← back to all models ← RevenueBench home
openai

openai/gpt-6-sol

Mean 0.941 · 29/40 perfect tests · $7.59 total · modalities in: text, image, file · out: text · each card: the prompt → the correct answer (gold) → this model's actual answer

What do the modalities mean?

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

data-crm 5 tests
stage-hygiene-auditPASS 1.00
Plain-English question: How much of the open DS2+ pipeline is missing a substantive why-buys, and is anything missing DS1 timestamps or out of order?
Prompt — what the model saw
Audit stage hygiene on the open pipeline below. Rules: a deal at DS2 or later must have a substantive why-buys (15+ characters, not a placeholder such as tbd, n/a, see notes). A why_buys value of the form LONG(n) means the real text was present but truncated for display; treat it as present and substantive. Every deal should have a DS1 entry timestamp. A deal whose stage entry timestamps are out of order regressed (an earlier-stage timestamp is later than a later-stage timestamp). Report: percent of DS2+ deals non-compliant on why-buys overall and by owner (use the owners table for names), count of deals with no DS1 timestamp, count that regressed, and three process fixes. State definitions before numbers.
cost $0.2192 · 58s · in 12 / out 3,827 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+ includes open deals at DS2, DS3, DS4, or DS5. A why-buys is non-compliant if blank, under 15 characters, or a placeholder; LONG(n) counts as substantive. A regression means a recorded earlier-stage entry timestamp is later than a recorded later-stage entry timestamp; equal dates are not regressions.

Why-buys non-compliance:
- Overall: 101 / 124 = 81.5%
- 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%

No DS1 timestamp: 0 deals. Regressed stage timestamps: 0 deals.

Process fixes:
1. Require a substantive why-buys before advancement to DS2; reject blanks and placeholders.
2. Validate DS1 timestamp capture when every deal is created or enters DS1.
3. Alert on out-of-order stage timestamps and route exceptions for correction.
owner-resolutionPASS 1.00
Plain-English question: Every open deal has a blank owner name — resolve each one to a real person using the owners table.
Prompt — what the model saw
The deal extract below has an owner name field that is blank on nearly every row and an owner id field that is populated. Using the owners table, resolve each open deal to an owner name. Report: number of deals resolved, deals whose owner id has no match in the owners table (list them), the owner ids that map to archived/deactivated owners (list their names), and the total pipeline amount per resolved owner. Do not guess a name for any unmatched id.
cost $0.1100 · 32s · in 9 / out 1,888 tok
✓ resolved_count✓ unmatched_none✓ deactivated_flagged✓ jake_amount✓ justin_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 · jake_amount · justin_amount · no_invented

Model's actual answer

show the model's full answer
All 156 open deals resolve to a name in the owners table. Arithmetic by owner:

| Resolved owner (owner ID) | Deals | Pipeline amount |
|---|---:|---:|
| Bryce Harmon (119337721) | 35 | $66,676 + $987,468 = $1,054,144 |
| Alex Franklin (84342457) | 67 | $69,304 + $555,006 = $624,310 |
| Dana Mercer (83155923) | 24 | $56,470 + $284,725 = $341,195 |
| Cole Ingram (83155924) | 22 | $4,090 + $284,071.43 = $288,161.43 |
| Farid Osman (716654662) | 7 | $1,249 + $1 + $1 + $1 + $2,880 + $1 + $1 = $4,134 |
| Elena Sinclair (701163055) | 1 | $2,100 |

Resolved count: 35 + 67 + 24 + 22 + 7 + 1 = 156. Total resolved pipeline: $1,054,144 + $624,310 + $341,195 + $288,161.43 + $4,134 + $2,100 = $2,314,044.43.

Unmatched owner IDs: none. Open deals mapped to archived/deactivated owners: none. The archived owners in the owners table—Gavin Porter (1520255671) and Hugo Lindqvist (77260721)—own no deals in this extract.
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 $0.2280 · 39s · in 15 / out 1,756 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 matching deal ID in deals_open (67 − 37 = 30). Sample aliases: Deal-8FA85D, Deal-8FC3F9, Deal-3B7945, Deal-42B265, Deal-9CCC42. A missing match in this open-deals list does not establish why the deal is absent.

(b) Duplicate conversation keys: 0 rows; no calls_90d value exceeds distinct_conversation_keys.

