← back to all models ← RevenueBench home
mistralai

mistralai/mistral-small-2603

Mean 0.707 · 10/40 perfect tests · $0.13 total · modalities in: text, image · 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-audit0.50
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 $0.0056 · 8s · in 36,202 / out 342 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
State definitions
- DS2+: stages DS2, DS3, DS4, DS5
- DS1 timestamp present: non-empty t_ds1
- Why-buys substantive: non-empty why_buys and length ≥ 15 (LONG(n) counts present)
- Stage timestamps out of order (regressed): any stage timestamp earlier than a later stage timestamp

Compliance
- DS2+ deals: 65
- DS2+ deals non-compliant on why-buys: 1 (1.5%)
  - Deal-499BF6 (Deal-499BF6)
- By owner (DS2+):
  - Bryce Harmon: 23 deals, 0 non-compliant (0.0%)
  - Alex Franklin: 19 deals, 0 non-compliant (0.0%)
  - Dana Mercer: 15 deals, 0 non-compliant (0.0%)
  - Cole Ingram: 8 deals, 1 non-compliant (12.5%)

Hygiene gaps
- Deals with no DS1 timestamp: 0
- Deals with regressed timestamps: 1 (Deal-547B2B)

Process fixes
1. Add a required why_buys field for DS2+ deals; auto-block saves without ≥15 chars.
2. Enforce DS1 timestamp entry at deal creation; block save if t_ds1 empty.
3. Add a pipeline rule: if any stage timestamp ≤ a later stage timestamp, flag the deal and require correction before advancing.
owner-resolution0.17
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 $0.0055 · 6s · in 36,103 / out 104 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
Deals resolved: 103

Unmatched owner ids:
- 83155924

Archived/deactivated owners:
- None

Pipeline amount per resolved owner:
- Bryce Harmon: 796,681
- Dana Mercer: 276,550
- Alex Franklin: 391,749
- Farid Osman: 288,000
- Elena Sinclair: 1
gong-hubspot-join-integrity0.75
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 $0.0040 · 7s · in 24,925 / out 106 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) Orphan count: 38. Sample aliases: Deal-8FA85D, Deal-8FC3F9, Deal-3B7945, Deal-42B265, Deal-9CCC42.

(b) Duplicate conversation keys: 0.

(c) Among open deals at DS3 or later (count=48), 29 have at least one logged call. Share: 60.4% (29/48).
snowflake-sql-trapped-catalog0.83
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 $0.0032 · 9s · in 17,491 / out 950 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
-- Use canonical daily HubSpot deals (live and populated)
WITH first_deal_month AS (
  SELECT
    d.PROPERTY_HS_OBJECT_ID AS deal_id,
    d.PROPERTY_DEALNAME AS deal_name,
    d.PROPERTY_HUBSPOT_OWNER_ID AS owner_id,
    d.PROPERTY_DEALSTAGE AS deal_stage_id,
    d.PROPERTY_AMOUNT AS deal_amount,
    d.PROPERTY_CLOSEDATE AS close_date,
    d.PROPERTY_HS_IS_CLOSED,
    d.PROPERTY_HS_MANUAL_FORECAST_CATEGORY,
    d.PROPERTY_AI_WHY_BUYS,
    d.PROPERTY_PIPELINE,
    -- First calendar month as customer: earliest close_date in sales pipeline
    DATE_TRUNC('month', d.PROPERTY_CLOSEDATE) AS first_month
  FROM HUBSPOT_HUB_1973303.V2_DAILY.OBJECTS_DEALS d
  WHERE d.PROPERTY_PIPELINE = 'default'
    AND d.PROPERTY_HS_IS_CLOSED = TRUE
),

deal_contacts AS (
  -- Associations between deals and contacts
  SELECT DISTINCT
    a.DEAL_OBJECTID AS deal_id,
    a.CONTACT_OBJECTID AS contact_id
  FROM HUBSPOT_HUB_1973303.V2_DAILY.ASSOCIATIONS_DEALS_TO_CONTACTS a
),

company_deals AS (
  -- Map deals to companies via contacts (HubSpot contacts lack company id; use engagements for company context)
  SELECT DISTINCT
    f.deal_id,
    f.deal_name,
    f.owner_id,
    f.deal_stage_id,
    f.deal_amount,
    f.close_date,
    f.first_month,
    e.COMPANY_ID AS company_id
  FROM first_deal_month f
  JOIN PRODUCTION.HUBSPOT.HS_ENGAGEMENTS_ENRICHED e
    ON e.DEAL_ID = f.deal_id
),

-- Unique givers per company in first calendar month (exclude deleted filter per rules)
givers AS (
  SELECT
    c.company_id,
    COUNT(DISTINCT dc.contact_id) AS unique_givers
  FROM company_deals c
  JOIN deal_contacts dc
    ON dc.deal_id = c.deal_id
  JOIN HUBSPOT_HUB_1973303.V2_DAILY.OBJECTS_CONTACTS oc
    ON oc.PROPERTY_HS_OBJECT_ID = dc.contact_id
  GROUP BY c.company_id
),

-- Recognition count per company in first calendar month (exclude deleted filter)
recognitions AS (
  SELECT
    e.COMPANY_ID AS company_id,
    COUNT(*) AS recognition_count
  FROM PRODUCTION.HUBSPOT.HS_ENGAGEMENTS_ENRICHED e
  JOIN company_deals c
    ON e.DEAL_ID = c.deal_id
    AND DATE_TRUNC('month', e.CREATED_AT) = c.first_month
  GROUP BY e.COMPANY_ID
),

-- Successful redemptions per company in first calendar month
redemptions AS (
  SELECT
    rr.COMPANY_ID AS company_id,
    COUNT(*) AS successful_redemption_count
  FROM PRODUCTION.DEPRECATED_RECOGNITION.REDEMPTION_RECORDS_V2 rr
  JOIN company_deals c
    ON rr.COMPANY_ID = c.company_id
    AND DATE_TRUNC('month', rr.CREATED_AT) = c.first_month
  WHERE rr.STATE = 'succeeded'
  GROUP BY rr.COMPANY_ID
)

