 100.00

Top 5 countries by redemptions (count):
1. US: 244
2. CA: 24
3. AU: 21
4. GB: 17
5. NL: 17
GB and NL tie at 17.
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 $0.0456 · 37s · in 20,649 / out 3,855 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
8 accounts meet all 3 rules: R1 health_score <60, R2 churn_save_eligible_amount >0, R3 renewal within 120 days of 2026-09-05 (i.e. 2026-09-05 to 2027-01-03).

Qualified churn-save accounts:

C-0F6C0F34: 49,707.00 - renewal 2026-10-03 (28 days after snapshot), health 51
C-0B827671: 25,365.00 - renewal 2026-11-14 (70 days), health 56
C-0B360C78: 35,748.00 - renewal 2026-10-28 (53 days), health 57
C-0B0F1BAB: 5,494.00 - renewal 2026-09-23 (18 days), health 38
C-0CA21961: 16,829.00 - renewal 2026-12-28 (114 days), health 58
C-0E9C27D1: 41,235.00 - renewal 2026-09-24 (19 days), health 39
C-0CEF69FD: 32,621.00 - renewal 2026-11-21 (77 days), health 53
C-0D3278C7: 17,602.00 - renewal 2026-11-12 (68 days), health 54

Total at stake:
49,707 + 25,365 = 75,072
75,072 + 35,748 = 110,820
110,820 + 5,494 = 116,314
116,314 + 16,829 = 133,143
133,143 + 41,235 = 174,378
174,378 + 32,621 = 206,999
206,999 + 17,602 = 224,601
Total = 224,601.00

Plays: No play-selection rules for usage revival / executive touch / commercial concession were provided in the files. Play fit cannot be determined under documented eligibility rules. Signals per qualified account for play selection:

C-0F6C0F34: champion_active=false, usage=growing, 308/395 seats used
C-0B827671: usage=declining, 113/202 used, champion_active=true
C-0B360C78: usage=growing, 246/327 used, champion_active=true
C-0B0F1BAB: champion_active=false, usage=flat, 238/363 used
C-0CA21961: usage=flat, 84/325 used (25.8%), champion_active=true
C-0E9C27D1: usage=flat, 134/157 used, champion_active=true
C-0CEF69FD: champion_active=false, usage=growing, 97/136 used
C-0D3278C7: usage=declining, 126/380 used (33.2%), champion_active=true

At-risk by health (R1) but NOT qualified:

C-0BC71BDD (55): fails R2 - eligible 0.00
C-0BA71F12 (52): fails R3 - renewal 2027-04-11 (218 days)
C-0F6694C3 (43): fails R2 (0.00) and R3 (2027-03-21, 197 days)
C-0BE96399 (54): fails R2 - eligible 0.00
C-0F876796 (47): fails R3 - renewal 2027-02-06 (154 days)
C-0FCCD2DF (43): fails R2 (0.00) and R3 (2027-04-23, 230 days)
C-10A56B0F (54): fails R2 - eligible 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 $0.0291 · 17s · in 19,413 / out 1,142 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
For C-0DDFC9A7:

Seat coverage
- 150 licensed / 400 headcount = 37.5% covered.

Usage health
- Monthly actives climbed every month Mar-Aug 2026: 88 -> 95 -> 102 -> 110 -> 118 -> 126.
- Aug actives 126 / 150 licensed = 84.0% of licensed seats in use.

Headroom at current per-seat rate
- Per-seat rate: $9,000.00 / 150 = $60.00/seat.
- Seat headroom: 400 - 150 = 250 seats.
- ARR headroom: 250 x $60.00 = $15,000.00.

Who replied / can they buy
- Maria S., People Operations Coordinator, replied 2026-09-02.
- Cannot buy: states “I'm not the right person for purchasing decisions here. Budget and seat expansion sit with Dana R.”

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

Reply email - 66 words

Hi Maria,

Thanks for sharing this - glad to hear the team loves Bonusly.

Love that monthly actives climbed to 126 in August - happy to share a quick usage snapshot you can pass to Dana R. if helpful.

If you're open to it, an intro to Dana would be great, since budget sits with her. No rush - whatever is easiest for 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 $0.0093 · 22s · in 474 / out 1,368 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 status (signup_date: 2026-08-11)

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 — field blank:
- integration_hris: integration_hris = [blank]
- first redemption: first_redemption_at = [blank]

Early engagement signals (onboarding_usage.csv, active_givers):
- Range: 2026-08-11 to 2026-09-04 = 25 days of data
- Start 3 on 2026-08-11, end 15 on 2026-09-04
- Change: 15 - 3 = 12; 12 / 3 = 4.00 = +400%
- Total: 3+3+4+4+5+4+7+5+7+6+9+8+9+9+9+11+10+10+11+13+11+13+13+15+15 = 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 on 2026-09-03 and 2026-09-04

Three things to cover on the call:
1. integration_hris still blank — unblock and set connect date.
2. first_redemption_at still blank despite first_recognition_at on 2026-08-15 — walk through redemption.
3. Convert giver growth (3 to 15) into repeat habit — review what drove 2026-08-26 onward when active_givers reached 11+ and stayed 10-15.
renewal-risk-conflicting-datesPASS 1.00
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 $0.0577 · 47s · in 23,848 / out 6,563 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 — trusted dates 2026-09-15 to 2026-11-24
As-of: usage through 2026-08. Window covers all 20 accounts below.