(c) DS3-or-later open-deal call coverage: 25 of 85 = 29.4%.
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 $0.1185 · 19s · in 6 / out 584 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
-- The catalog does not provide a recognition-event table or giver identifier,
-- so unique givers and recognition count cannot be calculated.
-- It also does not document the company key or event timestamp needed to
-- assign redemption records to each customer's first calendar month.
SELECT
    'Cannot calculate the requested metrics from the provided catalog.' AS missing_data;
```
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 $0.2028 · 59s · in 15 / out 3,644 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
The extract has no deals file. Owner, stage, amount, close date, and why-buys completeness cannot be calculated. Pipeline amount at stake also cannot be calculated, so the final fixes cannot be ranked by that measure.

Completeness (populated rows ÷ rows supplied):

| Object | Field | Arithmetic | Complete |
|---|---|---:|---:|
| Companies | Industry | 34 ÷ 34 | 100.0% |
| Companies | Employee count | 25 ÷ 34 | 73.5% |
| Companies | HQ country | 28 ÷ 34 | 82.4% |
| Contacts | Email, nonblank | 52 ÷ 52 | 100.0% |
| Contacts | Email, syntactically valid | 49 ÷ 52 | 94.2% |
| Contacts | Title | 39 ÷ 52 | 75.0% |
| Contacts | Persona | 37 ÷ 52 | 71.2% |

Duplicate company clusters, identified by shared domain (no company-name field was supplied):

- `acme-corp.com`: `C-0A092931` and `C-0A092932`. Proposed survivor: `C-0A092931` (lower alias as a provisional tie-breaker, not evidence of a better record). Reconcile employee counts of 500 versus 510 before merging.
- `globex.io`: `C-0A092933` and `C-0A092934`. Proposed survivor: `C-0A092933` (same provisional tie-breaker). Reconcile `SaaS` versus `Technology` before merging.

Invalid emails: `CT-0010` (`user0@`), `CT-0080` (`user0@`), and `CT-0192` (`user2@`). Request verified addresses; the contact domain alone does not establish the missing address.

Domain mismatch: `CT-0011` has `user1@other-domain.com`, while its contact domain and `C-66D1FC` company domain are `66d1fc.com`. Verify the association or address; do not rewrite it automatically.

Enrichment-backed missing-field fills, matched by domain:

- Employee count → 400: `C-EC3025`, `C-96039F`, `C-44EA29`, `C-D04904`, `C-B23205`, `C-60C75F`, `C-7BBDFA`, `C-50D386`.
- No missing HQ country can be filled: the matching enrichment rows for `C-2D1F1B`, `C-D73B89`, `C-44EA29`, `C-D04904`, and `C-2C60E5` also have blank countries. `C-EE9FFB` has no matching enrichment row.
- `C-93C8BF` has a missing employee count and no matching enrichment row. Leave it blank.

Populated-value disagreements and source recommendation:

- For `C-66D1FC`, `C-EC3025`, `C-44EA29`, `C-92D97D`, `C-D04904`, `C-77A95A`, `C-AA8DDA`, `C-B25F40`, `C-60C75F`, and `C-425E2A`, CRM industry is `tech`, `Technology`, or `Tech `; enrichment says `Computer Software`. Retain the populated CRM value pending a taxonomy decision; the enrichment label is more specific, not proof that CRM is wrong.
- CRM country `US` or `USA` versus enrichment `United States` occurs for `C-66D1FC`, `C-950043`, `C-EC3025`, `C-96039F`, `C-77A95A`, `C-B23205`, `C-E51FB7`, `C-D0662E`, `C-425E2A`, and `C-2D7423`. These are label differences, not conflicting countries. Recommend a single standardized country format; retain the original CRM values until that convention is chosen.
- Separately, the duplicate pairs disagree within CRM on employee count (`C-0A092931` 500; `C-0A092932` 510) and industry (`C-0A092933` `SaaS`; `C-0A092934` `Technology`). Enrichment has no matching rows to resolve either disagreement.

Ten fixes to queue — **unranked**, because no deal amounts or deal-to-company links were supplied:

1. Obtain the deals extract with owner, stage, amount, close date, why-buys, and company association; then calculate deal-field completeness and amount at stake.
2. Review the `acme-corp.com` duplicate cluster and its 500/510 employee-count conflict before merging.
3. Review the `globex.io` duplicate cluster and its `SaaS`/`Technology` conflict before merging.
4. Verify the email for `CT-0010`.
5. Verify the email for `CT-0080`.
6. Verify the email for `CT-0192`.
7. Investigate the email/company-domain mismatch for `CT-0011`.
8. Fill employee count on the eight enrichment-matched companies listed above.
9. Source, rather than infer, the remaining missing company employee count and six missing HQ countries.
10. Collect missing contact titles (13 of 52) and personas (15 of 52); do not infer either from another contact’s record.
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 $0.2789 · 119s · in 18 / out 7,481 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
Classifications below use only the supplied tag and free-text. “Other / unknown” means the text does not establish a primary cause; MIA is an outcome, not a cause. No supplied reason says a champion left.

| Category / side | Deals |
|---|---|
| Pricing / buyer | Deal-7ED004, Deal-7B2236, Deal-C33D91, Deal-8A119B |
| Competitor / buyer | Deal-F7F635, Deal-F97C37, Deal-422BA6, Deal-DDAB52, Deal-ACE061, Deal-2D2F8D, Deal-1BCA50, Deal-A2C349, Deal-C7156E, Deal-8A0992, Deal-D0C698, Deal-EECC02, Deal-47F1A1, Deal-BF2A98, Deal-1E7DA9, Deal-286F9C, Deal-369281, Deal-9FCD0D, Deal-64B19A |
| Competitor / unknown | Deal-381C8C, Deal-F1E8A6, Deal-0F96AA, Deal-7CC678 |
| No decision / buyer | Deal-13E9CF, Deal-E74A73, Deal-8E27DA, Deal-FAC17C, Deal-50E5D8, Deal-413C56, Deal-2A292B, Deal-7FBAC6, Deal-F325A5, Deal-ABD14C |
| Timing / buyer | Deal-DB0AAC, Deal-91A056, Deal-29326C, Deal-831B7B, Deal-39E25C, Deal-B3ABED, Deal-ED9AE7, Deal-B6AC09, Deal-E6E80A, Deal-B038F0, Deal-175756, Deal-BB78F3, Deal-15DA99, Deal-F4AF5D, Deal-79B7A1, Deal-9F176A, Deal-8A0992, Deal-69CF3D, Deal-ECBF89, Deal-D1A623, Deal-FEDBCB, Deal-DAFB82, Deal-2FEDDB |
| Product gap / Bonusly | Deal-9048EB, Deal-3618CC, Deal-5AD03E, Deal-981AD4, Deal-DC77FE |
| Other / unknown | Deal-AC944F, Deal-214060, Deal-5DB9B0, Deal-21B045, Deal-988493, Deal-F308CA, Deal-70F704, Deal-4664E1, Deal-D48E0B, Deal-583ADB, Deal-E0441F, Deal-7CB44D, Deal-AFA56C, Deal-D1AABF, Deal-2BBA21, Deal-386F6E, Deal-55867E, Deal-3F86A0, Deal-096750, Deal-79E61A, Deal-AE7C4E, Deal-DAB4F1, Deal-B4B50F, Deal-5885B9 |

Correction to the table: Deal-8A0992 appears twice. Its Nectar exit fee and October 2027 contract end make timing the primary category, not competitor. Removing it from competitor yields the counts below.

Category counts: pricing 4 + competitor 22 + no decision 10 + timing 23 + product gap 5 + champion left 0 + other 24 = 88. The supplied CSV has 90 rows; the remaining two are Deal-242273 and Deal-5E64CE. Deal-242273 is competitor / buyer (the text describes a vendor differentiator, not a confirmed Bonusly product inability). Deal-5E64CE is timing / buyer (Nectar exit fee and contract end). Final counts: pricing 4 + competitor 23 + no decision 10 + timing 24 + product gap 5 + champion left 0 + other 24 = 90. Side split: buyer 57 + Bonusly 5 + unknown 28 = 90.

Clear tag–text disagreements: 4 — Deal-8E27DA (Feature Request vs. not wanting R&R), Deal-9048EB (MIA vs. stated bad fit and feature gaps), Deal-5E64CE (doing nothing/not a priority/cost vs. an identified contract-end timing constraint), and Deal-5AD03E (Competitor vs. stated budget-access requirement). This excludes vague tags or text that merely lacks detail.

Two patterns worth acting on:
1. Secure specific re-engagement dates for timing losses: 24 deals, including Deal-91A056, Deal-E6E80A, and Deal-5E64CE, describe a later window or contract constraint.
2. Capture the actual competitive decision criterion: 23 competitor losses, but several reasons only say “another direction” or give no specifics (Deal-381C8C, Deal-F1E8A6, Deal-7CC678). The more specific entries point to differentiated offerings or requirements (Deal-F97C37, Deal-422BA6, Deal-DC77FE); the vague entries cannot support a targeted response.
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 $0.3089 · 72s · in 24 / out 3,066 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":20,"BUILD":31,"REVIVE":22,"WATCH":45,"RISKY":35},"tier_examples":{"LOCK":["Deal-D348E1","Deal-C26D20","Deal-403845"],"ACTION":["Deal-25F752","Deal-944310","Deal-3974EB"],"BUILD":["Deal-6787C2","Deal-A5E80A","Deal-499BF6"],"REVIVE":["Deal-2D1F1B","Deal-66D1FC","Deal-950043"],"WATCH":["Deal-C9C286","Deal-332637","Deal-E25A09"],"RISKY":["Deal-E53952","Deal-5408B0","Deal-9AAE5F"]},"risky_deals":["Deal-E53952","Deal-5408B0","Deal-9AAE5F","Deal-547B2B","Deal-B7EBD1","Deal-A2B47C","Deal-2465CE","Deal-C61CF7","Deal-62D607","Deal-584EE5","Deal-C6D97A","Deal-7B3B0F","Deal-F9A08A","Deal-0660B4","Deal-FD9F4E","Deal-BA571A","Deal-FC22A3","Deal-7BBDFA","Deal-60C2C2","Deal-4A13AD","Deal-8AD4A5","Deal-15D24F","Deal-9D0060","Deal-690476","Deal-635B8E","Deal-ED725A","Deal-55164C","Deal-3BA5EA","Deal-5FDCE4","Deal-F336B6","Deal-5EED42","Deal-BA3DDC","Deal-7599B8","Deal-F9A3C1","Deal-FA32A0"],"lock_violations":0,"pipeline_shape":"3 LOCK + 20 ACTION + 31 BUILD + 22 REVIVE + 45 WATCH + 35 RISKY = 156 deals. RISKY comprises 29 BEST_CASE and 6 COMMIT deals with zero meetings_30d despite those forecast categories. Engagement rows are missing for Deal-3EED2C and Deal-57FF13; their meeting activity cannot be assessed."}
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 $0.1575 · 28s · in 9 / out 1,564 tok
✓ json_emitted✓ budget_signal✓ null_discipline✓ stakeholders✓ competitor_prospect_only

✓ Correct Answer (ground truth)

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

Model's actual answer

show the model's full answer
[
  {
    "transcript_id": "TX-001",
    "deal_alias": "Deal-CFE7F4",
    "why_buys": ["Automate anniversary and birthday awards."],
    "pain_points": ["An HR team of three cannot keep up with awards manually.", "Spreadsheet tracking lets people slip through the cracks."],
    "stakeholders": ["Prospect (VP People)", "Prospect (HR Admin)"],
    "budget_signal": "About $40k earmarked for engagement tools this fiscal year.",
    "timeline_signal": "Ideally live before open enrollment in November.",
    "competitor_mentioned": "Achievers — evaluated last year; considered too heavy for a team their size.",
    "next_step": "Security review on September 12.",