-- Final result per customer company
SELECT
  c.company_id,
  c.deal_name AS customer_company,
  g.unique_givers,
  r.recognition_count,
  red.successful_redemption_count
FROM company_deals c
JOIN givers g
  ON g.company_id = c.company_id
JOIN recognitions r
  ON r.company_id = c.company_id
JOIN redemptions red
  ON red.company_id = c.company_id
GROUP BY
  c.company_id,
  c.deal_name,
  g.unique_givers,
  r.recognition_count,
  red.successful_redemption_count;
```
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 $0.0014 · 8s · in 3,255 / out 1,074 tok
✓ dup_clusters✓ invalid_emails✓ survivor_language✓ completeness_pct✓ no_invent fabricated: C-C9BB2A

✓ 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
## Completeness Audit

- Companies.csv: 100% fields present
- Contacts.csv: 80% email, 60% title, 50% persona
- ZoomInfo enrichment: 90% industry, 80% employee_count, 85% hq_country

---

## Company Field Discrepancies (CRM vs ZoomInfo)

- C-66D1FC: industry tech vs Computer Software; hq_country US vs United States
- C-C6FE92: industry Retail vs Retail (match)
- C-950043: industry Retail vs Retail (match)
- C-D73B89: industry Retail vs Retail (match)
- C-EC3025: industry Technology vs Computer Software
- C-96039F: industry Finance vs Finance (match)
- C-44EA29: industry tech vs Computer Software
- C-92D97D: industry Technology vs Computer Software
- C-D04904: industry Technology vs Computer Software
- C-31ED2A: industry Manufacturing vs Manufacturing (match)
- C-77A95A: industry Technology vs Computer Software
- C-AA8DDA: industry Technology vs Computer Software
- C-B23205: industry Healthcare vs Healthcare (match)
- C-E51FB7: industry Finance vs Finance (match)
- C-63A874: industry Healthcare vs Healthcare (match)
- C-D0662E: industry Retail vs Retail (match)
- C-B25F40: industry Technology vs Computer Software
- C-60C75F: industry tech vs Computer Software
- C-425E2A: industry Tech  vs Computer Software
- C-2C60E5: industry Healthcare vs Healthcare (match)
- C-B97B4E: industry Retail vs Retail (match)
- C-2D7423: industry Manufacturing vs Manufacturing (match)
- C-7BBDFA: industry health care vs health care (match)
- C-50D386: industry health care vs health care (match)
- C-BA969B: industry Tech  vs Computer Software
- C-332637: industry Technology vs Computer Software
- C-93C8BF: industry Tech  vs Computer Software
- C-EE9FFB: industry Healthcare vs Healthcare (match)
- C-C9BB2A: industry Tech  vs Computer Software
- C-0A092931: industry Technology vs Technology (match)
- C-0A092932: industry tech vs tech (match)
- C-0A092933: industry SaaS vs Technology
- C-0A092934: industry Technology vs Technology (match)

---

## Duplicate Company Clusters

- acme-corp.com: C-0A092931, C-0A092932
- globex.io: C-0A092933, C-0A092934

Survivors: C-0A092931, C-0A092933

---

## Invalid Emails and Domain Mismatches

- CT-0010: user0@ (invalid)
- CT-0011: user1@other-domain.com (domain mismatch)
- CT-0192: user2@ (invalid)

---

## Top 10 Fixes by Pipeline Amount at Stake

1. C-0A092934 (globex.io) — resolve industry discrepancy (SaaS vs Technology)
2. C-77A95A (77a95a.com) — resolve industry discrepancy (Technology vs Computer Software)
3. C-EC3025 (ec3025.com) — resolve industry discrepancy (Technology vs Computer Software)
4. C-66D1FC (66d1fc.com) — resolve industry and hq_country discrepancies
5. C-332637 (332637.com) — resolve industry discrepancy (Technology vs Computer Software)
6. C-44EA29 (44ea29.com) — resolve industry discrepancy (tech vs Computer Software)
7. C-92D97D (92d97d.com) — resolve industry discrepancy (Technology vs Computer Software)
8. C-D04904 (d04904.com) — resolve industry discrepancy (Technology vs Computer Software)
9. C-BA969B (ba969b.com) — resolve industry discrepancy (Tech  vs Computer Software)
10. C-60C75F (60c75f.com) — resolve industry discrepancy (tech vs Computer Software)
deal-intelligence 5 tests
closed-lost-classification0.60
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 $0.0055 · 20s · in 22,969 / out 3,355 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
I'll classify each deal based on the provided tags and free-text reasons, then summarize the findings.

### Deal Classifications

| deal_id      | deal_alias   | primary_category         | side   |
|--------------|--------------|--------------------------|--------|
| 63027745829  | Deal-DB0AAC  | timing                   | buyer  |
| 63683330727  | Deal-F7F635  | competitor               | buyer  |
| 63327490589  | Deal-AC944F  | MIA                      | unknown|
| 63027809948  | Deal-214060  | MIA                      | unknown|
| 49134744746  | Deal-91A056  | timing                   | buyer  |
| 48988037529  | Deal-29326C  | timing                   | buyer  |
| 64524670260  | Deal-5DB9B0  | product gap              | buyer  |
| 63836912221  | Deal-831B7B  | timing                   | buyer  |
| 63680220945  | Deal-F97C37  | competitor               | buyer  |
| 41554388661  | Deal-13E9CF  | no decision              | buyer  |
| 63222333276  | Deal-39E25C  | timing                   | buyer  |
| 63291006863  | Deal-7ED004  | pricing                  | buyer  |
| 59275344824  | Deal-21B045  | MIA                      | unknown|
| 58754552851  | Deal-B3ABED  | timing                   | buyer  |
| 62455767176  | Deal-422BA6  | competitor               | buyer  |
| 61050677765  | Deal-ED9AE7  | timing                   | buyer  |
| 61038826051  | Deal-988493  | MIA                      | unknown|
| 63222778291  | Deal-381C8C  | competitor               | buyer  |
| 59418526836  | Deal-F308CA  | MIA                      | unknown|
| 62750632013  | Deal-F1E8A6  | competitor               | buyer  |
| 60035957084  | Deal-B6AC09  | timing                   | buyer  |
| 62750599045  | Deal-70F704  | timing                   | buyer  |
| 61873010467  | Deal-E6E80A  | timing                   | buyer  |
| 54322940958  | Deal-B038F0  | timing                   | buyer  |
| 61625438845  | Deal-4664E1  | MIA                      | unknown|
| 63222258948  | Deal-175756  | timing                   | buyer  |
| 63717524046  | Deal-E74A73  | no decision              | buyer  |
| 63661381816  | Deal-DDAB52  | competitor               | buyer  |
| 63514024330  | Deal-ACE061  | competitor               | buyer  |
| 62852981522  | Deal-BB78F3  | timing                   | buyer  |
| 60984778911  | Deal-D48E0B  | MIA                      | unknown|
| 61054009677  | Deal-15DA99  | timing                   | buyer  |
| 49530802588  | Deal-F4AF5D  | timing                   | buyer  |
| 62115565909  | Deal-79B7A1  | timing                   | buyer  |
| 62487728289  | Deal-583ADB  | MIA                      | unknown|
| 63680238945  | Deal-8E27DA  | product gap              | buyer  |
| 63433935544  | Deal-2D2F8D  | competitor               | buyer  |
| 60694374202  | Deal-E0441F  | MIA                      | unknown|
| 60897501515  | Deal-7CB44D  | MIA                      | unknown|
| 60848492546  | Deal-0F96AA  | competitor               | buyer  |
| 60355222018  | Deal-1BCA50  | competitor               | buyer  |
| 61625560885  | Deal-7CC678  | competitor               | buyer  |
| 59370037379  | Deal-FAC17C  | timing                   | buyer  |
| 61052858247  | Deal-242273  | competitor               | buyer  |
| 56896716581  | Deal-50E5D8  | no decision              | buyer  |
| 62706569880  | Deal-A2C349  | competitor               | buyer  |
| 59729560611  | Deal-9F176A  | timing                   | buyer  |
| 61764780962  | Deal-7B2236  | no decision              | buyer  |
| 57663815975  | Deal-AFA56C  | MIA                      | unknown|
| 61129576246  | Deal-C7156E  | competitor               | buyer  |
| 60866104098  | Deal-C33D91  | pricing                  | buyer  |
| 59086317965  | Deal-9048EB  | MIA                      | unknown|
| 60857702003  | Deal-5E64CE  | no decision              | buyer  |
| 61415737717  | Deal-8A0992  | competitor               | buyer  |
| 63085142442  | Deal-D0C698  | competitor               | buyer  |
| 56549284976  | Deal-69CF3D  | timing                   | buyer  |
| 61507337022  | Deal-ECBF89  | timing                   | buyer  |
| 57663820059  | Deal-3618CC  | product gap              | buyer  |
| 60548236897  | Deal-EECC02  | competitor               | buyer  |
| 60896018951  | Deal-5AD03E  | competitor               | buyer  |
| 62121718303  | Deal-D1A623  | timing                   | buyer  |
| 63189310018  | Deal-413C56  | no decision              | buyer  |
| 60008683142  | Deal-47F1A1  | competitor               | buyer  |
| 54352704007  | Deal-BF2A98  | competitor               | buyer  |
| 62115549771  | Deal-2A292B  | no decision              | buyer  |
| 60868303272  | Deal-D1AABF  | MIA                      | unknown|
| 60331562409  | Deal-FEDBCB  | no decision              | buyer  |
| 62622503749  | Deal-1E7DA9  | competitor               | buyer  |
| 61625500700  | Deal-2BBA21  | MIA                      | unknown|
| 62852981127  | Deal-286F9C  | competitor               | buyer  |
| 62704591183  | Deal-7FBAC6  | no decision              | buyer  |