Date trust rule: is_multi_year=true in Chargebee = trust Chargebee (ChurnZero known wrong for multi-year). is_multi_year=false with matching dates = trust either.

Disagreements (5) — all multi-year, trust Chargebee:
C-0B7D2C30: CZ 2026-09-10 vs CB 2026-09-15, 36mo — use 2026-09-15
C-0BCDB8C2: CZ 2027-09-18 vs CB 2026-09-18, 36mo — use 2026-09-18
C-0D2AB865: CZ 2026-09-10 vs CB 2026-09-22, 24mo — use 2026-09-22
C-0BBE3E60: CZ 2027-09-26 vs CB 2026-09-26, 24mo — use 2026-09-26
C-0F5D2323: CZ 2026-09-10 vs CB 2026-09-29, 24mo — use 2026-09-29
Other 15: CZ = CB, 12mo, no disagreement.

Formulas: seat utilization = seats_used / seats. 3-mo trend = 2026-08 active_users minus 2026-06 active_users, % = diff / 2026-06.

Renewals:

1. C-0B7D2C30 | Dana Mercer | ARR 65901.00 | date used 2026-09-15 *DISAGREEMENT* | seats 274/476 = 57.6% | trend 97>94>84 = -13, -13.4% | HIGH — 57.6% seats with -13.4% 3-mo decline.
2. C-0BCDB8C2 | Cole Ingram | ARR 54427.00 | date used 2026-09-18 *DISAGREEMENT* | seats 232/424 = 54.7% | trend 127>118>110 = -17, -13.4% | HIGH — 54.7% seats with -13.4% 3-mo decline.
3. C-0D2AB865 | Elena Sinclair | ARR 38022.00 | date used 2026-09-22 *DISAGREEMENT* | seats 250/407 = 61.4% | trend 125>117>109 = -16, -12.8% | HIGH — 61.4% seats with -12.8% 3-mo decline.
4. C-0BBE3E60 | Dana Mercer | ARR 30993.00 | date used 2026-09-26 *DISAGREEMENT* | seats 74/114 = 64.9% | trend 39>35>33 = -6, -15.4% | HIGH — 64.9% seats with -15.4% 3-mo decline.
5. C-0F5D2323 | Cole Ingram | ARR 90647.00 | date used 2026-09-29 *DISAGREEMENT* | seats 111/390 = 28.5% | trend 20,21,18 = -2, -10.0% | HIGH — 28.5% seats with flat ~20 active users.
6. C-0EC6999D | Elena Sinclair | ARR 79419.00 | date used 2026-10-03 | seats 31/112 = 27.7% | trend 17,16,15 = -2, -11.8% | HIGH — 27.7% seats with flat ~15-17 active users.
7. C-0B20DB64 | Dana Mercer | ARR 21770.00 | date used 2026-10-07 | seats 214/378 = 56.6% | trend 294,298,294 = 0, 0.0% | MEDIUM — 56.6% seats despite flat usage at ~294.
8. C-0BBC4E7A | Cole Ingram | ARR 56374.00 | date used 2026-10-10 | seats 228/337 = 67.7% | trend 142,141,139 = -3, -2.1% | MEDIUM — 67.7% seats with flat usage.
9. C-0FD551AB | Elena Sinclair | ARR 48815.00 | date used 2026-10-14 | seats 210/376 = 55.9% | trend 123,122,126 = +3, +2.4% | MEDIUM — 55.9% seats despite flat usage.
10. C-0F9F8F13 | Dana Mercer | ARR 46230.00 | date used 2026-10-18 | seats 199/352 = 56.5% | trend 185,185,182 = -3, -1.6% | MEDIUM — 56.5% seats with flat usage.
11. C-0BC34584 | Cole Ingram | ARR 16740.00 | date used 2026-10-22 | seats 327/494 = 66.2% | trend 104,104,106 = +2, +1.9% | MEDIUM — 66.2% seats with flat usage.
12. C-0B7A7546 | Elena Sinclair | ARR 35062.00 | date used 2026-10-25 | seats 182/205 = 88.8% | trend 64,65,63 = -1, -1.6% | LOW — 88.8% seats with flat usage.
13. C-0B369871 | Dana Mercer | ARR 85128.00 | date used 2026-10-29 | seats 317/422 = 75.1% | trend 326>330>333 = +7, +2.1% | LOW — 75.1% seats with growing usage.
14. C-0B144C78 | Cole Ingram | ARR 30899.00 | date used 2026-11-02 | seats 169/224 = 75.4% | trend 101,101,106 = +5, +5.0% | LOW — 75.4% seats with growing usage.
15. C-0FC4DBB8 | Elena Sinclair | ARR 94732.00 | date used 2026-11-05 | seats 356/464 = 76.7% | trend 189>191>193 = +4, +2.1% | LOW — 76.7% seats with growing usage.
16. C-0D5BBE3A | Dana Mercer | ARR 39740.00 | date used 2026-11-09 | seats 85/102 = 83.3% | trend 88>90>91 = +3, +3.4% | LOW — 83.3% seats with growing usage.
17. C-0FB9D5AF | Cole Ingram | ARR 63158.00 | date used 2026-11-13 | seats 144/199 = 72.4% | trend 173,173,176 = +3, +1.7% | LOW — 72.4% seats with growing usage.
18. C-0B344485 | Elena Sinclair | ARR 64384.00 | date used 2026-11-16 | seats 224/287 = 78.0% | trend 238>240>244 = +6, +2.5% | LOW — 78.0% seats with growing usage.
19. C-0CB2C1B4 | Dana Mercer | ARR 40628.00 | date used 2026-11-20 | seats 386/473 = 81.6% | trend 47,48,49 = +2, +4.3% | LOW — 81.6% seats with flat/growing usage.
20. C-22170CA1 | Cole Ingram | ARR 45646.00 | date used 2026-11-24 | seats 251/294 = 85.4% | trend 143,148,146 = +3, +2.1% | LOW — 85.4% seats with flat/growing usage.