    "objections": ["IT sign-off requires SSO and audit logs."],
    "confidence": "high"
  },
  {
    "transcript_id": "TX-002",
    "deal_alias": "Deal-70BB30",
    "why_buys": ["Tie recognition to retention for the hourly workforce."],
    "pain_points": ["Regretted turnover among hourly workers is over 30%."],
    "stakeholders": ["Prospect (Head of Total Rewards)", "Prospect (CFO)"],
    "budget_signal": "Finance approved a $25k pilot budget for this quarter.",
    "timeline_signal": "Decision wanted by end of September; pilot agreement to be routed to legal this week.",
    "competitor_mentioned": null,
    "next_step": "Send the pilot agreement; the prospect will route it to legal this week.",
    "objections": ["Workday integration must be rock solid."],
    "confidence": "high"
  },
  {
    "transcript_id": "TX-003",
    "deal_alias": "Deal-530B50",
    "why_buys": ["Make recognition visible across 12 retail locations."],
    "pain_points": ["Store managers have no budget autonomy for on-the-spot recognition."],
    "stakeholders": ["Prospect (People Ops Manager)"],
    "budget_signal": null,
    "timeline_signal": "No rush until Q1.",
    "competitor_mentioned": "Bucketlist — the CEO used it at her last company and liked it.",
    "next_step": "Schedule a call with the CEO; the prospect will send two times.",
    "objections": ["The CEO must be sold first and decides people-related purchases."],
    "confidence": "high"
  },
  {
    "transcript_id": "TX-004",
    "deal_alias": "Deal-180D02",
    "why_buys": ["Consolidate three recognition tools into one."],
    "pain_points": ["They pay for three tools, none of which connect to their HRIS."],
    "stakeholders": ["Prospect (VP People)", "Prospect (IT Security Lead)"],
    "budget_signal": "The VP People can approve an annual cost under $15k without board approval.",
    "timeline_signal": "Procurement takes at least six to eight weeks.",
    "competitor_mentioned": null,
    "next_step": null,
    "objections": ["The security lead is hesitant because the last vendor's security review took three months."],
    "confidence": "high"
  },
  {
    "transcript_id": "TX-005",
    "deal_alias": "Deal-F8767A",
    "why_buys": ["Automate service milestones.", "Get analytics on recognition equity across departments."],
    "pain_points": ["Night-shift teams feel invisible; their engagement scores run 20 points lower."],
    "stakeholders": ["Prospect (HR Director)", "Prospect (People Ops Coordinator)"],
    "budget_signal": "$12k approved under the engagement line.",
    "timeline_signal": "Needs to be running before the January all-hands.",
    "competitor_mentioned": "Nectar — currently in a pilot.",
    "next_step": "Present to the exec team on October 2.",
    "objections": ["The experience must beat the ongoing Nectar pilot.", "The exec team is skeptical after a failed rollout two years ago."],
    "confidence": "high"
  },
  {
    "transcript_id": "TX-006",
    "deal_alias": "Deal-EE195F",
    "why_buys": ["Cut administrative time spent on service awards."],
    "pain_points": ["The HR Manager spends five hours a month ordering and shipping plaques."],
    "stakeholders": ["Prospect (HR Manager)"],
    "budget_signal": "Budget isn't the issue; time is. No amount stated.",
    "timeline_signal": "Fiscal year resets in February; a Q1 start is realistic.",
    "competitor_mentioned": null,
    "next_step": "Send a one-page overview; the prospect will forward it to the COO this week.",
    "objections": ["The 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 $0.1497 · 24s · in 9 / out 905 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
Based on the provided CRM export and September 4 Slack thread, these are the three closest to signature, not confirmed current statuses:

1. Deal-547B2B · $11,200. Redlines were clean, the signing page was out, and the buyer’s VP People said they would sign the next day. Left: confirm whether they signed; the thread contains no signature confirmation.

2. Deal-403845 · $9,000. The order form was with the buyer’s finance team. Left: finance approval and signature. Slack says it was “moving fine,” but gives no approval or signing date.

3. Deal-A2B47C · $6,360. It was DS5/COMMIT in CRM and described in Slack as warm, with legal review proceeding at a normal pace. Left: finish legal review and obtain signature.

Arithmetic: $11,200 + $9,000 + $6,360 = $26,560. Deal-2465CE is excluded despite DS5/COMMIT: Slack says its champion left and procurement froze new vendors. All cited Slack updates are from September 4, so none establishes signature status right now.
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 $0.1710 · 26s · in 12 / out 980 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
The supplied data has no deal amounts or deal-status fields. Amounts and whether these deals are active cannot be verified.

| Deal | Prospect line | Classification | Amount |
|---|---|---|---|
| Deal-EC3025 | “We need SCIM user provisioning — our security team will not approve any tool that requires manual account management.” | Real gap — SCIM is not listed as supported. | Not provided |
| Deal-D0D6B5 | “Our payroll runs on ADP Workforce Now and I don't see ADP anywhere in your integration list — that's a dealbreaker for us.” | Real gap — ADP Workforce Now is not listed as supported. | Not provided |
| Deal-CFE7F4 | “I tried to build a custom report combining recognition frequency with turnover and couldn't — is that possible on our current plan?” | Plan gate — the custom report builder is Enterprise-only; the deal’s current plan is not provided. | Not provided |
| Deal-84DBA6 | “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.” | Rollout/enablement issue — Slack integration is supported on all plans. | Not provided |

Real-gap summary: SCIM (Deal-EC3025) and ADP Workforce Now (Deal-D0D6B5). Arithmetic: 1 + 1 = 2 real-gap candidates. Deal-36C33F is excluded: the mobile-app absence was stated by the rep, while the prospect said the web version should be fine for now.
rep-performance 5 tests
stale-pipeline-by-rep0.83
Plain-English question: Which open deals have had no email, call, or meeting in the last 7 days?
Prompt — what the model saw
The snapshot date is 2026-09-05. Using the open deals and the engagements-by-deal table, list every open deal with no logged email, call, or meeting in the last 7 days. Compute recency from the engagements table's last_email/last_call/last_meeting fields, NOT from any date field on the deal (the deal's last_contacted_field is unreliable). For each stale deal give: deal alias, owner name, stage, amount, days since last contact. Group by owner, order by amount descending within each owner. Then state, per owner, how many stale deals they carry and the total stale amount. (Do not write outreach text.)
cost $0.3237 · 100s · in 18 / out 7,731 tok
✓ stale_recall_ge_80✓ grouped_by_owner✓ jake_top_amount✓ kevin_stale_amt✓ jenn_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 · jake_top_amount · kevin_stale_amt · jenn_stale_amt · stale_count

Model's actual answer

show the model's full answer
As of 2026-09-05, a deal is stale if its most recent logged email, call, or meeting was on or before 2026-08-28 (8 or more days ago). Days since contact = 2026-09-05 minus the latest of those three dates. Future-dated meetings do not count as contacts that have occurred.

Alex Franklin

| Deal alias | Stage | Amount | Days since last contact |
|---|---|---:|---:|
| Deal-CC08D1 | DS1 | $24,000 | 16 |
| Deal-E73427 | DS3 | $18,000 | 10 |
| Deal-885F45 | DS2 | $9,300 | 12 |
| Deal-C2FF3C | DS1 | $8,316 | 10 |
| Deal-0D2F7A | DS3 | $5,100 | 12 |
| Deal-6C60D4 | DS3 | $4,800 | 12 |
| Deal-819506 | DS1 | $4,400 | 8 |
| Deal-9D0060 | DS3 | $3,840 | 12 |
| Deal-690476 | DS2 | $3,600 | 18 |
| Deal-C6D97A | DS4 | $3,240 | 8 |
| Deal-EE195F | DS3 | $3,120 | 8 |
| Deal-278DEC | DS3 | $2,700 | 8 |
| Deal-635B8E | DS3 | $2,600 | 18 |
| Deal-6883F3 | DS1 | $2,400 | 16 |
| Deal-4A13AD | DS3 | $2,160 | 26 |
| Deal-F67D31 | DS2 | $1,800 | 8 |
| Deal-5FDCE4 | DS3 | $1,600 | 12 |

17 stale deals; $100,976 = $24,000 + $18,000 + $9,300 + $8,316 + $5,100 + $4,800 + $4,400 + $3,840 + $3,600 + $3,240 + $3,120 + $2,700 + $2,600 + $2,400 + $2,160 + $1,800 + $1,600.

Bryce Harmon

| Deal alias | Stage | Amount | Days since last contact |
|---|---|---:|---:|
| Deal-2D1F1B | DS1 | $240,000 | 81 |
| Deal-66D1FC | DS1 | $99,000 | 16 |
| Deal-950043 | DS1 | $70,000 | 19 |
| Deal-B23205 | DS1 | $45,000 | 16 |
| Deal-7BBDFA | DS3 | $37,440 | 46 |
| Deal-332637 | DS2 | $36,000 | 9 |
| Deal-1BEEBF | DS1 | $31,500 | 19 |
| Deal-A414F6 | DS1 | $25,200 | 19 |
| Deal-C5658B | DS1 | $23,400 | 16 |
| Deal-40522D | DS3 | $21,000 | 19 |
| Deal-C1FA6D | DS1 | $18,000 | 16 |
| Deal-01E193 | DS1 | $12,600 | 8 |
| Deal-F0EBBB | DS3 | $11,400 | 24 |
| Deal-927338 | DS1 | $10,920 | 18 |
| Deal-C9C286 | DS2 | $5,502 | 9 |
| Deal-012CB1 | DS1 | $1 | 23 |
| Deal-3795AD | DS2 | $1 | 8 |

17 stale deals; $686,964 = $240,000 + $99,000 + $70,000 + $45,000 + $37,440 + $36,000 + $31,500 + $25,200 + $23,400 + $21,000 + $18,000 + $12,600 + $11,400 + $10,920 + $5,502 + $1 + $1.

Cole Ingram

| Deal alias | Stage | Amount | Days since last contact |
|---|---|---:|---:|
| Deal-D04904 | DS2 | $58,529.25 | 11 |
| Deal-B25F40 | DS3 | $40,000 | 8 |
| Deal-813836 | DS2 | $32,175 | 11 |
| Deal-1BA595 | DS2 | $31,750 | 11 |
| Deal-CFE1E8 | DS3 | $18,000 | 11 |
| Deal-CD47A6 | DS2 | $12,168 | 11 |
| Deal-627646 | DS3 | $11,193 | 11 |
| Deal-FF809F | DS2 | $7,781.20 | 11 |
| Deal-AF932D | DS2 | $7,225.40 | 11 |
| Deal-A71728 | DS2 | $6,947.50 | 11 |
| Deal-8BC9F5 | DS2 | $5,616 | 10 |
| Deal-175395 | DS3 | $4,779.88 | 11 |
| Deal-13FEBD | DS2 | $4,680 | 12 |
| Deal-481E24 | DS3 | $4,140 | 10 |
| Deal-C7F9BF | DS2 | $3,360 | 11 |
| Deal-2F3A66 | DS3 | $3,334.80 | 11 |
| Deal-342E96 | DS2 | $2,700 | 24 |
| Deal-E568D5 | DS3 | $1,875 | 11 |
| Deal-FD9F4E | DS5 | $1,330 | 10 |

19 stale deals; $257,585.03 = $58,529.25 + $40,000 + $32,175 + $31,750 + $18,000 + $12,168 + $11,193 + $7,781.20 + $7,225.40 + $6,947.50 + $5,616 + $4,779.88 + $4,680 + $4,140 + $3,360 + $3,334.80 + $2,700 + $1,875 + $1,330.

Dana Mercer

| Deal alias | Stage | Amount | Days since last contact |
|---|---|---:|---:|
| Deal-44EA29 | DS2 | $60,000 | 10 |
| Deal-E51FB7 | DS2 | $43,875 | 12 |
| Deal-B42F46 | DS1 | $27,000 | 19 |
| Deal-BA3DDC | DS3 | $23,400 | 15 |