| 60008716662  | Deal-369281  | competitor               | buyer  |
| 61475258733  | Deal-386F6E  | MIA                      | unknown|
| 61114491171  | Deal-9FCD0D  | competitor               | buyer  |
| 55624236610  | Deal-55867E  | timing                   | buyer  |
| 62853160058  | Deal-DAFB82  | pricing                  | buyer  |
| 59370028385  | Deal-2FEDDB  | no decision              | buyer  |
| 61024624821  | Deal-64B19A  | competitor               | buyer  |
| 60419904928  | Deal-3F86A0  | MIA                      | unknown|
| 60675690108  | Deal-096750  | MIA                      | unknown|
| 61055126627  | Deal-F325A5  | timing                   | buyer  |
| 61432497792  | Deal-ABD14C  | no decision              | buyer  |
| 60868240474  | Deal-79E61A  | MIA                      | unknown|
| 60551632419  | Deal-8A119B  | pricing                  | buyer  |
| 60644185922  | Deal-AE7C4E  | MIA                      | unknown|
| 62115387928  | Deal-DAB4F1  | MIA                      | unknown|
| 61432389647  | Deal-B4B50F  | MIA                      | unknown|
| 60786197933  | Deal-981AD4  | product gap              | buyer  |
| 62121470977  | Deal-DC77FE  | competitor               | buyer  |
| 61129575303  | Deal-5885B9  | MIA                      | unknown|

### Summary

- **Category counts:**
  - competitor: 24
  - timing: 23
  - MIA: 17
  - no decision: 7
  - pricing: 3
  - product gap: 3

- **Side split:**
  - Bonusly: 0
  - buyer: 66
  - unknown: 21

- **Disagreements between structured tag and free-text reason:** 12 deals
  - Deal-DB0AAC: tag=Lost- Timing (1 year or more), reason=rescheduled meetings/pause
  - Deal-5DB9B0: tag=Lost- Does not fit ICP (write in notes), reason=Spam
  - Deal-7ED004: tag=Lost- Budget/Price, reason=Did not get budget approval
  - Deal-ED9AE7: tag=Lost DM, reason=Timing, budget, authority
  - Deal-70F704: tag=Lost DM, reason=MIA - will reopen if they reach back out
  - Deal-15DA99: tag=Lost- Timing (1 year or more), reason=looking to bring it back up early 2027
  - Deal-F4AF5D: tag=Lost- Timing (1 year or more), reason=Timing looking at early next year
  - Deal-79B7A1: tag=Lost- Timing (1 year or more), reason=Timing
  - Deal-5E64CE: tag=Doing nothing/Not a priority/Cost, reason=fee for getting out of Nectar agreement
  - Deal-413C56: tag=Doing nothing/Not a priority/Cost, reason=Back to school is priority and CEO not ready
  - Deal-2FEDDB: tag=Doing nothing/Not a priority/Cost, reason=Unsure on timing
  - Deal-8A119B: tag=Lost- Budget/Price, reason=Didn't get approval

- **Two patterns most worth acting on:**
  1. **Competitor losses (24 deals):** This is the largest single category. Competitive displacement, especially by ADP TotalSource PEO partnerships and Canadian providers, is a recurring theme. Focus on competitive differentiation and partnership strategies.
  2. **Timing issues (23 deals):** Many deals are being pushed out to 2027-2028. This suggests either a need for better pipeline qualification or more proactive nurture campaigns to keep deals warm until budget cycles align.
pipeline-tiering0.80
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 $0.0074 · 12s · in 43,594 / out 1,393 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": 11, "ACTION": 23, "BUILD": 29, "REVIVE": 14, "WATCH": 24, "RISKY": 2}, "tier_examples": {"LOCK": ["Deal-25F752", "Deal-E53952", "Deal-5408B0", "Deal-944310", "Deal-403845", "Deal-B7EBD1", "Deal-3974EB", "Deal-6787C2", "Deal-2465CE", "Deal-0660B4", "Deal-1FC049"], "ACTION": ["Deal-2D1F1B", "Deal-66D1FC", "Deal-C6FE92", "Deal-950043", "Deal-D73B89", "Deal-B23205", "Deal-012CB1", "Deal-40522D", "Deal-C5658B", "Deal-523604", "Deal-9D0060", "Deal-3BA5EA", "Deal-7FA0C3", "Deal-E531A6", "Deal-D0BC96", "Deal-42F601", "Deal-ED725A", "Deal-55164C", "Deal-B936FE", "Deal-4B0BEB", "Deal-D7E999", "Deal-E73427", "Deal-898FC5"], "BUILD": ["Deal-215CCA", "Deal-690476", "Deal-6C60D4", "Deal-F436DA", "Deal-034D49", "Deal-317E6F", "Deal-0D2F7A", "Deal-1E2498", "Deal-D1E6C2", "Deal-BE3D9D", "Deal-635B8E", "Deal-DCA846", "Deal-D9A72E", "Deal-D9A12F", "Deal-C2FF3C", "Deal-CA5E44", "Deal-4F775F", "Deal-819506", "Deal-712010", "Deal-13FEBD", "Deal-175395", "Deal-2F3A66", "Deal-481E24", "CFE1E8", "Deal-99A240", "Deal-87DDD1", "Deal-332637", "Deal-1BA595", "Deal-813836"], "REVIVE": ["Deal-584EE5", "Deal-62D607", "Deal-530B50", "Deal-60C2C2", "Deal-FA053A", "Deal-8AD4A5", "Deal-15D24F", "Deal-9DDE86", "Deal-44EA29", "Deal-F40F04", "Deal-5EED42", "Deal-DAF1D9", "Deal-8BC9F5", "Deal-342E96"], "WATCH": ["Deal-278DEC", "Deal-627646", "Deal-60869714514", "Deal-61024657672", "Deal-61418628616", "Deal-61432459847", "Deal-61432482880", "Deal-61475253432", "Deal-61625192572", "Deal-61749892214", "Deal-61750203694", "Deal-61873011731", "Deal-62121531689", "Deal-62121780531", "Deal-62121783047", "Deal-62121921419", "Deal-62453363854", "Deal-62455757718", "Deal-62494456737", "Deal-62494458497", "Deal-62499298608", "Deal-62616681006", "Deal-62622451763", "Deal-62622465606"], "RISKY": ["Deal-6787C2", "Deal-2D1F1B"]}, "risky_deals": ["Deal-6787C2", "Deal-2D1F1B"], "lock_violations": 0, "pipeline_shape": The pipeline is heavily weighted toward BUILD (29 deals) and ACTION (23 deals), reflecting a broad mid-funnel with many low-to-mid value opportunities needing nurture; LOCK is small (11 deals) and concentrated in high-forecast categories with recent engagement, while RISKY (2 deals) highlights forecast-category mismatches with weak engagement signals.
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 $0.0014 · 8s · in 2,190 / out 1,299 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
```json
[
  {
    "transcript_id": "TX-001",
    "deal_alias": "Deal-CFE7F4",
    "why-buys": [
      "automating anniversary and birthday awards",
      "our HR team of three cannot keep up with it manually",
      "track everything in a spreadsheet, and people slip through the cracks"
    ],
    "pain points": [
      "manual tracking of anniversary and birthday awards",
      "spreadsheet-based tracking causing people to slip through the cracks"
    ],
    "stakeholders": ["Prospect (VP People)", "Prospect (HR Admin)"],
    "budget signal": 40000,
    "timeline signal": "before open enrollment in November",
    "competitor mentioned": "Achievers",
    "next step": "security review on September 12",
    "objections": ["need SSO and audit logs for IT to sign off"],
    "confidence": "high"
  },
  {
    "transcript_id": "TX-002",
    "deal_alias": "Deal-70BB30",
    "why-buys": [
      "tie recognition to retention for our hourly workforce",
      "regretted turnover there is over 30%"
    ],
    "pain points": [
      "high regretted turnover (over 30%) for hourly workforce",
      "need integration with Workday to be rock solid"
    ],
    "stakeholders": ["Prospect (Head of Total Rewards)", "Prospect (CFO)"],
    "budget signal": 25000,
    "timeline signal": "decision by end of September",
    "competitor mentioned": null,
    "next step": "send the pilot agreement and route to legal this week",
    "objections": ["Integration with Workday has to be rock solid"],
    "confidence": "high"
  },
  {
    "transcript_id": "TX-003",
    "deal_alias": "Deal-530B50",
    "why-buys": [
      "make recognition visible across our 12 retail locations",
      "Store managers have zero budget autonomy for on-the-spot recognition today"
    ],
    "pain points": [
      "recognition not visible across 12 retail locations",
      "store managers have zero budget autonomy for on-the-spot recognition"
    ],
    "stakeholders": ["Prospect (People Ops Manager)"],
    "budget signal": null,
    "timeline signal": "no rush until Q1",
    "competitor mentioned": "Bucketlist",
    "next step": "schedule a call with CEO",
    "objections": ["CEO has to be sold first — she decides anything people-related"],
    "confidence": "medium"
  },
  {
    "transcript_id": "TX-004",
    "deal_alias": "Deal-180D02",
    "why-buys": [
      "consolidate three separate recognition tools into one",
      "paying for three tools and none of them talk to our HRIS"
    ],
    "pain points": [
      "consolidating three separate recognition tools",
      "three tools not talking to HRIS",
      "procurement cycle runs six to eight weeks minimum",
      "security review took three months for our last vendor"
    ],
    "stakeholders": ["Prospect (VP People)", "Prospect (IT Security Lead)"],
    "budget signal": 15000,
    "timeline signal": null,
    "competitor mentioned": null,
    "next step": null,
    "objections": [
      "procurement cycle runs six to eight weeks minimum",
      "security review took three months for our last vendor"
    ],
    "confidence": "medium"
  },
  {
    "transcript_id": "TX-005",
    "deal_alias": "Deal-F8767A",
    "why-buys": [
      "automate service milestones",
      "give us analytics on recognition equity across departments",
      "our night-shift teams feel invisible — their engagement scores run 20 points lower"
    ],
    "pain points": [
      "automating service milestones",
      "recognition equity analytics across departments",
      "night-shift teams feel invisible with 20-point lower engagement scores",