Totals:
Total ARR renewing = 65901+54427+38022+30993+90647+79419+21770+56374+48815+46230+16740+35062+85128+30899+94732+39740+63158+64384+40628+45646 = 1048715.00

ARR at risk (HIGH only) = 65901+54427+38022+30993+90647+79419 = 359409.00
MEDIUM ARR = 21770+56374+48815+46230+16740 = 189929.00
LOW ARR = 1048715-359409-189929 = 499377.00
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 $0.0927 · 43s · in 43,335 / out 7,722 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.

BROAD PATTERNS — ranked by ARR exposure:

1. HRIS provisioning failure
Count: 12, Share: 12/80 = 15.0%, Distinct accounts: 3, ARR affected: 36,000 + 30,000 + 48,000 = $114,000
Ex: IC-460059, IC-460062
Recommendation: Audit HRIS sync job and silent-failure logging.

2. Rewards redemption / checkout failure
Count: 18, Share: 18/80 = 22.5%, Distinct accounts: 7, ARR affected: 8,900 + 10,700 + 9,600 + 8,700 + 11,000 + 9,600 + 10,300 = $68,800
Ex: IC-460025, IC-460024
Recommendation: Fix checkout error handling to prevent points deduction on failure.

3. Points posting failure
Count: 20, Share: 20/80 = 25.0%, Distinct accounts: 9, ARR affected: 3,500 + 4,500 + 4,500 + 3,400 + 4,200 + 2,700 + 2,900 + 2,500 + 2,900 = $31,100
Ex: IC-460004, IC-460016
Recommendation: Investigate points-ledger posting delay/failure.

4. Slack integration failure
Count: 14, Share: 14/80 = 17.5%, Distinct accounts: 4, ARR affected: 4,400 + 5,400 + 3,900 + 5,200 = $18,900
Ex: IC-460041, IC-460047
Recommendation: Fix Slack sync disconnect, toggle reset, and slash-command errors.

SINGLE-ACCOUNT NOISE — excluded from broad ranking:

5. Billing / seat-count / renewal-tier errors
Count: 16, Share: 16/80 = 20.0%, Distinct accounts: 1 (C-0E9C27D1), ARR affected: $52,000
Ex: IC-460071, IC-460069
Recommendation: Resolve C-0E9C27D1 seat-count and renewal-tier billing with account-level audit.
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 $0.0115 · 22s · in 739 / out 1,826 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

Scoring: 1 point per exact match on industry, size_band, use_case, region. Max 4. Eligible pool = has_case_study=true only.

Rank 1: C-64171065 — 3/4
1 (industry: Technology) + 1 (size_band: Mid-Market) + 1 (use_case: employee_recognition) + 0 (region: NA-East vs NA-West) = 3
Drove match: industry, size_band, use_case

Rank 2: C-11C31562 — 3/4
0 (industry: Manufacturing vs Technology) + 1 (size_band: Mid-Market) + 1 (use_case: employee_recognition) + 1 (region: NA-West) = 3
Drove match: size_band, use_case, region

Rank 3: C-A13C193D — 3/4
1 (industry: Technology) + 1 (size_band: Mid-Market) + 0 (use_case: retention vs employee_recognition) + 1 (region: NA-West) = 3
Drove match: industry, size_band, region

Tie-break: prioritized use_case match, then industry match.
No other has_case_study=true customer scores >2/4.
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 $0.0605 · 37s · in 26,848 / out 5,562 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.

PAID

paid_search
- spend: 6 x 6,000 = 36,000
- SQMs: 40
- SQOs: 18
- cost per SQM: 36,000 / 40 = 900
- cost per SQO: 36,000 / 18 = 2,000
- SQM-to-SQO rate: 18 / 40 = 45.0%
- pipeline amount: 18 x 40,000 = 720,000
- pipeline per dollar: 720,000 / 36,000 = 20.0

linkedin_ads
- spend: 6 x 4,000 = 24,000
- SQMs: 25
- SQOs: 8
- cost per SQM: 24,000 / 25 = 960
- cost per SQO: 24,000 / 8 = 3,000
- SQM-to-SQO rate: 8 / 25 = 32.0%
- pipeline amount: 8 x 12,000 = 96,000
- pipeline per dollar: 96,000 / 24,000 = 4.0

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

paid_social
- spend: 6 x 3,000 = 18,000
- SQMs: 0, SQOs: 0, pipeline amount: 0
- cost per SQM: undefined
- cost per SQO: undefined
- SQM-to-SQO rate: undefined
- pipeline per dollar: 0 / 18,000 = 0.0