| Deal-9DDE86 | DS2 | $20,000 | 15 |
| Deal-215CCA | DS3 | $18,900 | 17 |
| Deal-5EED42 | DS3 | $16,250 | 11 |
| Deal-57887A | DS2 | $15,000 | 8 |
| Deal-944310 | DS4 | $10,500 | 33 |
| Deal-B7EBD1 | DS5 | $9,000 | 16 |
| Deal-3974EB | DS4 | $9,000 | 8 |
| Deal-F40F04 | DS2 | $8,100 | 15 |
| Deal-7599B8 | DS3 | $7,350 | 18 |
| Deal-87DDD1 | DS1 | $5,000 | 19 |
| Deal-F336B6 | DS3 | $4,200 | 15 |
| Deal-0660B4 | DS4 | $1,920 | 16 |
| Deal-BA571A | DS4 | $1,080 | 18 |

17 stale deals; $280,575 = $60,000 + $43,875 + $27,000 + $23,400 + $20,000 + $18,900 + $16,250 + $15,000 + $10,500 + $9,000 + $9,000 + $8,100 + $7,350 + $5,000 + $4,200 + $1,920 + $1,080.

Farid Osman

| Deal alias | Stage | Amount | Days since last contact |
|---|---|---:|---:|
| Deal-8BA24E | DS1 | $2,880 | 8 |
| Deal-8FDCD2 | DS1 | $1 | 15 |

2 stale deals; $2,881 = $2,880 + $1.

Deal-3EED2C (Alex Franklin) and Deal-57FF13 (Elena Sinclair) have no row in the engagements-by-deal table. Their contact recency—and therefore whether they are stale—cannot be determined from the supplied data.
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 $0.2553 · 44s · in 18 / out 2,477 tok
✓ alex_ds2_30d✓ justin_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 · justin_volume_high · efficient_named · mix_present · no_causal_claim

Model's actual answer

show the model's full answer
Using the supplied `*_30d` engagement counts and DS2 entry dates from 2026-08-06 through the 2026-09-05 snapshot, the ranking is:

| Rank | Rep | Emails | Calls | Meetings | Activity mix (email / call / meeting) | Total activities | DS2 entries | Activities per DS2 entry |
|---:|---|---:|---:|---:|---|---:|---:|---:|
| 1 | Alex Franklin | 307 | 36 | 41 | 79.95% / 9.38% / 10.68% | 384 | 18 | 384 ÷ 18 = 21.33 |
| 2 | Bryce Harmon | 162 | 0 | 43 | 79.02% / 0% / 20.98% | 205 | 4 | 205 ÷ 4 = 51.25 |
| 3 | Cole Ingram | 96 | 14 | 1 | 86.49% / 12.61% / 0.90% | 111 | 2 | 111 ÷ 2 = 55.50 |
| 4 | Farid Osman | 38 | 0 | 34 | 52.78% / 0% / 47.22% | 72 | 1 | 72 ÷ 1 = 72.00 |
| 5 | Dana Mercer | 84 | 18 | 11 | 74.34% / 15.93% / 9.73% | 113 | 1 | 113 ÷ 1 = 113.00 |
| — | Elena Sinclair | Missing | Missing | Missing | Not calculable | Missing | 0 | Undefined |

Each activity share is that activity count ÷ the rep’s total activities × 100; for example, Alex’s email share is 307 ÷ (307 + 36 + 41) × 100 = 79.95%.

Alex Franklin is both the most efficient and the highest-volume rep **on the available engagement rows**; they do not differ. These are provisional rankings: the engagement row for Alex’s Deal-3EED2C is missing, as is the row for Elena’s Deal-57FF13. Missing rows were not treated as zero.
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 $0.3487 · 97s · in 30 / out 5,415 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
Alex Franklin — QTD scorecard as of 2026-09-05 (Q3: July 1–September 5)

- Bookings vs quota: $150,000 / $200,000 = 75% attainment; $50,000 remaining. Bookings comprise 8 closed-won deals. Deal-B3E6F1 ($24,000; closed June 20) is excluded because it closed before Q3.
- Booking split: New $113,500 (5 deals) + expansion $36,500 (3 deals) = $150,000.
- Active pipeline: DS1 $284,621 (20 deals); DS2 $353,760 (28); DS3 $552,705 (67); DS4 $23,574 (5); DS5 $45,730 (5). Total: $284,621 + $353,760 + $552,705 + $23,574 + $45,730 = $1,260,390 across 125 open deals.
- Rolling 90-day DS2-to-won rate: For deals entering DS2 June 8–September 5, 8 won / 111 entered = 7.2%. The cohort also has 27 lost and 76 still open. This is an all-deal rate: deal type is missing on open and lost rows, so a new-deal-only rate cannot be calculated.
- QTD outcomes: 8 wins; 27 losses. Top recorded loss reason: “Lost- Timing (1 year or more)” — 13 of 27 losses.
- Last-30-day activity: 807 emails, 112 calls, 128 meetings, 50 notes, summed from the supplied per-deal 30-day fields. Individual activity dates are not provided, so the precise 30-day boundaries cannot be independently verified.

Coaching observations:
1. Work the 76 still-open deals in the DS2-entry cohort: only 8 of 111 have won so far.
2. Qualify timing earlier: “Lost- Timing (1 year or more)” accounts for 13 / 27 QTD losses.
3. Prioritize advancement beyond DS3: DS1–DS3 hold $284,621 + $353,760 + $552,705 = $1,191,086 of the $1,260,390 open pipeline; DS4–DS5 hold $69,304.
multithreading-gap0.75
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 $0.1754 · 38s · in 12 / out 2,270 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
The files contain no deal amounts, stages, or open/closed status. I cannot verify which deals are open or choose a persona *given the stage*. The 11 deals below meet the threading criteria **if they are open**. For every row, amount and stage are not provided, and the stage-based persona priority is undetermined.

As of 2026-09-24, the 60-day cutoff is 2026-09-24 − 60 days = 2026-07-26. Active counts exclude former contacts and contacts last engaged before that date. “Single” means fewer than 2 active contacts; “under” means fewer than 3, or all active contacts share one persona.

| Deal / company | Active count; flag | Personas present | Personas missing | On-file unengaged contact fitting a missing persona |
|---|---:|---|---|---|
| Deal-EC3025 / C-FDD0C7 | 1; single | champion | economic buyer, HR admin, IT security, finance | CT-6827DB — economic buyer |
| Deal-92D97D / C-E23238 | 1; single | HR admin | economic buyer, champion, IT security, finance | None on file |
| Deal-50D386 / C-EB10E4 | 2; under | champion, HR admin | economic buyer, IT security, finance | CT-A1C4B3 — economic buyer |
| Deal-D0D6B5 / C-32918E | 3; under (one persona) | champion | economic buyer, HR admin, IT security, finance | CT-1FA4DB — economic buyer |
| Deal-5BFE3B / C-535D36 | 2; under | champion | economic buyer, HR admin, IT security, finance | None on file |
| Deal-36C33F / C-077A0E | 1; single | IT security | economic buyer, champion, HR admin, finance | CT-1DB73E — economic buyer |
| Deal-885F45 / C-5E8EFB | 2; under | economic buyer, champion | HR admin, IT security, finance | CT-B3F25D — IT security |
| Deal-FCBE5B / C-737030 | 1; single | champion | economic buyer, HR admin, IT security, finance | None on file |
| Deal-5408B0 / C-2AE3AA | 2; under | champion, HR admin | economic buyer, IT security, finance | CT-07FA76 — economic buyer |
| Deal-C6D97A / C-5A8FC2 | 3; under (one persona) | champion | economic buyer, HR admin, IT security, finance | None on file |
| Deal-F9A08A / C-0D15DF | 1; single | champion | economic buyer, HR admin, IT security, finance | CT-697541 — economic buyer |

Arithmetic: 5 deals have 1 active contact; 4 have 2; 2 have 3 contacts all in one persona. 5 + 4 + 2 = 11 flagged deals.
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 $0.1763 · 30s · in 12 / out 1,263 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
From the 10 provided calls:

- First five minutes: Alex leads with the same retailer turnover case in 8/10 calls. Deal-403845 opens with a security/pricing agenda; Deal-1E2498 opens with pricing. “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.” (Deal-D348E1)
- Locked budget (4/10: Deal-D348E1, Deal-547B2B, Deal-60C2C2, Deal-84DBA6): Alex points to turnover savings and avoided backfills as a funding rationale. “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.” (Deal-D348E1)
- Timing/capacity (3/10: Deal-5408B0, Deal-C61CF7, Deal-D9A12F): Alex proposes a one-department, 90-day pilot ahead of the next planning cycle. “Makes sense. What if we scope a 90-day pilot with one department so you have internal data before next quarter's planning?” (Deal-5408B0)
- Existing spreadsheet and gift cards (3/10: Deal-403845, Deal-EDC141, Deal-1E2498): Alex contrasts the manual approach with automated milestones and recognition analytics. “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.” (Deal-403845)
- Concrete next step agreed: 7/10 = 70%. The prospects in Deal-D348E1, Deal-5408B0, Deal-547B2B, Deal-C61CF7, Deal-60C2C2, Deal-D9A12F, and Deal-1E2498 agree to a Thursday 2pm working session and an invite. “Yes, Thursday at 2pm works — send the invite and I'll bring our HRIS manager.” (Deal-D348E1)
- Competitors raised by prospects: Awardco (Deal-547B2B) and Kudos (Deal-EDC141). Workhuman is mentioned by Alex, not a prospect (Deal-C61CF7).

Coaching notes:
1. When budget approval is blocked, ask for a specific committee follow-up rather than leaving it open-ended, as in Deal-403845 and Deal-84DBA6.
2. When a prospect says there is no urgency, propose a dated next conversation rather than ending at “Fair enough,” as in Deal-EDC141.
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 $0.1449 · 544s · in 15 / out 3,297 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

| Category | Q3 deals | Total amount | Forecast contribution |
|---|---:|---:|---:|
| COMMIT | 7 | 44,729 | 44,729 × 100% = 44,729 |
| BEST_CASE | 24 | 203,565 | 203,565 × 35% = 71,247.75 |
| PIPELINE | 23 | Not included in forecast | 0 |

**Weighted forecast: 44,729 + 71,247.75 = 115,976.75.** Currency is not specified in the extract.

**Excluded for close dates outside Q3:** 32 deals, totaling 227,575 = 13,770 COMMIT + 28,240 BEST_CASE + 185,565 PIPELINE. All have October close dates.

- COMMIT: Deal-D348E1.
- BEST_CASE: Deal-C61CF7, Deal-48B656, Deal-901332, Deal-47AE31, Deal-15D24F, Deal-ED725A, Deal-8AD4A5, Deal-5FDCE4, Deal-F5A622.
- PIPELINE: Deal-E51FB7, Deal-B936FE, Deal-D9A12F, Deal-4062CF, Deal-293AF3, Deal-034D49, Deal-E0ADD8, Deal-9F2E43, Deal-FCBE5B, Deal-712010, Deal-6691E0, Deal-600CD9, Deal-A92065, Deal-1D532E, Deal-E531A6, Deal-D1E6C2, Deal-D9E112, Deal-5AD94B, Deal-766C74, Deal-D7E999, Deal-ED13B0, Deal-7FA0C3.

**Top 5 Q3 BEST_CASE deals by amount:** Deal-2D7423 (38,935), Deal-25F752 (24,000), Deal-E53952 (19,656), Deal-5EED42 (16,250), Deal-FA32A0 (11,116).

## Data quality

Owner is blank on nearly every row, and `why_buys_chars` is zero on most rows, limiting ownership and buyer-rationale checks. Deal-333EBB, Deal-57FF13, Deal-31AD2C, and Deal-7A2454 have close dates already past as of the 2026-09-05 extract but remain open. Deal-A5E80A is marked COMMIT at DS1, a stage/category combination that warrants review. The extract has no currency field, so monetary totals cannot be assigned a currency or checked for mixed currencies.
aha-moment-2x20.83