      "mid-pilot with Nectar right now",
      "exec team skeptical after a failed rollout two years ago"
    ],
    "stakeholders": ["Prospect (HR Director)", "Prospect (People Ops Coordinator)"],
    "budget signal": 12000,
    "timeline signal": "before our January all-hands",
    "competitor mentioned": "Nectar",
    "next step": "present to exec team on October 2",
    "objections": [
      "mid-pilot with Nectar right now",
      "exec team skeptical after a failed rollout two years ago"
    ],
    "confidence": "high"
  },
  {
    "transcript_id": "TX-006",
    "deal_alias": "Deal-EE195F",
    "why-buys": [
      "cut the admin time on service awards",
      "personally spend five hours a month ordering and shipping plaques"
    ],
    "pain points": [
      "admin time on service awards (five hours/month ordering and shipping plaques)",
      "COO usually prefers building things in-house"
    ],
    "stakeholders": ["Prospect (HR Manager)"],
    "budget signal": null,
    "timeline signal": "Q1 start is realistic",
    "competitor mentioned": null,
    "next step": "send one-page overview to COO this week",
    "objections": ["COO usually prefers building things in-house"],
    "confidence": "medium"
  }
]
```
next-to-close0.75
Plain-English question: Which 3 deals are closest to signature right now?
Prompt — what the model saw
Which 3 deals are closest to signature right now? Use the CRM data and the Slack thread; Slack often has the real status before the CRM does. For each: deal, amount, why it is close, what is left. Under 250 words.
cost $0.0005 · 3s · in 1,582 / out 108 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
- Deal-547B2B ($11,200, DS5/COMMIT): redlines clean, signing page out, VP People says signing tomorrow. Left: signature.
- Deal-403845 ($9,000, DS5/COMMIT): order form with finance. Left: finance approval.
- Deal-D348E1 ($13,770, DS5/COMMIT): warm, legal review in progress. Left: legal approval.
product-gap-detection0.50
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 $0.0004 · 3s · in 813 / out 39 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
Deal-D0D6B5 (ADP Workforce Now integration missing): real gap
Deal-EC3025 (SCIM user provisioning missing): real gap
rep-performance 5 tests
stale-pipeline-by-rep0.17
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 $0.0076 · 15s · in 43,559 / out 1,767 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
Deal alias: Deal-25F752
Owner name: Bryce Harmon
Stage: DS4
Amount: 24000
Days since last contact: 5

Deal alias: Deal-E53952
Owner name: Bryce Harmon
Stage: DS4
Amount: 19656
Days since last contact: 5

Deal alias: Deal-5408B0
Owner name: Dana Mercer
Stage: DS4
Amount: 14850
Days since last contact: 5

Deal alias: Deal-9AAE5F
Owner name: Dana Mercer
Stage: DS4
Amount: 11250
Days since last contact: 3

Deal alias: Deal-944310
Owner name: Dana Mercer
Stage: DS4
Amount: 10500
Days since last contact: 4

Deal alias: Deal-6787C2
Owner name: Bryce Harmon
Stage: DS4
Amount: 7000
Days since last contact: 3

Deal alias: Deal-62D607
Owner name: Dana Mercer
Stage: DS4
Amount: 4800
Days since last contact: 4

Deal alias: Deal-584EE5
Owner name: Dana Mercer
Stage: DS5
Amount: 4600
Days since last contact: 5

Deal alias: Deal-C6D97A
Owner name: Alex Franklin
Stage: DS4
Amount: 3240
Days since last contact: 8

Deal alias: Deal-7B3B0F
Owner name: Dana Mercer
Stage: DS4
Amount: 2760
Days since last contact: 4

Deal alias: Deal-403845
Owner name: Alex Franklin
Stage: DS5
Amount: 9000
Days since last contact: 3

Deal alias: Deal-B7EBD1
Owner name: Dana Mercer
Stage: DS5
Amount: 9000
Days since last contact: 17

Deal alias: Deal-3974EB
Owner name: Dana Mercer
Stage: DS4
Amount: 9000
Days since last contact: 9

Deal alias: Deal-523604
Owner name: Bryce Harmon
Stage: DS1
Amount: 13680
Days since last contact: 2

Deal alias: Deal-C9C286
Owner name: Bryce Harmon
Stage: DS2
Amount: 5502
Days since last contact: 9

Deal alias: Deal-CA7DC0
Owner name: Bryce Harmon
Stage: DS2
Amount: 8160
Days since last contact: 3

Deal alias: Deal-483B2D
Owner name: Bryce Harmon
Stage: DS1
Amount: 1
Days since last contact: 3

Deal alias: Deal-F0EBBB
Owner name: Bryce Harmon
Stage: DS3
Amount: 11400
Days since last contact: 25

Deal alias: Deal-3795AD
Owner name: Bryce Harmon
Stage: DS2
Amount: 1
Days since last contact: 9

Deal alias: Deal-332637
Owner name: Bryce Harmon
Stage: DS2
Amount: 36000
Days since last contact: 10

Deal alias: Deal-1BEEBF
Owner name: Bryce Harmon
Stage: DS1
Amount: 31500
Days since last contact: 20

Deal alias: Deal-E25A09
Owner name: Bryce Harmon
Stage: DS1
Amount: 6000
Days since last contact: 10

Deal alias: Deal-FC22A3
Owner name: Bryce Harmon
Stage: DS3
Amount: 10800
Days since last contact: 7

Deal alias: Deal-036E80
Owner name: Bryce Harmon
Stage: DS1
Amount: 30275
Days since last contact: 2

Deal alias: Deal-BB8880
Owner name: Bryce Harmon
Stage: DS1
Amount: 17400
Days since last contact: 3

Deal alias: Deal-01E193
Owner name: Bryce Harmon
Stage: DS1
Amount: 12600
Days since last contact: 9

Deal alias: Deal-C1FA6D
Owner name: Bryce Harmon
Stage: DS1
Amount: 18000
Days since last contact: 17

Deal alias: Deal-7BBDFA
Owner name: Bryce Harmon
Stage: DS3
Amount: 37440
Days since last contact: 47

Deal alias: Deal-A62B1D
Owner name: Bryce Harmon
Stage: DS2
Amount: 18828
Days since last contact: 4

Deal alias: Deal-93C8BF
Owner name: Bryce Harmon
Stage: DS2
Amount: 36000
Days since last contact: 4

Deal alias: Deal-1CCE5C
Owner name: Bryce Harmon
Stage: DS3
Amount: 20880
Days since last contact: 6

Deal alias: Deal-A414F6
Owner name: Bryce Harmon
Stage: DS1
Amount: 25200
Days since last contact: 20

Deal alias: Deal-D9A72E
Owner name: Alex Franklin
Stage: DS3
Amount: 18000
Days since last contact: 4

Deal alias: Deal-D9A12F
Owner name: Alex Franklin
Stage: DS3
Amount: 17000
Days since last contact: 3

Deal alias: Deal-C2FF3C
Owner name: Alex Franklin
Stage: DS1
Amount: 8316
Days since last contact: 15

Deal alias: Deal-4F775F
Owner name: Alex Franklin
Stage: DS3
Amount: 18000
Days since last contact: 3

Deal alias: Deal-898FC5
Owner name: Alex Franklin
Stage: DS3
Amount: 12600
Days since last contact: 4

Deal alias: Deal-CC08D1
Owner name: Alex Franklin
Stage: DS1
Amount: 24000
Days since last contact: 4

Deal alias: Deal-792D44
Owner name: Alex Franklin
Stage: DS3
Amount: 15000
Days since last contact: 5

Deal alias: Deal-293AF3
Owner name: Alex Franklin
Stage: DS3
Amount: 9000
Days since last contact: 5

Deal alias: Deal-D8ABF7
Owner name: Alex Franklin
Stage: DS1
Amount: 7200
Days since last contact: 5

Deal alias: Deal-E73427
Owner name: Alex Franklin
Stage: DS3
Amount: 18000
Days since last contact: 6

---
Bryce Harmon stale deals: 25
Bryce Harmon stale amount: 298,542

Dana Mercer stale deals: 8
Dana Mercer stale amount: 66,760

Alex Franklin stale deals: 13
Alex Franklin stale amount: 150,180
activity-mix-vs-outcome0.20
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 $0.0066 · 6s · in 43,562 / out 37 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
I need the engagements_by_deal_90d.csv file to compute the last-30-day totals of emails, calls, and meetings per rep. Please provide it.
ae-qtd-scorecard0.67
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 $0.0038 · 17s · in 12,993 / out 2,662 tok
✗ bookings✓ quota✓ attainment✗ new_expansion_split✓ top_loss_reason✓ coaching_obs

✓ Correct Answer (ground truth)

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

Model's actual answer

show the model's full answer
QTD Scorecard — Alex Franklin — as of 2026-09-05
(Quarter excludes closed-won dated before 2026-07-01)

Bookings vs Quota
- Bookings (closed-won in Q3): 24,000 + 40,000 + 20,000 + 35,000 + 21,000 + 12,000 + 11,000 + 6,500 + 4,500 = 174,000
- Quota: 200,000
- Attainment: 174,000 / 200,000 = 87.0 %

New vs Expansion Split
- New: 24,000 + 40,000 + 35,000 + 21,000 + 11,000 + 6,500 = 137,500 (79.0 %)
- Expansion: 20,000 + 12,000 + 4,500 = 36,500 (21.0 %)

Active Pipeline by Stage (open, 2026-09-05)
- DS1: 5400 + 7200 + 41000 + 8316 + 7200 + 24000 + 7000 + 24000 + 40000 + 16605 + 4400 + 1800 = 180,121
- DS2: 2520 + 3240 + 1400 + 5400 + 4400 + 7500 + 1800 + 12000 + 36000 + 18000 + 15000 + 62000 + 23800 + 2700 + 8100 + 15000 + 4680 + 7200 + 15000 = 237,540
- DS3: 1275 + 3060 + 9720 + 3600 + 528 + 18000 + 3120 + 3780 + 3840 + 4080 + 2880 + 2916 + 7200 + 5400 + 1600 + 18000 + 5400 + 1620 + 15000 + 32000 + 18000 + 2730 + 2700 + 9600 + 1968 + 10000 + 5400 + 9360 + 12600 + 1632 + 5100 + 31200 + 12150 + 30000 + 4800 + 16200 + 16700 + 18000 = 247,881
- DS4: 1920 + 2484 + 3240 + 1080 = 8,724
- DS5: 9000 + 11200 + 6360 = 26,560
- Total: 800,826

Rolling 90-Day DS2-to-Won Rate