ORGANIC / UNPAID (no spend file provided)

organic_search
- volume: 30
- SQOs: 10
- SQO rate: 10 / 30 = 33.3%
- pipeline: 10 x 9,000 = 90,000

referral
- volume: 15
- SQOs: 6
- SQO rate: 6 / 15 = 40.0%
- pipeline: 6 x 8,000 = 48,000

DATE FLAGS: SQO date precedes SQM date
- CT-000044, linkedin_ads, sqm_date 2026-07-23, sqo_date 2026-07-18, 12000
- CT-000041, linkedin_ads, sqm_date 2026-06-14, sqo_date 2026-06-09, 12000

REALLOCATION RECOMMENDATION
Cut or pause paid_social: 18,000 spend with 0 SQMs. Reduce linkedin_ads: highest cost per SQO at 3,000 and lowest paid pipeline per dollar at 4.0. Reallocate to paid_search first: 2,000 cost per SQO, 20.0 pipeline per dollar, 45.0% SQM-to-SQO rate; second to webinars: 750 cost per SQM, 1,800 cost per SQO, 6.67 pipeline per dollar.

Confidence: low-moderate. Sample sizes are small: paid_search 40/18, linkedin_ads 25/8, webinars 12/5, paid_social 0, organic_search 30/10. Two linkedin_ads SQOs, CT-000044 and CT-000041, have date errors, so linkedin_ads 8 SQOs / 32.0% rate is uncertain.
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 $0.0184 · 35s · in 1,387 / out 3,248 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 — updated 2026-10-19

1. One-line positioning
- Points-based recognition with an engaging recognition feed [S02][S16].
- Old card claim “for mid-market” unverified: no snippet states positioning; only a mid-market reviewer cited [S04].

2. Pricing with source and date (newer wins)
- Current: $7 per user/month, Recognition Starter tier, annual billing required, per pricing page updated 2026-08-12 [S17].
- Conflict note: supersedes $5 per user/month, annual billing, from 2026-01-20 [S03] and still $5 on 2026-04-01 [S08].
- Deal-quote conflict: $6.50/user/mo quoted to a 500-seat prospect, annual term, noted 2026-06-02 [S13] vs $7/user/mo list with 15% discount offered for 3-year term, noted 2026-08-14 [S18].
- Arithmetic: $7 x (1-0.15) = $5.95 effective per user/month for the 3-year offer [S18].

3. Where they win
- Fast setup: under a week, Slack integration worked out of the box [S04].
- EU enterprise fit: strong for distributed EU teams, multi-language support praised [S12].
- EU data residency pitched [S05]; generally available, Dublin office opened, 2026-07-01 [S15].
- Support response praised, under 4 hours [S22].
- Engaging recognition feed [S02][S16].
- Excluded: UI “clunky” is AE opinion only, not a competitor fact [S09].

4. Where we win
- Analytics depth: limited analytics [S02]; reporting dashboards basic vs enterprise tools [S07]; 800-seat prospect picked Bonusly over Rivally citing analytics depth [S25].
- Admin / IT: lacks SCIM provisioning, manual user management painful [S10]; admin tooling lags peers [S16]; admin console lacks bulk recognition editing [S24]; analytics exports CSV-only [S20].
- Rewards: EMEA catalog thinner than US catalog [S14].
- Excluded: “discounting aggressively” is rep opinion only [S21].

5. Objections and responses (responses limited to provided data)
- Obj: “Rivally covers EU residency / EU teams.” [S05][S12][S15] Resp: Acknowledge; no Bonusly residency/capability data provided — cannot counter from this dataset.
- Obj: “Rivally is fast to set up with Slack.” [S04] Resp: No Bonusly setup-time data provided — cannot counter from this dataset.
- Obj: “Rivally feed is engaging / support is fast.” [S02][S16][S22] Resp: Redirect to cited differentiators only: analytics depth [S25][S02][S07] and SCIM/admin gaps [S10][S16][S24].
- Old card “Rivally lacks a Slack integration” is contradicted by [S04]; do not use.

6. Recent changes
- 2025-11-04: $40M Series C led by Northgate Ventures [S01].
- 2026-03-05: launched ‘Rivally Pulse’ lightweight survey add-on [S06].
- 2026-05-09: hired ex-Workday VP EMEA to lead European expansion [S11].
- 2026-07-01: Dublin office; EU data residency GA [S15].
- 2026-08-12: Recognition Starter repriced to $7/user/mo annual [S17].
- 2026-08-19: Microsoft Teams app v2 in public preview [S19].
- 2026-09-01: Pulse exits beta; priced as add-on, not bundled [S23].

7. Our 12-month win/loss vs Rivally
- Window used: 2025-10 through 2026-08 (data provided ends 2026-08; no Sep 2026 data provided).
- Record: 12 wins – 6 losses in 18 deals. Arithmetic: 12+6=18; 12/18=66.7% win rate.
- Wins (12): Deal-A9FD43, Deal-F65C8F, Deal-7AA785, Deal-44C524, Deal-0D0CD6, Deal-E46EAB, Deal-D5B790, Deal-1D2392, Deal-5C636E, Deal-67BE14, Deal-1B6969, Deal-F03E7B.
- Losses (6): Deal-D263E0, Deal-935746, Deal-9066A6, Deal-5645A5, Deal-72A02F, Deal-C6FFAA.
- Excluded from 12-mo as outside window: Deal-7767F5 (2025-09 loss), Deal-072E31 (2025-09 win). Full file total 20 deals = 13-7; 13+7=20.