Plain-English question: Do companies that hit 5+ givers and one redemption in month one actually retain better at 24 months?
Prompt — what the model saw
Test the activation hypothesis on the company cohort below: companies with 5+ unique givers (m1_users >= 5) AND 1+ successful redemption (m1_redemptions >= 1) in their first calendar month retain better at 24 months than those with one signal or neither. Every company in this extract is already 25+ months old, so current_status = 'active' means retained at 24 months. Report the full 2x2 (cohort size and 24-month retention rate for: both signals, givers-only, redemption-only, neither), state how many companies were excluded from the denominator and why (if none, say so), name the single signal with the largest retention lift, and state what this does and does not prove.
cost $0.1050 · 37s · in 6 / out 2,597 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
Using `current_status = active` as the specified 24-month retention proxy:

| First-month signals | Retained / companies | 24-month retention |
|---|---:|---:|
| Both: 5+ givers and 1+ redemption | 31 / 47 | 31 ÷ 47 = 66.0% |
| Givers only | 23 / 49 | 23 ÷ 49 = 46.9% |
| Redemption only | 9 / 29 | 9 ÷ 29 = 31.0% |
| Neither | 38 / 95 | 38 ÷ 95 = 40.0% |

Excluded: 0 companies. All 220 companies are old enough and have the fields needed for this classification; `non_renewing` is counted as not active.

The stronger single signal is 5+ unique givers: givers-only exceeds neither by 46.9% − 40.0% = 6.9 percentage points. Redemption-only is 31.0% − 40.0% = 9.0 points lower than neither.

The data support an association for both signals together (66.0%, higher than every other cell), but not the claim that *either* single signal improves retention. They do not prove that the signals cause retention; this is an observational comparison, and the provided status is a proxy rather than a recorded status at the exact 24-month mark.
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 $0.2187 · 47s · in 15 / out 3,186 tok
✓ billing_total✓ crm_total✓ variance✓ buckets_sum✓ violations_listed

✓ Correct Answer (ground truth)

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

Model's actual answer

show the model's full answer
As of 2026-09-05, using active subscriptions only and billing ARR = MRR × 12:

CRM company ARR: $603,581.76
Billing ARR: $604,739.28
Variance (CRM − billing): −$1,157.52

Reconciliation:
- Status mismatch: +$13,158.48 = $4,905.24 + $8,253.24. Both company records retain ARR for cancelled subscriptions; those subscriptions contribute $0 to active billing ARR.
- Rounding: +$36.00 = $16.00 + $20.00.
- Missing records: −$11,952.00 = $16,497.24 CRM-only − $28,449.24 billing-only.
- Other: −$2,400.00 = $24,396.00 − $26,796.00.
- Check: $13,158.48 + $36.00 − $11,952.00 − $2,400.00 = −$1,157.52.

Mismatched accounts (difference is CRM − active billing ARR):

| Company alias | CRM ARR | Billing ARR | Difference | Suggested owner |
|---|---:|---:|---:|---|
| C-0C8323BF | $4,905.24 | $0.00 (cancelled) | +$4,905.24 | CRM operations |
| C-0DC4FB8C | $8,253.24 | $0.00 (cancelled) | +$8,253.24 | CRM operations |
| C-0D66DF9E | $23,200.00 | $23,184.00 | +$16.00 | Revenue operations |
| C-14D70CE0 | $18,200.00 | $18,180.00 | +$20.00 | Revenue operations |
| C-0D5BBE3A | $16,497.24 | No subscription record | +$16,497.24 | Billing operations |
| C-21629AA4 | No company record | $28,449.24 | −$28,449.24 | CRM operations |
| C-0F7269D7 | $24,396.00 | $26,796.00 | −$2,400.00 | Revenue operations |

The provided data has no assigned-owner field; the owners above are suggested functions, not identified people. The two small differences are classified as rounding for reconciliation, but their cause is not established by the files.

Agreement-end-date violations (non-12-month term with blank `cf_agreement_end_date`): SUB-0002 / C-1794A52C (24 months); SUB-0019 / C-22170CA1 (36 months).
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 $0.1734 · 26s · in 9 / out 1,778 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
Using the unweighted mean of the 30 company rows in each month:

| KVM | 2026-08 | 2026-07 | Absolute change | Relative change | Direction |
|---|---:|---:|---:|---:|---|
| Giving rate | 0.602713 | 0.602297 | +0.000417 | +0.07% | Up |
| Redemptions per user | 1.730163 | 1.729983 | +0.000180 | +0.01% | Up |
| 1:1 meetings engagement | 0.447177 | 0.446887 | +0.000290 | +0.06% | Up |
| Pulse check engagement | 0.508610 | 0.600587 | −0.091977 | −15.31% | Down |

Arithmetic: absolute change = August mean − July mean; relative change = absolute change ÷ July mean × 100. Pulse check engagement had the largest relative move. The `enterprise` size_band drove it: its mean fell from 0.54998 to 0.27428 (−0.27570, or −50.13%). With 10 of 30 rows, that contributes −0.27570 × 10/30 = −0.09190 of the overall −0.091977 change.
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 $0.3566 · 108s · in 36 / out 2,196 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
Redemptions YTD (January–August 2026). Last completed month: August 2026.

- Redemption count: 378
- Spend: $27,846.00
- Unique redeemers: 235 distinct user keys
- Redemptions per redeemer: 378 ÷ 235 = 1.61

Provider mix (% of spend):
- custom: $10,873 ÷ $27,846 = 39.05%
- Tremendous: $8,505 ÷ $27,846 = 30.54%
- Snappy: $5,238 ÷ $27,846 = 18.81%
- TangoCard: $3,230 ÷ $27,846 = 11.60%
- Total: $27,846 ÷ $27,846 = 100.00%

Top 5 countries by redemptions: US 244; CA 24; AU 21; GB 17; NL 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 $0.1754 · 41s · in 12 / out 2,244 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
The documented rules require all three conditions: health score <60, churn-save eligible amount >$0, and renewal within 120 days of the 2026-09-05 snapshot (through 2027-01-03). Eight accounts qualify. “Amount at stake” below is the churn-save eligible amount, not full ARR.

| Account | Amount at stake | Best-fit play and supporting signal |
|---|---:|---|
| C-0F6C0F34 | $49,707 | Executive touch — champion inactive; renewal 2026-10-03. |
| C-0B827671 | $25,365 | Usage revival — three-month usage declining; 113/202 seats used = 55.9%. |
| C-0B360C78 | $35,748 | Commercial concession candidate — usage growing and champion active despite health score 57; renewal 2026-10-28. No pricing objection is provided, so a concession is not yet justified. |
| C-0B0F1BAB | $5,494 | Executive touch — champion inactive; renewal 2026-09-23. |
| C-0CA21961 | $16,829 | Usage revival — 84/325 seats used = 25.8%; usage flat. |
| C-0E9C27D1 | $41,235 | Commercial concession candidate — 134/157 seats used = 85.4% and champion active despite health score 39; renewal 2026-09-24. No pricing objection is provided, so a concession is not yet justified. |
| C-0CEF69FD | $32,621 | Executive touch — champion inactive. |
| C-0D3278C7 | $17,602 | Usage revival — usage declining; 126/380 seats used = 33.2%. |

Total at stake: $49,707 + $25,365 + $35,748 + $5,494 + $16,829 + $41,235 + $32,621 + $17,602 = **$224,601**.

At risk (health <60) but not eligible:

| Account | Why excluded |
|---|---|
| C-0BC71BDD | Eligible amount is $0. |
| C-0BA71F12 | Renewal 2027-04-11 is outside the 120-day window. |
| C-0F6694C3 | Eligible amount is $0; renewal 2027-03-21 is outside the window. |
| C-0BE96399 | Eligible amount is $0. |
| C-0F876796 | Renewal 2027-02-06 is outside the window. |
| C-0FCCD2DF | Eligible amount is $0; renewal 2027-04-23 is outside the window. |
| C-10A56B0F | Eligible amount is $0. |
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 $0.1732 · 26s · in 15 / out 974 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
C-0DDFC9A7 expansion kit

- Seat coverage: 150 licensed seats ÷ 400 headcount = 37.5%.
- Usage health: Monthly users rose from 88 in March to 126 in August, up 38 (38 ÷ 88 = 43.2%).
- Usage health: August’s 126 users equal 84% of licensed seats (126 ÷ 150); 24 licensed seats remain unused.
- Headroom: 400 − 150 = 250 additional seats. Current rate: $9,000 ARR ÷ 150 = $60 per seat annually. At that rate, 250 seats represent $15,000 in additional ARR, for $24,000 total ARR if all 400 employees were licensed. This is capacity, not a forecast.
- Reply and buyer: Maria S. replied and explicitly said she does not make purchasing decisions. She identified Dana R., VP People, as the budget and seat-expansion buyer and offered an introduction.

Reply email

Hi Maria,

Thanks for the update—and for offering to connect us with Dana. It’s good to see monthly users rise from 88 in March to 126 in August.

Since Dana has been asking about usage, I can put together a short summary of adoption and what broader seat coverage could look like. If you’re comfortable making the introduction, I’d be glad to share it with her and answer any questions. No need to schedule anything until it’s useful for her.

Thanks,
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 $0.1602 · 22s · in 12 / out 777 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 call prep

Complete (shown in onboarding_account.csv):
- Slack integration connected August 12; allowance set August 13; 2 admins added; first recognition given August 15 at 14:22.

Not shown as complete:
- HRIS integration and first redemption have blank fields. Their status is unconfirmed, not necessarily incomplete.

Early engagement (onboarding_usage.csv, through September 4):
- Daily active givers rose from 3 on August 11 to 15 on September 4: 15 − 3 = 12 more, or 15 ÷ 3 = 5× the starting count.
- The first 7 days averaged 30 ÷ 7 = 4.3 daily active givers; the last 7 averaged 91 ÷ 7 = 13. These are daily counts, not unique givers across each week.

Cover on the call:
1. Confirm HRIS integration status and any blocker.
2. Confirm whether a first redemption has happened; if not, identify what is preventing it.
3. Review the rise in daily active givers and agree on the next adoption step.
renewal-risk-conflicting-dates0.75
Plain-English question: Two systems disagree on renewal dates — which do you trust per account, and who is actually renewing inside 90 days?
Prompt — what the model saw
Produce a 90-day renewal risk brief. Two systems hold renewal dates and disagree on some accounts; decide which to trust per account and say why (multi-year contracts are known to be wrong in ChurnZero). For every renewal: company, CSM, ARR, date used, seat utilization, 3-month usage trend, risk rating with one sentence of evidence. Flag every disagreement. Close with total ARR renewing and ARR at risk.