- DS2 deals entered DS2 in last 90 days (2026-06-07 → 2026-09-05): Deal-F436DA (2520), Deal-6A544F (3240), Deal-9D0060 (3840), Deal-DD7659 (4080), Deal-FA053A (2880), Deal-001FF4 (2916), Deal-5D8CEE (7200), Deal-DBF65A (5400), Deal-7FA0C3 (1400), Deal-600CD9 (5400), Deal-D1E6C2 (4400), Deal-9F2E43 (7690), Deal-ED725A (2400), Deal-F5A622 (1080), Deal-15D24F (3600), Deal-293AF3 (9000), Deal-47AE31 (3600), Deal-C61CF7 (5400), Deal-D9E112 (4300), Deal-ED13B0 (1680), Deal-766C74 (3300), Deal-034D49 (9000), Deal-4062CF (10800), Deal-48B656 (5160), Deal-5AD94B (4000), Deal-6691E0 (5700), Deal-712010 (7200), Deal-901332 (3600), Deal-A92065 (5400), Deal-D348E1 (13770), Deal-D7E999 (1800), Deal-D9A12F (17000), Deal-E0ADD8 (7920), Deal-E531A6 (4800), Deal-5913B3 (7500), Deal-635B8E (2600), Deal-A4C1CB (6480), Deal-DCA846 (7200), Deal-EC93DA (7500), Deal-F0F288 (12000), Deal-98FCB6 (18036), Deal-60C2C2 (19000), Deal-723297 (5760), Deal-7D1566 (20000), Deal-000AB9 (4800), Deal-317E6F (5400), Deal-3BA5EA (7200), Deal-4B0BEB (12000), Deal-50D386 (36000), Deal-5BFE3B (18000), Deal-7436E2 (7000), Deal-CC08D1 (24000), Deal-D0D6B5 (23800), Deal-F67D31 (1800), Deal-6883F3 (2400), Deal-87CE1C (1500), Deal-BE3D9D (1620), Deal-425E2A (40000), Deal-4A13AD (2160), Deal-792D44 (15000), Deal-BA571A (1080), Deal-CFE7F4 (32000), Deal-D9A72E (18000), Deal-CA5E44 (8100), Deal-42F601 (2730), Deal-D8ABF7 (7200), Deal-278DEC (2700), Deal-57F4C2 (15000), Deal-D0662E (41000), Deal-C2FF3C (8316), Deal-CE79B6 (9600), Deal-0D0211 (1968), Deal-40FFDE (16800), Deal-5296C9 (10000), Deal-B1AB47 (5400), Deal-F8767A (9360), Deal-5408B0 (14850), Deal-819506 (4400), Deal-885F45 (9300), Deal-CC50C1 (16605), Deal-898FC5 (12600), Deal-D0BC96 (1632), Deal-0D2F7A (5100), Deal-3EED2C (7200), Deal-530B50 (31200), Deal-690476 (3600), Deal-71590D (6000), Deal-84DBA6 (16000), Deal-9DA22E (1800), Deal-37255F (12150), Deal-70BB30 (30000), Deal-60C75F (40000), Deal-6C60D4 (4800), Deal-EC3025 (62000), Deal-E0B692 (16200), Deal-05CBC9 (2700), Deal-87C1AC (20000), Deal-1E2498 (16700), Deal-CF6F3B (3600), Deal-E73427 (18000), Deal-EDC141 (18000), Deal-92D97D (60000), Deal-13FEBD (4680), Deal-A181B3 (7200), Deal-36C33F (15000) = 702,671
- Won from above DS2 list: Deal-F2C7D8 (20,000), Deal-A8B4D6 (12,000), Deal-C5D9E2 (4,500) = 36,500
- DS2-to-Won rate: 36,500 / 702,671 = 5.2 %

Win/Loss Summary (Q3 only)
- Wins: 9
- Losses: 28
- Top loss reason: Lost- Timing (1 year or more) — 13 occurrences

Activity Volume (last 30 days)
- Emails: 520
- Calls: 108
- Meetings: 131
- Notes: 72

Coaching Observations
1. Pipeline coverage at 4.0x quota is healthy, but DS2-to-won conversion is weak (5.2 %). Focus on advancing DS2 deals to DS3/4 and shorten sales cycles.
2. Win rate on expansion deals is strong (3/9 = 33 %), yet new-logo attainment lags (87 % of quota). Prioritize new-logo discovery and early-stage qualification.
3. Activity volume is high, yet loss reasons skew to “timing” and “MIA.” Implement a 30-day re-engagement cadence for stalled deals and require documented next steps at every stage gate.
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 $0.0037 · 10s · in 18,752 / out 1,439 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
Deal-EC3025
- Amount: not provided
- Stage: not provided
- Active contacts: 1 (CT-047C54, champion)
- Personas present: champion
- Personas missing: economic buyer, HR admin, IT security, finance
- Most valuable persona to add: economic buyer
- Unengaged contact on file: CT-6827DB (Chief People Officer, economic buyer)

Deal-92D97D
- Amount: not provided
- Stage: not provided
- Active contacts: 2 (CT-01F5B4 HR admin, CT-A902AE champion)
- Personas present: HR admin, champion
- Personas missing: economic buyer, IT security, finance
- Most valuable persona to add: economic buyer
- Unengaged contact on file: none

Deal-50D386
- Amount: not provided
- Stage: not provided
- Active contacts: 2 (CT-AA41B2 champion, CT-B9C35B HR admin)
- Personas present: champion, HR admin
- Personas missing: economic buyer, IT security, finance
- Most valuable persona to add: economic buyer
- Unengaged contact on file: CT-A1C4B3 (Chief People Officer, economic buyer)

Deal-D0D6B5
- Amount: not provided
- Stage: not provided
- Active contacts: 3 (CT-87CED4 champion, CT-DE6D7C champion, CT-FD70B2 champion)
- Personas present: champion
- Personas missing: economic buyer, HR admin, IT security, finance
- Most valuable persona to add: economic buyer
- Unengaged contact on file: CT-1FA4DB (Chief People Officer, economic buyer)

Deal-5BFE3B
- Amount: not provided
- Stage: not provided
- Active contacts: 2 (CT-57123B champion, CT-5CE757 champion)
- Personas present: champion
- Personas missing: economic buyer, HR admin, IT security, finance
- Most valuable persona to add: economic buyer
- Unengaged contact on file: none

Deal-84DBA6
- Amount: not provided
- Stage: not provided
- Active contacts: 3 (CT-BAA9D3 economic buyer, CT-60834D champion, CT-3F23A4 IT security)
- Personas present: economic buyer, champion, IT security
- Personas missing: HR admin, finance
- Most valuable persona to add: finance
- Unengaged contact on file: CT-2A0169 (Controller, finance)

Deal-36C33F
- Amount: not provided
- Stage: not provided
- Active contacts: 1 (CT-4FE556 IT security)
- Personas present: IT security
- Personas missing: economic buyer, champion, HR admin, finance
- Most valuable persona to add: economic buyer
- Unengaged contact on file: CT-1DB73E (Chief People Officer, economic buyer)

Deal-4B0BEB
- Amount: not provided
- Stage: not provided
- Active contacts: 4 (CT-A96531 champion, CT-DE5BDC economic buyer, CT-1543C8 HR admin, CT-3E135F finance)
- Personas present: champion, economic buyer, HR admin, finance
- Personas missing: IT security
- Most valuable persona to add: IT security
- Unengaged contact on file: none

Deal-885F45
- Amount: not provided
- Stage: not provided
- Active contacts: 2 (CT-51C81E economic buyer, CT-D9A0E8 champion)
- Personas present: economic buyer, champion
- Personas missing: HR admin, IT security, finance
- Most valuable persona to add: HR admin
- Unengaged contact on file: CT-B3F25D (IT Security Lead, IT security)

Deal-FCBE5B
- Amount: not provided
- Stage: not provided
- Active contacts: 1 (CT-4A5317 champion)
- Personas present: champion
- Personas missing: economic buyer, HR admin, IT security, finance
- Most valuable persona to add: economic buyer
- Unengaged contact on file: none

Deal-5408B0
- Amount: not provided
- Stage: not provided
- Active contacts: 2 (CT-D33AE4 champion, CT-8742FD HR admin)
- Personas present: champion, HR admin
- Personas missing: economic buyer, IT security, finance
- Most valuable persona to add: economic buyer
- Unengaged contact on file: CT-07FA76 (Chief People Officer, economic buyer)

Deal-D348E1
- Amount: not provided
- Stage: not provided
- Active contacts: 5 (CT-4EA0A4 champion, CT-2164AD economic buyer, CT-EC404C IT security, CT-08E5FA finance, CT-BEDF5E HR admin)
- Personas present: champion, economic buyer, IT security, finance, HR admin
- Personas missing: none
- Most valuable persona to add: none required
- Unengaged contact on file: CT-8E04F5 (HRIS Manager, HR admin)

Deal-C6D97A
- Amount: not provided
- Stage: not provided
- Active contacts: 3 (CT-223DDC champion, CT-B03555 champion, CT-4E8A2B champion)
- Personas present: champion
- Personas missing: economic buyer, HR admin, IT security, finance
- Most valuable persona to add: economic buyer
- Unengaged contact on file: none

Deal-F9A08A
- Amount: not provided
- Stage: not provided
- Active contacts: 2 (CT-931B10 champion, CT-913581 economic buyer)
- Personas present: champion, economic buyer
- Personas missing: HR admin, IT security, finance
- Most valuable persona to add: HR admin
- Unengaged contact on file: CT-697541 (Chief People Officer, economic buyer)
talk-track-from-transcripts0.80
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 $0.0031 · 5s · in 19,592 / out 276 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
- First five minutes lead: "Quick one to kick off: a 400-person retailer we work with cut regretted turnover 18% in two quarters after automating milestone awards, and I wanted to walk you through exactly how they did it."

- Objection handling:
  - Budget locked: "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."
  - Next quarter revisit: "Makes sense. What if we scope a 90-day pilot with one department so you have internal data before next quarter's planning?"
  - Spreadsheet recognition: "Spreadsheets work until they scale — the difference is automation: milestones fire without HR lifting a finger, and you get analytics on who is being recognized."

- Concrete next step rate: 70% (7/10 calls)

- Competitors raised:
  - Awardco
  - Kudos
  - Workhuman

Coaching notes:
- Standardize the lead to include the specific metric and outcome ("400-person retailer cut regretted turnover 18% in two quarters") to improve clarity and memorability.
- When handling budget objections, immediately pivot to funding mechanisms (e.g., turnover savings) to keep momentum.
reporting-analytics 5 tests
q3-weighted-forecast0.40
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 $0.0033 · 7s · in 20,612 / out 323 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
COMMIT total: 46,999
BEST_CASE total: 201,357
Weighted forecast: 46,999 + (0.35 * 201,357) = 46,999 + 70,474.95 = 117,473.95

Count of deals inside the quarter:
- COMMIT: 5
- BEST_CASE: 24

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

Deals excluded for being outside the quarter:
- Count: 23
- Total amount: 286,198.4

## Data quality
- Missing owner on most deals, making accountability unclear.
- PIPELINE deals included in extract despite instruction to exclude them from forecast.
- Why_buys_chars populated on some deals but not consistently; no mapping to revenue drivers.
- Close dates on excluded deals extend beyond 2026-10-15, indicating the date filter was not applied.
aha-moment-2x20.33
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 $0.0118 · 83s · in 36,211 / out 8,567 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
2x2 Cohort Table:
both_signals: cohort_size=36, retention_rate=0.694
givers_only: cohort_size=34, retention_rate=0.441
redemption_only: cohort_size=17, retention_rate=0.412
neither: cohort_size=56, retention_rate=0.429

Companies excluded from denominator: 0

Single signal with largest retention lift: givers_only (lift=-0.253, rate=0.441)

What this does and does not prove:
- DOES: Show correlation between early activation signals and 24-month retention
- DOES NOT: Prove causation; other confounding factors may exist
- DOES NOT: Establish these signals as the sole or primary drivers of retention
arr-rollforward-reconciliation0.20
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 $0.0008 · 5s · in 2,083 / out 366 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
Billing ARR total = 169,456.80
CRM ARR total = 172,456.80
Variance = -3,000.00 (CRM higher)

Decomposition:
- status mismatch: -3,000.00
- rounding: 0.00
- missing records: 0.00
- other: 0.00

Mismatched accounts (CRM > Billing):
- C-0C8323BF: CRM 4,905.24 vs Billing 0 (cancelled subscription)
- C-0DC4FB8C: CRM 8,253.24 vs Billing 0 (cancelled subscription)

Suggested owners:
- C-0C8323BF: RevOps Ops
- C-0DC4FB8C: RevOps Ops

Agreement end date violations:
- SUB-0002 (C-1794A52C): term_months=24, cf_agreement_end_date missing
- SUB-000C (C-0DB48281): term_months=24, cf_agreement_end_date present (2027-11-30)
- SUB-0019 (C-22170CA1): term_months=36, cf_agreement_end_date missing
- SUB-001A (C-0FC4DBB8): term_months=36, cf_agreement_end_date present (2027-11-30)
kvm-month-over-month0.40
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 $0.0031 · 5s · in 19,652 / out 247 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
KVMs 2026-08 vs 2026-07

| KVM | 2026-07 | 2026-08 | Abs Δ | Rel Δ | Dir |
|---|---|---|---|---|---|
| giving_rate | 0.6019 | 0.6022 | +0.0003 | +0.05% | ↑ |
| redemptions_per_user | 1.7317 | 1.7320 | +0.0003 | +0.02% | ↑ |
| one_to_one_engagement | 0.4498 | 0.4501 | +0.0003 | +0.07% | ↑ |
| pulse_engagement | 0.5993 | 0.5089 | -0.0904 | -15.08% | ↓ |

Largest relative move: pulse_engagement (-15.08%). Data does not support segment attribution.
rewards-ytd-section0.50
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 $0.0037 · 4s · in 22,047 / out 182 tok
✗ count✗ spend✗ unique_redeemers✓ month_named✓ provider_mix✓ top_country

✓ Correct Answer (ground truth)

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

Model's actual answer

show the model's full answer
Last completed month: 2026-08

Redemption count: 43
Spend: $8,076.00
Unique redeemers: 36
Redemptions per redeemer: 1.19

Provider mix as percent of spend:
- Tremendous: 55.7% ($4,499.00)
- TangoCard: 33.6% ($2,714.00)
- custom: 10.6% ($853.00)
- Snappy: 0.1% ($10.00)

Top 5 countries by redemptions:
1. US: 29
2. CA: 5
3. GB: 3
4. AU: 2
5. CH: 2
customer-success 5 tests
churn-save-eligibility0.80
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 $0.0032 · 7s · in 18,068 / out 778 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
Qualifying at-risk accounts (meet R1, R2, R3):

- C-0F6C0F34: $49,707 at stake; play = usage revival; signal = usage_trend_3m = growing
- C-0B827671: $25,365; play = executive touch; signal = usage_trend_3m = declining
- C-0B360C78: $35,748; play = executive touch; signal = usage_trend_3m = growing
- C-0B0F1BAB: $5,494; play = usage revival; signal = usage_trend_3m = flat
- C-0CA21961: $16,829; play = usage revival; signal = usage_trend_3m = flat
- C-0E9C27D1: $41,235; play = usage revival; signal = usage_trend_3m = flat
- C-0CEF69FD: $32,621; play = usage revival; signal = usage_trend_3m = growing
- C-0D3278C7: $17,602; play = executive touch; signal = usage_trend_3m = declining
- C-0BA71F12: $6,824; play = commercial concession; signal = usage_trend_3m = declining
- C-0F876796: $19,958; play = commercial concession; signal = usage_trend_3m = declining

Total at stake: $251,403

---

At-risk but do not qualify:

- C-0BC71BDD: churn_save_eligible_amount = 0
- C-0BE96399: churn_save_eligible_amount = 0
- C-0FCCD2DF: churn_save_eligible_amount = 0
- C-10A56B0F: churn_save_eligible_amount = 0
- C-8C2E8F00: renewal_date outside 120 days of 2026-09-05
- C-0B843542: renewal_date outside 120 days of 2026-09-05
- C-14264ABD: health_score ≥ 60
- C-0B2895EF: health_score ≥ 60
- C-0EE1203E: health_score ≥ 60
- C-0FC7A215: health_score ≥ 60
- C-0D035262: health_score ≥ 60
- C-0D6CC8E3: health_score ≥ 60
- C-0B2213A9: health_score ≥ 60
- C-0D0B047C: health_score ≥ 60
- C-21FEBCBB: health_score ≥ 60
- C-172EEFBC: health_score ≥ 60
- C-0C3848D2: health_score ≥ 60
- C-0D890324: health_score ≥ 60
- C-0AAA9434: health_score ≥ 60
expansion-kit0.83
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 $0.0027 · 5s · in 16,792 / out 336 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
Seat coverage: 150 licensed / 400 headcount = 37.5%.

Usage health:
- Monthly active users climbed from 88 (Mar 2026) to 126 (Aug 2026) = +43% growth.
- Current licensed seats (150) are below peak usage (126 ≤ 150), indicating healthy headroom.

Headroom:
- Seats: 150 licensed – 126 active = 24 seats available.
- ARR at current per-seat rate: 24 seats × ($9,000 / 150) = $1,440 expansion ARR.

Who replied: Maria S., People Operations Coordinator; cannot buy.

Right buyer: Dana R., VP People (last engaged 2026-05-18).

Reply email (149 words):
---
Subject: Intro to Dana R. on Bonusly usage & expansion

Hi Maria,

Thanks for the note and the kind words about Bonusly. I see the team’s monthly active users grew from 88 in March to 126 in August—that’s a great signal of adoption.

I’d love to connect Dana R. with our team to discuss how Bonusly can scale alongside your growth. We have 24 seats available under your current license and could add them at the same per-seat rate ($60/seat/month), adding $1,440 ARR if needed. Let me know if an intro would be helpful.

Best,
Cole
---
onboarding-status0.75
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 $0.0027 · 4s · in 16,868 / out 234 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
Complete:
- Integrations connected: Slack (2026-08-12)
- Allowance set: 2026-08-13
- Admins added: 2 (2026-08-13)
- First recognition given: 2026-08-15 14:22

Not complete:
- First redemption: missing

Early engagement signals:
- Active givers grew from 3 (2026-08-11) to 15 (2026-09-04), +12 over 24 days.
- 7-day rolling average active givers on 2026-09-04: (15+13+11+13+15+15+13)/7 = 95/7 = 13.6

Three things to cover on the call:
1. Confirm first redemption date.
2. Review allowance configuration and admin roles.
3. Discuss engagement growth and next steps for scaling recognition.
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 $0.0025 · 13s · in 6,781 / out 1,983 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 (trusting Chargebee for multi-year; ChurnZero otherwise)

Disagreements
- C-0BCDB8C2: ChurnZero shows 2027-09-18; Chargebee shows 2026-09-18. Trust Chargebee (term_months=36, is_multi_year=true) → renewal date 2026-09-18.
- C-0BBE3E60: ChurnZero shows 2027-09-26; Chargebee shows 2026-09-26. Trust Chargebee (term_months=24, is_multi_year=true) → renewal date 2026-09-26.
- C-0F5D2323: ChurnZero shows 2026-09-10; Chargebee shows 2026-09-29. Trust Chargebee (term_months=24, is_multi_year=true) → renewal date 2026-09-29.

Renewals (next 90 days)

| Company | CSM | ARR | Date | Seats | Util% | 3-mo trend | Risk | Evidence |
|---|---|---|---|---|---|---|---|---|
| C-0B7D2C30 | Dana Mercer | 65,901 | 2026-09-15 | 476 | 57.6% | ↓11.3% | MEDIUM | Usage fell from 110 to 84 (-23.6%) over 12 months; seats used 274 vs 476. |
| C-0D2AB865 | Elena Sinclair | 38,022 | 2026-09-22 | 407 | 61.4% | ↓12.7% | MEDIUM | Usage fell from 144 to 109 (-24.3%) over 12 months; seats used 250 vs 407. |
| C-0F5D2323 | Cole Ingram | 90,647 | 2026-09-29 | 390 | 28.5% | ↓14.3% | HIGH | Usage flat-to-down (18→18); seats used 111 vs 390; low utilization. |
| C-0EC6999D | Elena Sinclair | 79,419 | 2026-10-03 | 112 | 27.7% | ↓12.5% | HIGH | Usage fell from 17 to 15 (-11.8%) over 12 months; seats used 31 vs 112. |
| C-0B20DB64 | Dana Mercer | 21,770 | 2026-10-07 | 378 | 56.6% | ↓0.3% | LOW | Usage flat (294→294); seats used 214 vs 378; stable usage. |
| C-0BBC4E7A | Cole Ingram | 56,374 | 2026-10-10 | 337 | 67.7% | ↓1.4% | LOW | Usage flat (142→139); seats used 228 vs 337; stable usage. |
| C-0FD551AB | Elena Sinclair | 48,815 | 2026-10-14 | 376 | 55.9% | ↑2.4% | LOW | Usage up from 122 to 126 (+3.3%) over 12 months; seats used 210 vs 376. |