Unverified from old card
- “Rivally was acquired by WorkHuman in 2025” — unverified: no snippet supports it.
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 $0.0490 · 32s · in 24,103 / out 3,103 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 steps):

New Logo Nurture: sent 1386 (500+458+428). Open 490/1386=35.4%. Reply 90/1386=6.5%. Meeting 27/1386=1.9%. Weakest Step 3: 120/428=28.0% open, 18/428=4.2% reply, 6/428=1.4% meet.

Expansion Nurture: sent 875 (300+300+275). Open 565/875=64.6%. Reply 59/875=6.7%. Meeting 12/875=1.4%. Weakest Step 3: 95/275=34.5% open, 12/275=4.4% reply.

Cold Outbound - HR Leaders: sent 1785 (600+595+590). Open 545/1785=30.5%. Reply 8/1785=0.45%. Meeting 0/1785=0%. Weakest Step 1: 5/600=0.83% reply, 0 meet - dead on arrival, decays to 1/590=0.17% in Step 3.

Cold Outbound - People Ops: sent 1163 (400+386+377). Open 340/1163=29.2%. Reply 29/1163=2.49%. Meeting 6/1163=0.52%. Weakest Step 3: 80/377=21.2% open, 6/377=1.59% reply, 1/377=0.27% meet.

Tracking error: Expansion Nurture Step 2: 340 opened > 300 sent =113.3% open. Impossible without re-opens counted as uniques, carryover, or join error.

Audience overlap: 12 contact_keys in 2 sequences. Cross-sequence: CT-000301, CT-000624 in New Logo Nurture + Expansion Nurture. CT-000849, CT-000884, CT-001101, CT-001103, CT-001153, CT-001159, CT-001217, CT-001227, CT-001345 in Cold Outbound - HR Leaders + Cold Outbound - People Ops. CT-001033 appears 3x (2x HR Leaders + 1x People Ops).

Failure mode <2% reply: Cold Outbound - HR Leaders at 0.45%. Opens 30.5% are normal, so not deliverability. Replies fail, 0 meetings: offer/message-audience mismatch.

Fixes: HR Leaders - pause, rewrite Step 1 hook/offer. Expansion - fix open logging before judging Step 3. People Ops - replace Step 3 with breakup/case proof.

Fix first: Cold Outbound - HR Leaders. Largest waste (1785 sends, 0 meetings) and contaminates People Ops via overlap.
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 $0.0283 · 22s · in 16,731 / out 1,640 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
Weekly marketing goals update — Q3-2026 (66/92 days elapsed = 71.7%)

Pace baseline: 66 / 92 = 0.7174. Expected QTD = target x 0.7174.

1. SQMs
QTD actual: 230
Target: 300
Delta: 230 - 300 = -70
Attainment: 230 / 300 = 76.7%
Expected QTD: 300 x 66 / 92 = 215.2
Pace: ahead (230 > 215.2 by +14.8)

2. SQOs
QTD actual: 84
Target: 120
Delta: 84 - 120 = -36
Attainment: 84 / 120 = 70.0%
Expected QTD: 120 x 66 / 92 = 86.1
Pace: behind (84 < 86.1 by -2.1)

3. DS2s
QTD actual: 40
Target: 75
Delta: 40 - 75 = -35
Attainment: 40 / 75 = 53.3%
Expected QTD: 75 x 66 / 92 = 53.8
Pace: behind (40 < 53.8 by -13.8)

4. Closed-lost MIA rate
QTD actual: 5 / 25 = 0.20 (20.0%)
Target: 0.10 (10.0%)
Delta: 0.20 - 0.10 = +0.10 (+10.0pp, lower_better)
Pace: behind (actual exceeds target; rate is not time-prorated)

5. Same-quarter closes
QTD actual: 10
Target: 20
Delta: 10 - 20 = -10
Attainment: 10 / 20 = 50.0%
Expected QTD: 20 x 66 / 92 = 14.3
Pace: behind (10 < 14.3 by -4.3)

6. Active pipeline coverage against target
QTD actual: 3,000,000
Target: 4,000,000
Delta: 3,000,000 - 4,000,000 = -1,000,000
Coverage: 3,000,000 / 4,000,000 = 0.75 (75.0%)
Expected QTD: 4,000,000 x 66 / 92 = 2,869,565
Pace: ahead (3,000,000 > 2,869,565 by +130,435)

What moved this week: Data missing. No prior-week snapshot or deal/company-level movement data was provided, so week-over-week change cannot be calculated. No deal/company aliases were provided to cite.
communication 5 tests
ceo-slack-compressionPASS 1.00
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 $0.0310 · 26s · in 19,571 / out 1,527 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
Q3 weighted forecast is 115,976.75 from 54 in-quarter deals: 44,729 COMMIT plus 35 percent of 203,565 BEST_CASE. 32 deals worth 227,575 fall after Sep 30, including COMMIT Deal-D348E1 for 13,770 on Oct 15. Do not lock this: all 7 COMMIT deals have empty why-buy, so the committed base has no documented reason.
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 $0.0134 · 28s · in 456 / out 2,344 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
Subject: Re: July 28 demo + 150-seat pricing [Deal-0D2F7A]

Hi team,

Following up on the Aug 5 recap of the July 28 demo with pricing for 150 seats.