cost $0.2283 · 67s · in 15 / out 4,954 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 — September 24–December 22, 2026

Date rule: Use Chargebee for multi-year contracts because ChurnZero renewal dates are known to be wrong for those contracts. For annual contracts, the two dates agree. Seat utilization is seats_used ÷ seats; usage trend is monthly active users in June → July → August 2026. Risk ratings below use these two signals only: High for utilization below 30% or a June-to-August usage decline of at least 10%; Moderate for utilization below 60% without a High signal; Low otherwise. These are exposure ratings, not predictions of non-renewal.

| Company | CSM | ARR | Date used | Seat utilization | 3-month usage | Risk and evidence |
|---|---|---:|---|---:|---|---|
| C-0BBE3E60 | Dana Mercer | $30,993 | 2026-09-26 | 74 ÷ 114 = 64.9% | 39 → 35 → 33 | High — active users fell 6 ÷ 39 = 15.4% from June to August. |
| C-0F5D2323 | Cole Ingram | $90,647 | 2026-09-29 | 111 ÷ 390 = 28.5% | 20 → 21 → 18 | High — utilization is 28.5% and active users fell 2 ÷ 20 = 10.0%. |
| C-0EC6999D | Elena Sinclair | $79,419 | 2026-10-03 | 31 ÷ 112 = 27.7% | 17 → 16 → 15 | High — utilization is 27.7% and active users fell 2 ÷ 17 = 11.8%. |
| C-0B20DB64 | Dana Mercer | $21,770 | 2026-10-07 | 214 ÷ 378 = 56.6% | 294 → 298 → 294 | Moderate — utilization is 56.6%, though June and August active-user counts match. |
| C-0BBC4E7A | Cole Ingram | $56,374 | 2026-10-10 | 228 ÷ 337 = 67.7% | 142 → 141 → 139 | Low — utilization is 67.7% and active users fell only 3 ÷ 142 = 2.1%. |
| C-0FD551AB | Elena Sinclair | $48,815 | 2026-10-14 | 210 ÷ 376 = 55.9% | 123 → 122 → 126 | Moderate — utilization is 55.9%, despite active users rising 3 ÷ 123 = 2.4%. |
| C-0F9F8F13 | Dana Mercer | $46,230 | 2026-10-18 | 199 ÷ 352 = 56.5% | 185 → 185 → 182 | Moderate — utilization is 56.5% and active users fell 3 ÷ 185 = 1.6%. |
| C-0BC34584 | Cole Ingram | $16,740 | 2026-10-22 | 327 ÷ 494 = 66.2% | 104 → 104 → 106 | Low — utilization is 66.2% and active users rose 2 ÷ 104 = 1.9%. |
| C-0B7A7546 | Elena Sinclair | $35,062 | 2026-10-25 | 182 ÷ 205 = 88.8% | 64 → 65 → 63 | Low — utilization is 88.8% and active users fell 1 ÷ 64 = 1.6%. |
| C-0B369871 | Dana Mercer | $85,128 | 2026-10-29 | 317 ÷ 422 = 75.1% | 326 → 330 → 333 | Low — utilization is 75.1% and active users rose 7 ÷ 326 = 2.1%. |
| C-0B144C78 | Cole Ingram | $30,899 | 2026-11-02 | 169 ÷ 224 = 75.4% | 101 → 101 → 106 | Low — utilization is 75.4% and active users rose 5 ÷ 101 = 5.0%. |
| C-0FC4DBB8 | Elena Sinclair | $94,732 | 2026-11-05 | 356 ÷ 464 = 76.7% | 189 → 191 → 193 | Low — utilization is 76.7% and active users rose 4 ÷ 189 = 2.1%. |
| C-0D5BBE3A | Dana Mercer | $39,740 | 2026-11-09 | 85 ÷ 102 = 83.3% | 88 → 90 → 91 | Low — utilization is 83.3% and active users rose 3 ÷ 88 = 3.4%. |
| C-0FB9D5AF | Cole Ingram | $63,158 | 2026-11-13 | 144 ÷ 199 = 72.4% | 173 → 173 → 176 | Low — utilization is 72.4% and active users rose 3 ÷ 173 = 1.7%. |
| C-0B344485 | Elena Sinclair | $64,384 | 2026-11-16 | 224 ÷ 287 = 78.0% | 238 → 240 → 244 | Low — utilization is 78.0% and active users rose 6 ÷ 238 = 2.5%. |
| C-0CB2C1B4 | Dana Mercer | $40,628 | 2026-11-20 | 386 ÷ 473 = 81.6% | 47 → 48 → 49 | Low — utilization is 81.6% and active users rose 2 ÷ 47 = 4.3%. |
| C-22170CA1 | Cole Ingram | $45,646 | 2026-11-24 | 251 ÷ 294 = 85.4% | 143 → 148 → 146 | Low — utilization is 85.4% and active users rose 3 ÷ 143 = 2.1%. |

Date disagreements (ChurnZero → Chargebee; Chargebee used in each case because the contract is multi-year):
- C-0B7D2C30: 2026-09-10 → 2026-09-15; outside the 90-day window.
- C-0BCDB8C2: 2027-09-18 → 2026-09-18; outside the 90-day window.
- C-0D2AB865: 2026-09-10 → 2026-09-22; outside the 90-day window.
- C-0BBE3E60: 2027-09-26 → 2026-09-26; included.
- C-0F5D2323: 2026-09-10 → 2026-09-29; included.

Total ARR renewing: $890,365 across the 17 in-window accounts (sum of the 17 ARR rows above). ARR at risk, defined here as High plus Moderate: ($30,993 + $90,647 + $79,419) + ($21,770 + $48,815 + $46,230) = $201,059 + $116,815 = $317,874.
ticket-theme-synthesis0.80
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 $0.1650 · 32s · in 12 / out 1,697 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
ARR affected is exposure, not confirmed revenue loss. Each account’s ARR is counted once per theme. Shares use all 80 tickets as the denominator; themes are ranked by ARR exposure.

| Theme | Tickets / share | Distinct accounts | ARR affected (arithmetic) | Example ticket IDs | Recommendation |
|---|---:|---:|---:|---|---|
| HRIS new-hire provisioning failures — broad pattern | 12 / 80 = 15.0% | 3 | $36,000 + $30,000 + $48,000 = **$114,000** | IC-460059, IC-460062 | Investigate skipped new hires and provisioning logs across the three accounts. |
| Redemption and gift-card failures — broad pattern | 18 / 80 = 22.5% | 7 | $8,900 + $9,600 + $10,700 + $8,700 + $9,600 + $11,000 + $10,300 = **$68,800** | IC-460025, IC-460024 | Trace checkout failures, missing delivery, and cases where points were deducted. |
| Invoice seat-count and renewal-price errors — **single-account concentration** | 16 / 80 = 20.0% | 1: C-0E9C27D1 | **$52,000** | IC-460069, IC-460078 | Reconcile C-0E9C27D1’s seat count and renewal tier against its invoices; do not treat repeat tickets as a cross-account pattern. |
| Recognition points not posting — broad pattern | 20 / 80 = 25.0% | 9 | $4,500 + $2,700 + $3,500 + $3,400 + $4,500 + $4,200 + $2,900 + $2,500 + $2,900 = **$31,100** | IC-460001, IC-460004 | Audit delivered recognitions against point postings and balances. |
| Slack recognition sync and command failures — broad pattern | 14 / 80 = 17.5% | 4 | $4,400 + $5,400 + $3,900 + $5,200 = **$18,900** | IC-460041, IC-460051 | Test sync, re-authentication, toggle persistence, and slash commands across affected accounts. |
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 $0.1635 · 26s · in 12 / out 1,065 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
For prospect C-82AF3719 (Technology, Mid-Market, employee_recognition, NA-West), three case-study customers tie on exact field matches:

1. C-64171065 — 3/4: Technology industry, Mid-Market size band, employee_recognition use case. Region differs (NA-East).
2. C-11C31562 — 3/4: Mid-Market size band, employee_recognition use case, NA-West region. Industry differs (Manufacturing).
3. C-A13C193D — 3/4: Technology industry, Mid-Market size band, NA-West region. Use case differs (retention).

Arithmetic: each matches 3 of the 4 requested fields. This order favors a matching use case over a matching region when scores tie; no field weights were provided. Source: customers.csv and prospect.csv.
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 $0.1918 · 43s · in 12 / out 2,441 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 six months: March–August 2026. SQM and SQO counts use the provided first-touch contact rows; pipeline is the sum of their `pipeline_amount` values.

| Paid channel | Spend | SQMs | SQOs | Cost/SQM | Cost/SQO | SQM→SQO | Pipeline | Pipeline/$ |
|---|---:|---:|---:|---:|---:|---:|---:|---:|
| paid_search | $36,000 | 40 | 18 | $900 | $2,000 | 45.0% | $720,000 | $20.00 |
| linkedin_ads | $24,000 | 25 | 8 | $960 | $3,000 | 32.0% | $96,000 | $4.00 |
| paid_social | $18,000 | 0 | 0 | undefined | undefined | undefined | $0 | undefined* |
| webinars | $9,000 | 12 | 5 | $750 | $1,800 | 41.7% | $60,000 | $6.67 |
| Total | $87,000 | 77 | 31 | $1,129.87 | $2,806.45 | 40.3% | $876,000 | $10.07 |

Arithmetic: spend = six monthly entries per paid channel; cost/SQM = spend ÷ SQMs; cost/SQO = spend ÷ SQOs; SQM→SQO = SQOs ÷ SQMs; pipeline/$ = pipeline ÷ spend. For example, paid_search: $6,000 × 6 = $36,000; $36,000 ÷ 40 = $900; $36,000 ÷ 18 = $2,000; 18 ÷ 40 = 45.0%; 18 × $40,000 = $720,000; $720,000 ÷ $36,000 = $20.00. Total: $87,000 ÷ 77 = $1,129.87; $87,000 ÷ 31 = $2,806.45; 31 ÷ 77 = 40.3%; $876,000 ÷ $87,000 = $10.07.

| Organic channel | Volume (SQMs) | SQOs | SQO rate | Pipeline |
|---|---:|---:|---:|---:|
| organic_search | 30 | 10 | 10 ÷ 30 = 33.3% | 10 × $9,000 = $90,000 |
| referral | 15 | 6 | 6 ÷ 15 = 40.0% | 6 × $8,000 = $48,000 |
| Total | 45 | 16 | 16 ÷ 45 = 35.6% | $138,000 |

Date flags: CT-000044 (`linkedin_ads`) has SQO 2026-07-18 before SQM 2026-07-23; CT-000041 (`linkedin_ads`) has SQO 2026-06-09 before SQM 2026-06-14. Both are included in the table as supplied; excluding them would change `linkedin_ads` to 6 SQOs, $72,000 pipeline, and 6 ÷ 25 = 24.0% conversion.

Recommendation: Pause or sharply reduce `paid_social` pending an attribution check, then test a limited reallocation toward `paid_search` rather than committing the full $18,000 elsewhere. Confidence is moderate in the case for reviewing `paid_social` (0 SQMs on $18,000 spend), but low in the precise destination or expected return: `paid_search` has only 18 SQOs, `webinars` 5, and the two inverted `linkedin_ads` dates need correction before comparing channels definitively.

*For `paid_social`, pipeline/$ is shown as undefined rather than a performance multiple because spend produced zero recorded SQMs.
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 $0.2162 · 36s · in 15 / out 1,868 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
# Rivally battlecard

**One-line positioning:** Rivally is a points-based recognition platform with an engaging feed; its EU offering includes multi-language support and generally available EU data residency. Mid-market as its primary segment is unverified. [S02, S12, S15]

**Pricing:** Recognition Starter lists at **$7/user/month, annual billing required** on Rivally’s pricing page dated 2026-08-12. This supersedes the **$5/user/month** page dated 2026-04-01 and conflicts with a **$6.50/user/month** annual quote reported for a 500-seat prospect on 2026-06-02; the latter is a deal-specific quote, not list pricing. A prospect reported a $7 list quote with a 15% discount for a three-year term on 2026-08-14. [S17, S08, S13, S18]

**Where they win:** Reviewers praise the recognition feed, quick setup, working Slack integration, multi-language support for distributed EU teams, and support response time. EU data residency became generally available on 2026-07-01. These are reported strengths, not verified reasons for any recorded loss. [S02, S04, S12, S22, S15]

**Where we win:** An 800-seat prospect picked Bonusly over Rivally citing analytics depth. Reviews also describe Rivally’s reporting as basic, its EMEA rewards catalog as thinner than its US catalog, and enterprise administration as limited by missing SCIM provisioning and bulk recognition editing. No broader Bonusly feature comparison is established by the supplied data. [S25, S07, S14, S10, S24]

**Objections and responses:**
- “Rivally has Slack integration.” **Acknowledge it**; a reviewer said it worked out of the box. Do not repeat the old card’s “lacks Slack integration” claim. [S04]