| C-0F9F8F13 | Dana Mercer | 46,230 | 2026-10-18 | 352 | 56.5% | ↓0.5% | LOW | Usage flat (185→182); seats used 199 vs 352; stable usage. |
| C-0BC34584 | Cole Ingram | 16,740 | 2026-10-22 | 494 | 66.2% | ↑2.9% | LOW | Usage up from 104 to 106 (+1.9%) over 12 months; seats used 327 vs 494. |
| C-0B7A7546 | Elena Sinclair | 35,062 | 2026-10-25 | 205 | 88.8% | ↑5.2% | LOW | Usage up from 60 to 63 (+5.0%) over 12 months; seats used 182 vs 205; near-full utilization. |
| C-0B369871 | Dana Mercer | 85,128 | 2026-10-29 | 422 | 75.1% | ↑10.9% | LOW | Usage up from 300 to 333 (+11.0%) over 12 months; seats used 317 vs 422. |
| C-0B144C78 | Cole Ingram | 30,899 | 2026-11-02 | 224 | 75.4% | ↑11.6% | LOW | Usage up from 95 to 106 (+11.6%) over 12 months; seats used 169 vs 224. |
| C-0FC4DBB8 | Elena Sinclair | 94,732 | 2026-11-05 | 464 | 76.7% | ↑14.9% | LOW | Usage up from 176 to 193 (+9.7%) over 12 months; seats used 356 vs 464. |
| C-0D5BBE3A | Dana Mercer | 39,740 | 2026-11-09 | 102 | 83.3% | ↑19.7% | LOW | Usage up from 79 to 91 (+15.2%) over 12 months; seats used 85 vs 102; near-full utilization. |
| C-0FB9D5AF | Cole Ingram | 63,158 | 2026-11-13 | 199 | 72.4% | ↑13.6% | LOW | Usage up from 157 to 176 (+12.1%) over 12 months; seats used 144 vs 199. |
| C-0B344485 | Elena Sinclair | 64,384 | 2026-11-16 | 287 | 78.0% | ↑12.8% | LOW | Usage up from 218 to 244 (+12.0%) over 12 months; seats used 224 vs 287. |
| C-0CB2C1B4 | Dana Mercer | 40,628 | 2026-11-20 | 473 | 81.6% | ↑8.9% | LOW | Usage up from 45 to 49 (+8.9%) over 12 months; seats used 386 vs 473. |
| C-22170CA1 | Cole Ingram | 45,646 | 2026-11-24 | 294 | 85.4% | ↑12.3% | LOW | Usage up from 134 to 146 (+9.0%) over 12 months; seats used 251 vs 294. |

Totals
- ARR renewing: 966,663
- ARR at risk: 154,068
ticket-theme-synthesis0.60
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 $0.0036 · 7s · in 21,444 / out 647 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
Theme: Slack sync failures
- Count: 18
- Share: 22.5%
- Distinct accounts: 6
- ARR affected: 199,400
- Ticket ids: IC-460047, IC-460049
- Recommendation: Prioritize Slack OAuth re-authentication and toggle persistence; schedule a maintenance window to reset and stabilize the integration.

---

Theme: Points not posting / balance not updating
- Count: 12
- Share: 15.0%
- Distinct accounts: 5
- ARR affected: 15,500
- Ticket ids: IC-460004, IC-460001
- Recommendation: Investigate async job queue backlog and duplicate event deduplication; add real-time balance update webhooks.

---

Theme: HRIS provisioning failures
- Count: 10
- Share: 12.5%
- Distinct accounts: 4
- ARR affected: 150,000
- Ticket ids: IC-460059, IC-460062
- Recommendation: Patch HRIS webhook handler for new-hire payload parsing; add dry-run mode and escalation SLA.

---
Theme: Billing seat-count discrepancies
- Count: 8
- Share: 10.0%
- Distinct accounts: 2
- ARR affected: 208,000
- Ticket ids: IC-460071, IC-460069
- Recommendation: Implement seat-usage delta alerts and require explicit seat-count approval before invoicing.

---
Theme: Redemption failures (gift cards)
- Count: 8
- Share: 10.0%
- Distinct accounts: 5
- ARR affected: 48,900
- Ticket ids: IC-460025, IC-460035
- Recommendation: Add idempotent redemption IDs and retry logic; surface failure reasons in UI.

---
Theme: Checkout spins / redemption failures
- Count: 7
- Share: 8.8%
- Distinct accounts: 3
- ARR affected: 30,300
- Ticket ids: IC-460025, IC-460030
- Recommendation: Instrument checkout latency and payment-gateway timeouts; add circuit breaker.

---
Theme: Invoice tier-pricing errors
- Count: 6
- Share: 7.5%
- Distinct accounts: 1
- ARR affected: 312,000
- Ticket ids: IC-460071, IC-460078
- Recommendation: Freeze annual renewals for C-0E9C27D1; implement tier-change pre-approval and price-lock guarantees.
marketing 5 tests
case-study-match0.75
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 $0.0026 · 3s · in 17,085 / out 121 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
Technology,Mid-Market,employee_recognition,NA-West

1) C-CD4829A7: Technology,Mid-Market,retention,NA-East
   - industry, size_band, use_case

2) C-64171065: Technology,Mid-Market,employee_recognition,NA-East
   - industry, size_band, use_case

3) C-A13C193D: Technology,Mid-Market,retention,NA-West
   - industry, size_band, region
channel-attribution-math0.80
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 $0.0012 · 5s · in 4,377 / out 489 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
Channel performance (trailing 6 months: 2026-03 through 2026-08)

Paid channels
channel       spend_usd   SQMs   SQOs   cost/SQM   cost/SQO   SQM→SQO rate   pipeline   pipeline/$   flag
paid_search   36000       23     10     1565.22    3600.00    43.48%         320000     8.89         –
linkedin_ads  24000       13     7      1846.15    3428.57    53.85%         72000      3.00         –
paid_social   18000       0      0      undefined  undefined  –              0          –            –
webinars      9000        0      0      undefined  undefined  –              0          –            –

Organic channels
channel        volume   SQO rate   pipeline
organic_search 23       21.74%     108000
referral       11       27.27%     40000

Notes
- cost/SQM = spend_usd / SQMs (undefined if SQMs = 0)
- cost/SQO = spend_usd / SQOs (undefined if SQOs = 0)
- SQM→SQO rate = SQOs / SQMs (excludes rows with missing SQM or SQO)
- pipeline/$ = pipeline / spend_usd (0 if spend_usd = 0)
- Flagged rows where SQO date precedes SQM date: none in this dataset

Reallocation recommendation
- Shift budget from paid_social and webinars (both undefined cost/SQM and zero SQOs) into paid_search and linkedin_ads, which show positive pipeline and measurable SQM→SQO rates.
- Confidence: low due to small sample sizes (≤23 SQMs per paid channel; ≤13 SQMs per organic channel).
competitor-battlecard-update0.60
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 $0.0029 · 5s · in 17,939 / out 349 tok
✓ competitor_named✓ pricing✓ win_loss✗ unverified_marked✗ citations

✓ Correct Answer (ground truth)

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

Model's actual answer

show the model's full answer
# Battlecard: Rivally

- Positioning: points-based recognition for mid-market and distributed EU teams. S12
- Pricing: $7 per user/month, annual billing required (as of 2026-08). S17,S18

Where they win:
- Strong for distributed EU teams with multi-language support. S12
- Engaging recognition feed and quick Slack integration. S04,S16
- EU data residency and Microsoft Teams app v2. S15,S19

Where we win:
- Deeper analytics and reporting dashboards. S07
- SCIM provisioning and bulk recognition editing. S10,S24
- Thicker rewards catalog in EMEA. S14

Objections and responses:
- Objection: Rivally's admin tooling lags peers.
  Response: Our admin console supports SCIM provisioning and bulk recognition editing, addressing common admin pain points. S10,S24
- Objection: Rivally's rewards catalog in EMEA is thinner.
  Response: Our catalog is stronger in EMEA, providing more localized reward options. S14

Recent changes:
- Pricing increased from $5 to $7 per user/month. S03,S08,S17
- Launched Rivally Pulse engagement survey add-on. S06,S23
- Opened Dublin office and announced EU data residency GA. S15
- Updated Microsoft Teams app to v2. S19

Our 12-month win/loss record against Rivally: 12 wins, 8 losses. S12
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 $0.0031 · 7s · in 16,516 / out 596 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
New Logo Nurture
- 1: sent 500, opened 210 (42%), replied 42 (20% of opened), meetings 12 (29% of replies)
- 2: sent 458, opened 160 (35%), replied 30 (19% of opened), meetings 9 (30% of replies)
- 3: sent 428, opened 120 (28%), replied 18 (15% of opened), meetings 6 (33% of replies)
Weakest: Step 3 (15% reply rate). Fix: shorten email body and add social proof.

Expansion Nurture
- 1: sent 300, opened 130 (43%), replied 22 (17% of opened), meetings 5 (23% of replies)
- 2: sent 300, opened 340 (113% opened>sent), replied 25 (7% of opened), meetings 4 (16% of replies)
- 3: sent 275, opened 95 (35%), replied 12 (13% of opened), meetings 3 (25% of replies)
Weakest: Step 2 (7% reply). Fix: remove duplicate contacts causing opened>sent. Failure mode: duplicate suppression broken.

Cold Outbound - HR Leaders
- 1: sent 600, opened 240 (40%), replied 5 (2% of opened), meetings 0
- 2: sent 595, opened 175 (29%), replied 2 (1% of opened), meetings 0
- 3: sent 590, opened 130 (22%), replied 1 (1% of opened), meetings 0
Weakest: all steps under 2% reply. Fix: replace generic messaging with role-specific pain points.

Cold Outbound - People Ops
- 1: sent 400, opened 150 (38%), replied 14 (9% of opened), meetings 3 (21% of replies)
- 2: sent 386, opened 110 (28%), replied 9 (8% of opened), meetings 2 (22% of replies)
- 3: sent 377, opened 80 (21%), replied 6 (8% of opened), meetings 1 (17% of replies)
Weakest: Step 3 (8% reply). Fix: add clear CTA.

Prioritize: Cold Outbound - HR Leaders first (all steps <2% reply).
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 $0.0004 · 4s · in 328 / out 243 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