You reacted strongly to automated milestone awards and the points catalog, with birthdays and anniversaries tracked manually today.

Is this still a priority? Can we reconnect briefly next week to confirm fit?

Best,
Alex Franklin

Word count: 54 < 120
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 $0.0082 · 23s · in 314 / out 1,167 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 (52-46=6 short, 46/52=88.5% to goal), with the webinar channel contributing 18 of those SQMs (18/46=39.1% of the week's total) while paid search held cost per SQM at 150 dollars.

Sales converted 14 SQOs and set 9 DS2 meetings, creating 310000 dollars in new pipeline while closing 3 same-quarter deals, showing steady conversion from meeting to pipeline to close within the week.

CS saved 2 renewals to protect the base, held team NPS at 61, and carries 3 open red-flag accounts into next week, giving the team a clear and focused save list.

PLG added 412 new signups with 31 percent activation (412x0.31=127.72, about 128 activated), and 38 companies reached the aha moment of 10 recognition gives (38/412=9.2% of signups).
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 $0.0082 · 17s · in 118 / out 1,210 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

Active:

- Apex Rewards Co — 2 partner-sourced opps, $275,000. Deal-DDAAF2 ($180,000) + Deal-2CF33E ($95,000) = $275,000. Both in DS1. Co-webinar locked for 09-15.
- HRCloud Partners — 1 partner-sourced opp, $140,000. Deal-F1CDA5 ($140,000). Opp moved to DS2 after security review closed.
- CultureBridge — 2 partner-sourced opps, $135,000. Deal-096E1D ($60,000) + Deal-067213 ($75,000) = $135,000. Both early stage from lunch-and-learn.
- WorkWell Group — 0 partner-sourced opps, $0. No sourced deals this period; joint playbook restart planned for Q4, planning call booked for 09-09.

Quiet:

- Recogniq — quiet, no activity in provided data.
- KudosWave — quiet, no activity in provided data.
- PeopleFirst Advisors — quiet, no activity in provided data.
- TotalPerk — quiet, no activity in provided data.

Partner-sourced pipeline total: 5 deals, $550,000.

Arithmetic: $180,000 + $95,000 + $140,000 + $60,000 + $75,000 = $550,000. By partner: Apex Rewards Co $275,000 (2) + HRCloud Partners $140,000 (1) + CultureBridge $135,000 (2) + WorkWell Group $0 (0) = $550,000 (5).
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 $0.0058 · 17s · in 121 / out 638 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. Available to prospects under NDA. [P2]

Q4: Duration of the contract plus 90 days, after which it is deleted from production systems. [P3]

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

Q6: Yes. SAML 2.0 single sign-on and SCIM user provisioning are 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 provided excerpts. No excerpt addresses ISO 27001. Would require compliance/certification documentation. No excerpt cited.

Q9: Unanswerable from provided excerpts. No excerpt states a contractual uptime SLA percentage. Would require SLA / MSA. No excerpt cited.

Q10: Unanswerable from provided excerpts. No excerpt addresses HIPAA or a Business Associate Agreement. Would require legal/compliance documentation. No excerpt cited.
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 $0.1095 · 50s · in 64,456 / out 6,123 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 vs email-drafter
Severity: CRITICAL | Action: MERGE
Evidence: both claim ALWAYS on identical phrases: "write me an email", "draft a follow-up", "help me reply" / "help me reply to this", "what should I say", "bump email", "contract nudge". comms-drafter body also routes deal-strategy to deal-strategy-coach; email-drafter body routes same to deal-strategy-coach.
Proposal: MERGE into one drafting skill; keep one trigger list, delete the other skill.

2) Circular delegation chain — deal-strategy-coach <-> email-drafter
Severity: CRITICAL | Action: UPDATE_BODY
Evidence: deal-strategy-coach body: "When drafting manager-to-prospect emails, use the `email-drafter` skill". email-drafter body: "If the user needs strategic deal coaching ... point them to the deal-strategy-coach skill". Chain length 2: deal-strategy-coach -> email-drafter -> deal-strategy-coach.
Proposal: UPDATE_BODY to make delegation one-way only; remove one direction.

3) Dangling delegation target with no file / no manifest row
Severity: CRITICAL | Action: REVIEW
Evidence: invoked as skills but 0 files provided and 0 manifest rows: `prospect-research-multithreading` invoked by 3 files (comms-drafter, deal-strategy-coach, email-drafter); `bonusly-brand` invoked by 4 files (comms-drafter, email-drafter, sales-forecast, signalforge-claim-compressor); `signalforge-reports` invoked by 2 files (pipeline-intelligence-report, weekly-pipeline-report); 8x `bonusly-*` specialists invoked by 1 file (analysis-validator 12.4: 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); `skill-orchestrator` referenced by 1 file (signalforge-feedback). Total distinct dangling skill names counted from bodies: 1+1+1+8+1=12.
Proposal: REVIEW all 12; either add missing files+manifest rows or remove references. Named example: prospect-research-multithreading.