- “Rivally is cheaper.” **Compare the current $7/user/month annual list price and the actual quoted term**, not the superseded $5 price; a prospect reported a three-year discount. [S17, S08, S18]
- “We need EU coverage.” **Acknowledge** generally available EU data residency and praised multi-language support; ask the buyer to assess its EMEA rewards catalog against their needs. [S15, S12, S14]
- “We need enterprise controls and reporting.” **Test SCIM, bulk editing, and analytics requirements**: reviewers report gaps in the first two, and one prospect selected Bonusly citing analytics depth. [S10, S24, S25]

**Recent changes:** Rivally Pulse launched as a survey add-on on 2026-03-05 and exited beta on 2026-09-01; it is priced separately, not bundled. Rivally hired an EMEA leader on 2026-05-09, opened a Dublin office and made EU data residency generally available on 2026-07-01, raised Recognition Starter list pricing by 2026-08-12, and put Microsoft Teams app v2 in public preview on 2026-08-20. [S06, S23, S11, S15, S08, S17, S19]

**Old-card claims not carried forward:** “Acquired by WorkHuman in 2025” is **unverified** by the supplied snippets. “Points-based recognition for mid-market” is supported only as to points-based recognition; the primary-segment claim remains **unverified**. “Lacks a Slack integration” is contradicted by the reviewer account. [S02, S04]

**Our 12-month win/loss record (2025-09 through 2026-08):** 13 wins + 7 losses = 20 recorded Rivally deals; win rate = 13 ÷ 20 × 100 = **65%**. The deal file supplies outcomes, not reasons for those outcomes.

Wins: Deal-A9FD43, Deal-7AA785, Deal-44C524, Deal-0D0CD6, Deal-D5B790, Deal-5C636E, Deal-67BE14, Deal-1B6969, Deal-F03E7B, Deal-072E31, Deal-F65C8F, Deal-E46EAB, Deal-1D2392.

Losses: Deal-7767F5, Deal-5645A5, Deal-C6FFAA, Deal-D263E0, Deal-935746, Deal-9066A6, Deal-72A02F.
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 $0.2390 · 76s · in 18 / out 2,883 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
Rates below use summed events ÷ summed sends across all three steps; “weakest” means lowest step reply rate.

| Sequence | Sent | Open rate | Reply rate | Meeting rate | Weakest step |
|---|---:|---:|---:|---:|---|
| New Logo Nurture | 500+458+428=1,386 | 490/1,386=35.35% | 90/1,386=6.49% | 27/1,386=1.95% | 3: 18/428=4.21% reply |
| Expansion Nurture | 300+300+275=875 | 565/875=64.57% reported; unreliable | 59/875=6.74% | 12/875=1.37% | 3: 12/275=4.36% reply |
| Cold Outbound - HR Leaders | 600+595+590=1,785 | 545/1,785=30.53% | 8/1,785=0.45% | 0/1,785=0% | 3: 1/590=0.17% reply |
| Cold Outbound - People Ops | 400+386+377=1,163 | 340/1,163=29.23% | 29/1,163=2.49% | 6/1,163=0.52% | 3: 6/377=1.59% reply |

Tracking error: Expansion Nurture step 2 records 340 opens against 300 sends (340/300=113.33%). Its aggregate open rate should not be used until that count is corrected.

Audience overlap: 21 contact keys appear in both Cold Outbound - HR Leaders and Cold Outbound - People Ops; 2 appear in both New Logo Nurture and Expansion Nurture. These are overlapping assignments, not evidence that both sequences sent to each contact.

Under 2% reply: Cold Outbound - HR Leaders is weak at every step (5/600=0.83%, 2/595=0.34%, 1/590=0.17%); opens are not turning into replies or meetings. Cold Outbound - People Ops falls below 2% only at step 3 (6/377=1.59%). The files do not show whether targeting, copy, or timing caused either failure.

One change each: revise New Logo Nurture step 3’s ask; correct Expansion Nurture step 2 open tracking; test a more specific first-step ask for Cold Outbound - HR Leaders; revise Cold Outbound - People Ops step 3’s ask. Fix the Expansion tracking error first for measurement integrity; prioritize Cold Outbound - HR Leaders first for performance.
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 $0.1563 · 19s · in 9 / out 925 tok
✓ metrics_present✓ deltas✓ coverage_ratio✓ pace✓ paragraph

✓ Correct Answer (ground truth)

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

Model's actual answer

show the model's full answer
Q3-2026 QTD (66 of 92 days elapsed; linear pace = 66 ÷ 92 = 71.7% of quarter). Delta is actual minus target.

| Metric | QTD actual | Target | Delta | Pace |
|---|---:|---:|---:|---|
| SQMs | 230 | 300 | 230 − 300 = −70 | Ahead: 230 vs 300 × 66/92 = 215.2 |
| SQOs | 84 | 120 | 84 − 120 = −36 | Behind: 84 vs 120 × 66/92 = 86.1 |
| DS2s | 40 | 75 | 40 − 75 = −35 | Behind: 40 vs 75 × 66/92 = 53.8 |
| Closed-lost MIA rate | 5 ÷ 25 = 20% | ≤10% | +10 percentage points | Behind: rate exceeds the ceiling; linear pacing does not apply |
| Same-quarter closes | 10 | 20 | 10 − 20 = −10 | Behind: 10 vs 20 × 66/92 = 14.3 |
| Active pipeline coverage against target | $3,000,000 ÷ $4,000,000 = 75% | 100% ($4,000,000) | −25 percentage points (−$1,000,000) | Ahead of a *linear* benchmark: $3,000,000 vs $4,000,000 × 66/92 = $2,869,565; still below the full target |

What moved this week cannot be determined: only one QTD snapshot was provided, with no prior-week values.
communication 5 tests
ceo-slack-compression0.80
Plain-English question: Compress the forecast analysis into one Slack message the CEO can read in ten seconds.
Prompt — what the model saw
Compress the forecast analysis below into a single Slack message for the CEO. Rules: at most three sentences; under 80 words; lead with the decision or the so-what; keep every distinct number that matters and the one caveat that changes the conclusion; cut any sentence that does not carry a claim, a number, or a directive. No em dashes, no throat-clearing phrases.
cost $0.1578 · 21s · in 12 / out 786 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
Treat Q3’s $115,976.75 weighted forecast as unvalidated: $44,729 COMMIT + 35% × $203,565 BEST_CASE ($71,247.75); PIPELINE contributes $0. Only 54 of 86 deals have in-quarter close dates; 32 totaling $227,575 fall after September 30, including COMMIT Deal-D348E1 ($13,770). All 7 in-quarter COMMIT deals lack a documented why-buy, so do not treat the $44,729 committed amount as buyer-validated.
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 $0.0945 · 22s · in 9 / out 581 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: Following up on the demo

Hi,

I’m following up on the August 5 recap of our July 28 demo and the pricing for 150 seats. Your People team had a strong reaction to automated milestone awards and the points catalog.

Would you let me know if you’d like to discuss the pricing further?

Best,
Alex
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 $0.1570 · 19s · in 12 / out 702 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: We brought in 46 SQMs against a target of 52, a gap of 6 (52 − 46). Webinars delivered 18 of the 46 SQMs. Paid search cost per SQM held at $150.

Sales: We converted 14 SQOs, set 9 DS2 meetings, and created $310,000 in new pipeline. The same-quarter close count was 3.

CS: We saved 2 renewals this week. Team NPS moved to 61, and 3 red-flag accounts remain open heading into next week. The prior NPS score was not provided, so the size of the change is unknown.

PLG: We added 412 signups, with activation at 31%. Separately, 38 companies reached the aha moment of 10 recognition gives. The extract does not establish whether those companies came from this week’s 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 $0.1517 · 17s · in 12 / out 741 tok
✓ all_partners✓ pipeline_amount✓ quiet_one_line

✓ Correct Answer (ground truth)

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

Model's actual answer

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

Partner-sourced pipeline: 2 + 1 + 2 = 5 deals; $275,000 + $140,000 + $135,000 = $550,000.

- Apex Rewards Co — 2 DS1 sourced deals: Deal-DDAAF2 ($180,000) + Deal-2CF33E ($95,000) = $275,000. Co-webinar locked for 09-15.
- HRCloud Partners — 1 sourced deal: Deal-F1CDA5 ($140,000). Security review closed; opportunity moved to DS2.
- CultureBridge — 2 early-stage sourced deals: Deal-096E1D ($60,000) + Deal-067213 ($75,000) = $135,000. Lunch-and-learn produced both.
- WorkWell Group — 0 sourced deals. Q4 joint-playbook restart discussed; planning call booked for 09-09.
- Recogniq — Quiet; no activity or sourced deals provided.
- KudosWave — Quiet; no activity or sourced deals provided.
- PeopleFirst Advisors — Quiet; no activity or sourced deals provided.
- TotalPerk — Quiet; no activity or sourced deals provided.
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 $0.1080 · 17s · in 6 / out 603 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 using TLS 1.2 or higher. [P1]

Q3. Yes. Bonusly maintains a SOC 2 Type II report, renewed annually. Prospects can obtain it under NDA. [P2]

Q4. Customer data is retained for 90 days after the contract ends, then deleted from production systems. [P3]

Q5. The current subprocessor list is 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 is available on the Enterprise plan. [P5]

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

Q8. Unanswerable from these excerpts; they do not state whether Bonusly holds ISO 27001 certification. An ISO 27001 certificate or certification record would answer this. [P1–P8]

Q9. Unanswerable from these excerpts; they do not state a contractual uptime percentage. The applicable service-level agreement would answer this. [P1–P8]

Q10. Unanswerable from these excerpts; they do not state whether Bonusly will sign a HIPAA Business Associate Agreement. An approved BAA policy or agreement template would answer this. [P1–P8]
ops-maintenance 5 tests
skill-file-reconciliation0.86
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 $0.3482 · 50s · in 9 / out 2,882 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