4) Version conflict — which survives
Severity: WARNING | Action: UPDATE_BODY
Evidence: analysis-validator.SKILL.md header: "Version: 3.6" + "Last Updated: May 9, 2026 (v3.6" + footer "analysis-validator v3.6" vs Section 7 trail template: "Validator: analysis-validator v3.2". No other skill has duplicate manifest rows. Arithmetic: 3.6 - 3.2 = 0.4 version drift in same file.
Proposal: UPDATE_BODY Section 7 trail to v3.6; v3.6 survives, v3.2 deleted.

5) Manifest descriptions >1,024 chars
Severity: INFO | Action: REVIEW
Evidence: description_chars given: 656, 897, 996, 792, 965, 676, 945, 1004, 1006, 962, 1006, 708, 762, 656. Max = 1006. Arithmetic: count where >1024 = 0/14 = 0.
Proposal: No TRIM_DESC needed; REVIEW confirms 0 exceed.

6) Hardcoded page ids, dates, person names in bodies
Severity: WARNING | Action: UPDATE_BODY
Evidence samples exactly as given: analysis-validator: "83155923", "150582537", "Dana Mercer", "Gavin Porter", "May 4, 2026", "May 9, 2026", "~452,000", "~110,097"; pipeline-intelligence-report: "1973303", "119337721", "83155923", "83155924", "84342457", "1520255671"; partner-digest: "73fe98de-a4a3-4869-9f8a-bb1eeed4cf7f", "1958248479", "2286616609", "2286321666", "Week of May 19, 2026", "May 16, 2026", "Amani"; sales-forecast: "2232811524", "2232582148", "1CLZeOsElVDF_LF0ZG_t2nfwvhnZ6bpwqM_nX3WEYzcw", "1ENuaEcCuLjdKhMvp8FK3Ys1ek5Aw9ZuOZhsHJJFoB_k", "Q3 2026 Forecast Intelligence — July 9, 2026", "Elena", "Alaina"; weekly-pipeline-report: same 2 spreadsheet ids + "Ben Lavin"; stale-pipeline-report: "C0561C1JCPJ", "55483190"; signalforge-feedback: "2295136266", "2234417154", "2247295002"; closed-lost-analysis: "Estee Lauder", "LIFTOFF", "MinIO", "Softheon"; signalforge-claim-compressor: "Panopto", "Schneider Downs", "Felix Construction"; deal-strategy-coach: "2257879045/AE+Excellence+Playbook+April+2026"; next-to-close: "https://app.hubspot.com/contacts/1973303/record/0-3/{hs_object_id}".
Proposal: UPDATE_BODY to parameterize ids/dates/names to live lookups; rewrite nothing now.

7) Manifest drift BOTH directions
Severity: INFO | Action: REVIEW
Evidence: Files provided = 14. Manifest rows = 14. Names match exactly, including 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. Arithmetic: 14-14=0 files-with-no-row; 14-14=0 rows-with-no-file.
Proposal: No DELETE_SKILL needed; drift is 0 both ways.
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 $0.0110 · 25s · in 666 / out 1,715 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

Arithmetic: none required. No calculations performed.

Step 1 [M01] — Acknowledge and take IC
Action: PagerDuty alert for reward-worker queue depth > 10k acknowledged.
Who: Bryce Harmon
Verification: Not stated in thread.
State change: No. Rollback: N/A.

Step 2 [M02] — Check reward queue depth
Command: `bundle exec rake sidekiq:queue_depth`
Who: Farid Osman
Verification: Returned 48,213 pending jobs. Normal stated as under 500.
State change: No. Rollback: N/A.

Step 3 [M03] — Check dead set — NEEDS CONFIRMATION (exact command not stated)
Action: Dead set observed at 112 jobs, all Redis::TimeoutError from around 13:58.
Who: Farid Osman
Verification: Not stated in thread.
State change: No. Rollback: N/A.

Step 4 [M04] — Pause enqueue
Command: `bin/rails runner 'FeatureFlag.disable(:auto_recognition_enqueue)'`
Who: Farid Osman
Verification: Not stated in M04 — NEEDS CONFIRMATION.
State change: Yes. Rollback (per M04): `bin/rails runner 'FeatureFlag.enable(:auto_recognition_enqueue)'`

Step 5 [M05] — Clear dead set — NEEDS CONFIRMATION (exact command, verification, rollback not stated)
Action: "cleared out the dead set" from console.
Who: Elena Sinclair
Verification: Not stated in thread.
State change: Yes. Rollback: None stated in thread.

Step 6 [M06] — Scale workers up
Command: `kubectl scale deployment/reward-worker --replicas=6` (was 3)
Who: Bryce Harmon
Verification: Not stated in M06. Later reports: 9,400 and falling ~1,200/min [M07]; 0 [M08].
State change: Yes. Rollback (per M06): `kubectl scale deployment/reward-worker --replicas=3`

Step 7 [M07] — Monitor drain
Action: Queue depth check reported at 9,400 and falling ~1,200/min.
Who: Farid Osman
Verification: The 9,400 reading itself.
State change: No. Rollback: N/A.

Step 8 [M08] — Verify drain to zero
Command: `bundle exec rake sidekiq:queue_depth`
Who: Cole Ingram
Verification: Returned 0. Error rate in Datadog back to baseline.
State change: No. Rollback: N/A.

Step 9 [M09] — Re-enable enqueue
Command: `bin/rails runner 'FeatureFlag.enable(:auto_recognition_enqueue)'`
Who: Bryce Harmon
Verification: 40 new jobs processed cleanly in the next 3 minutes.
State change: Yes. Rollback: None stated in M09 for this step; inverse disable command was given in M04.

Step 10 [M10] — Scale workers back down, resolve
Command: `kubectl scale deployment/reward-worker --replicas=3`
Who: Bryce Harmon
Verification: Queue stable at 0. Incident resolved.
State change: Yes. Rollback: None stated in thread for this step.
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 $0.0359 · 26s · in 20,641 / out 2,361 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

Service and job:
Service: reward-service, then sidekiq. Downstream: api-gateway, web-app.
Job: RewardGiveJob. sidekiq_jobs.csv also shows RecognitionDigestJob failing with same error.

Cascade in order:

1. 14:01:12 reward-service ERROR Redis timeout
2. 14:01:20 reward-service ERROR retry exhausted for RewardGiveJob
3. 14:01:30 reward-service ERROR retry exhausted for RewardGiveJob
4. 14:01:40 reward-service ERROR retry exhausted for RewardGiveJob
5. 14:01:40 sidekiq ERROR RewardGiveJob failed: Redis::TimeoutError; retrying in 60s
6. 14:02:28 sidekiq ERROR RewardGiveJob failed
7. 14:02:30 sidekiq WARN Queue reward depth above 10,000
8. 14:03:05 api-gateway ERROR 502 upstream timeout calling reward-service /gives
9. 14:03:30 web-app ERROR Give form submission failed: upstream 502 from api-gateway
10. 14:03:31 sidekiq ERROR RewardGiveJob failed
11. 14:03:48 api-gateway ERROR 502 upstream timeout
12. 14:04:13 api-gateway ERROR 502 upstream timeout
13. 14:04:22 sidekiq ERROR RewardGiveJob failed
14. 14:04:45 web-app ERROR Give form submission failed: upstream 502
15. 14:05:16 api-gateway ERROR 502 upstream timeout
16. 14:05:26 sidekiq ERROR RewardGiveJob failed
17. 14:05:42 web-app ERROR Give form submission failed: upstream 502
18. 14:06:47 sidekiq ERROR RewardGiveJob failed
19. 14:06:49 web-app ERROR Give form submission failed: upstream 502
20. 14:06:52 api-gateway ERROR 502 upstream timeout
21. 14:22:10 reward-service INFO Redis connection restored; resuming job processing
22. 14:24:45 sidekiq INFO Queue reward depth below 500

Arithmetic:
reward-service ERROR = 1 + 3 = 4
sidekiq ERROR = 6
api-gateway ERROR 502 = 5
web-app ERROR = 4
sidekiq_jobs.csv: RewardGiveJob J-00001 to J-00012 = 12; RecognitionDigestJob J-00013 to J-00016 = 4; total 12 + 4 = 16
Outage window: 14:22:10 - 14:01:12 = 20m 58s = 20*60 + 58 = 1,258s
Queue drop: >10,000 to <500 = at least 10,000 - 500 = 9,500 drained

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

Logs do not show:
No deal/company aliases provided in either file, so none to cite.
No root cause for the Redis timeout.
No Redis server-side metrics, no deploy/config change, no customer/revenue impact counts beyond queue depth warnings.
No resolution action, only restoration timestamps.
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 $0.0300 · 25s · in 19,484 / out 1,323 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 — targeting_rules: segment:beta_companies — company_count: 42
   Controls per code: app/models/recognition.rb — if enabled, StreakTracker.record(give)

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

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

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

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

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

7. legacy_give_modal — state: off — targeting_rules: segment:legacy_plan — company_count: 14
   Controls per code: no reference in provided excerpt.

8. survey_boosters_q3 — state: on — targeting_rules: segment:legacy_plan — company_count: 7
   Controls per code: no reference in provided excerpt.

9. paused_offboard_cleanup — state: off — targeting_rules: [blank] — company_count: 0
   Controls per code: no reference in provided excerpt.
   No targets: targeting_rules empty and company_count 0.

Arithmetic check (counts as listed, not deduplicated unique companies):
On flags: 42 + 220 + 87 + 65 + 7 = 421
Off flags: 12 + 9 + 14 + 0 = 35
Total listed: 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 $0.0094 · 20s · in 593 / out 1,375 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 — Driving clause: "obligations survive for three (3) years after termination." Reasoning: mutual, Delaware law, full carve-outs, no non-solicit/non-compete. Arithmetic: 2 + 3 = 5 years total obligation.
NDA-2 ([PARTY B]) — YELLOW — Driving clause: "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." Reasoning: otherwise standard mutual/Delaware deal but embedded non-solicit needs counsel review. Arithmetic: 3 + 18/12 = 3 + 1.5 = 4.5 years total restriction.
NDA-3 ([PARTY C]) — RED — Driving clause: "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." Reasoning: one-way, 5-year term, no carve-outs stated, Ireland exclusive jurisdiction plus 3-year non-compete needs full legal review. Arithmetic: 5 years confidentiality; 3 years non-compete.