Reconciliation is limited to the 14 manifest rows and 14 skill files supplied. A target absent from this set cannot be confirmed nonexistent outside it.

| Severity | Action | Finding and proposal |
|---|---|---|
| CRITICAL | MERGE | `comms-drafter` and `email-drafter` both claim “write me an email,” “draft a follow-up,” and “what should I say,” including sales and CS emails. Make `comms-drafter` the broad entry point and retain `email-drafter` only for its distinct email-signature workflow, with non-overlapping triggers. |
| WARNING | UPDATE_BODY | `deal-strategy-coach` → `email-drafter` → `deal-strategy-coach` is a conditional handoff loop: the coach invokes the drafter for manager emails, while the drafter points strategic requests back to the coach. Make the return handoff conditional on a *new* strategy request, not the draft already being handled. |
| WARNING | REVIEW | Targets referenced but absent from both the supplied files and manifest include `bonusly-brand`, `prospect-research-multithreading`, and `signalforge-reports`; `analysis-validator` also delegates to eight `bonusly-*-questions` specialists not listed here. Verify those dependencies in the full registry before labeling any globally dangling; add their rows/files or remove invalid handoffs. |
| WARNING | MERGE | `weekly-pipeline-report` (“pipeline update,” “pipeline report,” “what does pipeline look like”) overlaps `pipeline-intelligence-report` (“pipeline update,” “pipeline report,” “what’s the pipeline look like”). Retain both only with an explicit routing boundary: weekly funnel/booking metrics versus full deal-by-deal scoring. `sales-forecast` also overlaps the latter on “pipeline forecast” and forecast context; reserve current-quarter revenue outlooks for `sales-forecast`. |
| CRITICAL | UPDATE_BODY | Transcript schema conflicts: `closed-lost-analysis` selects `t.SNIPPET`; `stale-pipeline-report` says `GONG_TRANSCRIPTS_AGG` has only `CONVERSATION_KEY` and `TRANSCRIPT`, consistent with `analysis-validator`’s approved transcript source. Retain the `TRANSCRIPT` specification; correct the closed-lost query. |
| WARNING | UPDATE_BODY | `analysis-validator` identifies itself as v3.6 but its validation-trail template says v3.2. Retain v3.6, the stated current version in the supplied file, and align the template. |
| WARNING | UPDATE_BODY | Hardcoded destination IDs appear in `deal-strategy-coach` (AE Excellence Playbook page `2257879045`), `partner-digest` (folder `2286616609` and reference-page IDs), `sales-forecast` (parent page `2232582148`), and `signalforge-feedback` (feedback page `2295136266`). Resolve destinations from maintained configuration or lookup rather than embedding them in workflow bodies. |
| WARNING | UPDATE_BODY | Hardcoded dates and time-bound assumptions include `model-selection`’s `last_checked: 2026-05-19`, `weekly-pipeline-report`’s fixed Q2 2026 business-day window, `sales-forecast`’s “Open Q2 Deals” and “Q2 Narrative,” and dated examples/expected ranges in `analysis-validator`, `closed-lost-analysis`, and `partner-digest`. Make operational windows dynamic; keep historical dates clearly labeled as examples or changelog entries. |
| WARNING | UPDATE_BODY | Hardcoded people/rosters include `pipeline-intelligence-report`’s AE owner list, `analysis-validator`’s GTM roster, `weekly-pipeline-report`’s Ben Lavin ownership, `partner-digest`’s Amani Phipps ownership and named contacts, and example companies/people in `closed-lost-analysis` and `signalforge-claim-compressor`. Resolve current personnel at run time; label historical examples as non-operational. |
| INFO | REVIEW | Description-length check: **0 over limit**. Arithmetic: 14 listed lengths checked; 0 are greater than 1,024 (maximum listed: 1,006). No trimming proposed. |
| INFO | REVIEW | Manifest drift: **0 files without rows; 0 rows without files**. Arithmetic: 14 supplied file names − 14 matching manifest names = 0 in either direction. No manifest change proposed. |
runbook-from-slack-threadPASS 1.00
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 $0.0845 · 22s · in 9 / out 799 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
1. [M01] Bryce Harmon acknowledged the PagerDuty alert for reward-worker queue depth > 10k and took IC. Verification: the thread records his acknowledgment; no independent verification is documented. Rollback: not documented — needs confirmation.

2. [M02] Farid Osman ran `bundle exec rake sidekiq:queue_depth`. Verification: it returned 48,213 pending reward jobs; he stated normal is under 500.

3. [M03] Farid Osman inspected the dead set and reported 112 jobs, all `Redis::TimeoutError` from around 13:58. Exact inspection command and independent verification: not documented — needs confirmation.

4. [M04] Farid Osman paused enqueue with `bin/rails runner 'FeatureFlag.disable(:auto_recognition_enqueue)'`. Verification of the flag state: not documented — needs confirmation. Rollback: `bin/rails runner 'FeatureFlag.enable(:auto_recognition_enqueue)'`.

5. [M05] Elena Sinclair cleared the dead set in the console. Exact command, verification, and rollback: not documented — each needs confirmation. This thread does not establish a repeatable clearing procedure.

6. [M06] Bryce Harmon scaled workers from 3 to 6 with `kubectl scale deployment/reward-worker --replicas=6`. Direct verification of replica count: not documented — needs confirmation. Rollback: `kubectl scale deployment/reward-worker --replicas=3`.

7. [M07] Farid Osman reported queue depth at 9,400 and falling ~1,200/min. Measurement command: not documented — needs confirmation.

8. [M08] Cole Ingram ran `bundle exec rake sidekiq:queue_depth` and reported that it returned 0. He also reported the Datadog error rate back to baseline.

9. [M09] Bryce Harmon re-enabled enqueue with `bin/rails runner 'FeatureFlag.enable(:auto_recognition_enqueue)'`. Verification: 40 new jobs processed cleanly in the next 3 minutes. Rollback for this step: not documented — needs confirmation.

10. [M10] Bryce Harmon scaled workers back down with `kubectl scale deployment/reward-worker --replicas=3`. Verification: he reported the queue stable at 0 and the incident resolved; direct replica-count verification is not documented — needs confirmation. Rollback for this step: not documented — needs confirmation.
datadog-incident-timeline0.80
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 $0.1656 · 35s · in 15 / out 1,206 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
The first logged error is at 2026-09-03 14:01:12 UTC: `reward-service` reports `Redis::TimeoutError` connecting to `redis-primary:6379` after 5 seconds (`datadog_logs.csv`).

The cascade, in logged order: `reward-service` exhausts retries for `RewardGiveJob` (14:01:20–14:01:40) → `sidekiq` reports `RewardGiveJob` failures and retries (from 14:01:40) → the `reward` queue exceeds 10,000 (14:02:30) → `api-gateway` times out calling `reward-service` and returns 502s (from 14:03:05) → `web-app` reports failed Give form submissions from those 502s (from 14:03:30). `sidekiq_jobs.csv` also lists `RecognitionDigestJob` Redis timeouts: 12 `RewardGiveJob` + 4 `RecognitionDigestJob` = 16 listed failed jobs. `reward-service` logs Redis connection restoration at 14:22:10; `sidekiq` logs queue depth below 500 at 14:24:45.

Datadog query to confirm the first error, scoped to that minute:
`service:reward-service "Redis::TimeoutError" "redis-primary:6379"`
Time range: 2026-09-03 14:01:00–14:02:00 UTC.

The logs do not show why Redis timed out, whether the timeout began before this slice, how many users were affected, or whether every failed job ultimately succeeded.
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 $0.1321 · 21s · in 9 / out 816 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
The export names no individual companies, so only segments or targeting rules can be reported. An “off” flag may have configured targets, but the export does not show it enabled for them.

| Flag | State | What the code excerpt controls | Targeting rule; company count |
|---|---|---|---|
| `recognition_streaks_v2` | On | Records a give in `StreakTracker`. | `segment:beta_companies`; 42 |
| `points_budget_guardrails` | On | Enforces the giver’s points budget. | `all_companies`; 220 |
| `slack_dm_nudges` | On | Allows the job to send a Slack DM nudge. | `segment:region_na`; 87 |
| `redeem_flow_redesign` | Off | Renders `RedeemV2Component` when enabled; otherwise `RedeemV1Component`. | `targeted_list`; 12 configured targets |
| `analytics_dashboard_v3` | On | Uses `AnalyticsV3` for the dashboard. | `segment:tier_three`; 65 |
| `ms_teams_app_v2` | Off | Installs `TeamsAppV2` when enabled. | `targeted_list`; 9 configured targets |
| `legacy_give_modal` | Off | No reference in the supplied code excerpt; behavior unknown. | `segment:legacy_plan`; 14 configured targets |
| `survey_boosters_q3` | On | No reference in the supplied code excerpt; behavior unknown. | `segment:legacy_plan`; 7 |
| `paused_offboard_cleanup` | Off | No reference in the supplied code excerpt; behavior unknown. | No targeting rule; 0 targets |

Count check: on-flag counts sum to 42 + 220 + 87 + 65 + 7 = 421; off-flag configured-target counts sum to 12 + 9 + 14 + 0 = 35. These are sums across flags, not distinct-company totals; overlap is unknown. Sources: `flags_export.csv` and `flag_code.md` as provided.
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 $0.0976 · 12s · in 6 / out 346 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 — GREEN (standard approval): Mutual confidentiality, standard carve-outs, and Delaware law; §3 includes information that “is independently developed” and “must be disclosed by law or court order.”

NDA-2 — YELLOW (counsel review): §4 adds an employment restriction: “During the term of this Agreement and for eighteen (18) months thereafter, neither party shall solicit for employment or hire any employee of the other party with whom it came into contact under this Agreement.”

NDA-3 — RED (full legal review): §2 bars the Recipient from “engag[ing] in or provid[ing] services to any business that competes with Discloser’s business”; §3 selects “the laws of the Republic of Ireland” and exclusive jurisdiction there; §4 states “No confidentiality carve-outs are stated in this Agreement,” alongside the one-way, five-year term in §1.