QTD actual vs target (Q3-2026, 66 days elapsed):

- SQMs: 230 vs 300, delta -70, pace behind (77% of target).
- SQOs: 84 vs 120, delta -36, pace behind (70% of target).
- DS2s: 40 vs 75, delta -35, pace behind (53% of target).
- Closed-lost MIA rate: 5/25 = 0.20 vs 0.10 target, delta +0.10, pace behind (200% of target).
- Same-quarter closes: 10 vs 20, delta -10, pace behind (50% of target).
- Active pipeline: $3.0M vs $4.0M, delta -$1.0M, pace behind (75% of target).

This week: SQMs, SQOs, DS2s, same-quarter closes, and active pipeline all remain behind target with no new data to indicate a directional change.
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 $0.0026 · 4s · in 17,013 / out 83 tok
✓ max_3_sentences✓ under_80_words✓ weighted_present✗ caveat_present✓ no_em_dash

✓ Correct Answer (ground truth)

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

Model's actual answer

show the model's full answer
Q3 weighted forecast: 115,977. Excludes 32 late deals (227,575) including one COMMIT (Deal-D348E1, 13,770). Caveat: 85/86 deals lack owner and 71/86 lack why-buys, so forecast is unverified.
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 $0.0004 · 3s · in 473 / out 72 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: Follow-up on Deal-0D2F7A

Hi [Name],

Following up on the July 28 demo where you requested pricing for 150 seats. We emailed a recap with pricing on Aug 5 but haven’t heard back.

Could you share any updates on timing or next steps?

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 $0.0026 · 4s · in 16,602 / out 143 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 drove 46 SQMs (target 52) with webinars contributing 18 SQMs and paid search holding at 150 dollars per SQM.

Sales closed 14 SQOs, set 9 DS2 meetings, and generated 310000 dollars of new pipeline while closing 3 deals in the same quarter.

CS saved 2 renewals, lifted team NPS to 61, and carries 3 red-flag accounts into next week.

PLG onboarded 412 new signups at a 31 percent activation rate and saw 38 companies hit the 10-recognition-gives aha moment.
partner-digest-section0.67
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 $0.0005 · 4s · in 512 / out 215 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

Apex Rewards Co (active) — 2 sourced opps; $275,000 partner-sourced pipeline
HRCloud Partners (active) — 1 sourced opp; $140,000 partner-sourced pipeline
CultureBridge (active) — 2 sourced opps; $135,000 partner-sourced pipeline
WorkWell Group (active) — 0 sourced opps; $0 partner-sourced pipeline
Recogniq (quiet) — 0 sourced opps; $0 partner-sourced pipeline
KudosWave (quiet) — 0 sourced opps; $0 partner-sourced pipeline
PeopleFirst Advisors (quiet) — 0 sourced opps; $0 partner-sourced pipeline
TotalPerk (quiet) — 0 sourced opps; $0 partner-sourced pipeline
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 $0.0027 · 5s · in 16,790 / out 281 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, using AES-256. AES-256. [P1]
Q2: Yes, using TLS 1.2 or higher. TLS 1.2 or higher. [P1]
Q3: Yes, SOC 2 Type II renewed annually; available under NDA. SOC 2 Type II renewed annually; available under NDA. [P2]
Q4: Duration of the contract plus 90 days, then deleted. Duration of the contract plus 90 days, then deleted. [P3]
Q5: Published at trust.bonusly.com; 30 days notice before a new subprocessor is added. trust.bonusly.com; 30 days notice. [P4]
Q6: Yes, on the Enterprise plan. Yes, on the Enterprise plan. [P5]
Q7: Daily backups retained for 35 days. Daily backups retained for 35 days. [P6]
Q8: unanswerable; ISO 27001 not mentioned. Would require Trust portal or compliance page.
Q9: unanswerable; uptime SLA not mentioned. Would require SLA or MSA.
Q10: unanswerable; HIPAA BAA not mentioned. Would require HIPAA policy or BAA template.
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 $0.0130 · 9s · in 85,477 / out 357 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
CRITICAL · TRIM_DESC · **closed-lost-analysis** and **email-drafter**
- Duplicate ALWAYS-trigger phrases: "write me an email" and "draft a follow-up" appear in both skills' descriptions. Recommend merging or clarifying scope split.

---

WARNING · UPDATE_BODY · **deal-strategy-coach**
- Circular delegation chain: `deal-strategy-coach` → `prospect-research-multithreading` → (implicit) `deal-strategy-coach` via multithreading. Recommend breaking the loop by removing the implicit call or documenting the handoff explicitly.

---

WARNING · DELETE_SKILL · **model-selection**
- Dangling delegation target: `model-selection` references a non-existent skill `bonusly-brand` in its execution steps. Recommend removing the reference or replacing with an existing skill.

---

INFO · UPDATE_BODY · **stale-pipeline-report**
- Hardcoded page ID: `C0561C1JCPJ` (Slack channel ID) is hardcoded. Recommend parameterizing or documenting as a constant.

---

INFO · TRIM_DESC · **weekly-pipeline-report**
- Exceeds 1,024 characters: description is 1,055 characters. Recommend trimming to under 1,024.

---
INFO · DELETE_SKILL · **signalforge-feedback**
- Manifest row exists but no SKILL.md file found. Recommend removing the manifest row or creating the skill file.

---
INFO · DELETE_SKILL · **signalforge-claim-compressor**
- Manifest row exists but no SKILL.md file found. Recommend removing the manifest row or creating the skill file.
runbook-from-slack-thread0.75
Plain-English question: Turn the resolved incident thread into a runbook.
Prompt — what the model saw
Turn the resolved incident thread into a runbook: ordered steps with the exact command or action taken, who ran it, how success was verified, and rollback for each step that changed state. Every step must trace to a message in the thread. Add nothing the thread does not contain; where the thread is unclear, mark the step as needing confirmation.
cost $0.0006 · 5s · in 739 / out 442 tok
✓ ordered_steps✓ rollback✓ needs_confirmation✗ sourced

✓ Correct Answer (ground truth)

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

Model's actual answer

show the model's full answer
Runbook: reward-worker queue depth > 10k (#incident-2026-08-29-reward-queue)

1) Diagnose queue depth
   Action: `bundle exec rake sidekiq:queue_depth`
   Who: Farid Osman
   Success: reward queue at 48,213 pending (normal ≤ 500)
   Rollback: none — read-only diagnostic

2) Identify dead set
   Action: `bin/rails runner 'FeatureFlag.disable(:auto_recognition_enqueue)'`
   Who: Farid Osman
   Success: dead set had 112 Redis::TimeoutError jobs from ~13:58
   Rollback: `bin/rails runner 'FeatureFlag.enable(:auto_recognition_enqueue)'`

3) Clear dead set
   Action: manual clear via console (Elena Sinclair)
   Who: Elena Sinclair
   Success: dead set cleared (exact command not provided; step needs confirmation)
   Rollback: not specified

4) Scale workers up
   Action: `kubectl scale deployment/reward-worker --replicas=6` (was 3)
   Who: Bryce Harmon
   Success: queue depth down to 9,400 and falling ~1,200/min
   Rollback: `kubectl scale deployment/reward-worker --replicas=3`

5) Verify queue cleared
   Action: `bundle exec rake sidekiq:queue_depth`
   Who: Cole Ingram
   Success: queue depth 0; Datadog error rate back to baseline

6) Re-enable enqueue
   Action: `bin/rails runner 'FeatureFlag.enable(:auto_recognition_enqueue)'`
   Who: Bryce Harmon
   Success: 40 new jobs processed cleanly in next 3 minutes

7) Scale workers down
   Action: `kubectl scale deployment/reward-worker --replicas=3`
   Who: Bryce Harmon
   Success: queue stable at 0; incident resolved
datadog-incident-timelinePASS 1.00
Plain-English question: Sequence the failure from the logs — what broke first, and what cascaded after it?
Prompt — what the model saw
From the log slice, sequence the failure: first error with timestamp, the cascade in order, the service and job involved, and the Datadog query that would confirm the first error. State what the logs do not show.
cost $0.0012 · 7s · in 2,135 / out 1,011 tok
✓ first_error_ts✓ service_named✓ cascade_ordered✓ query✓ gaps_stated

✓ Correct Answer (ground truth)

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

Model's actual answer

show the model's full answer
First error with timestamp
2026-09-03T14:01:12Z

Cascade in order
1) 2026-09-03T14:01:12Z reward-service Redis::TimeoutError: Connection to Redis at redis-primary:6379 timed out after 5s
2) 2026-09-03T14:01:20Z reward-service Redis::TimeoutError: retry exhausted for RewardGiveJob
3) 2026-09-03T14:01:30Z reward-service Redis::TimeoutError: retry exhausted for RewardGiveJob
4) 2026-09-03T14:01:40Z reward-service Redis::TimeoutError: retry exhausted for RewardGiveJob
5) 2026-09-03T14:01:40Z sidekiq RewardGiveJob failed: Redis::TimeoutError; retrying in 60s
6) 2026-09-03T14:02:28Z sidekiq RewardGiveJob failed: Redis::TimeoutError; retrying
7) 2026-09-03T14:02:30Z sidekiq WARN Queue reward depth above 10,000
8) 2026-09-03T14:03:05Z api-gateway 502 upstream timeout calling reward-service /gives
9) 2026-09-03T14:03:30Z web-app Give form submission failed: upstream 502 from api-gateway
10) 2026-09-03T14:03:31Z sidekiq RewardGiveJob failed: Redis::TimeoutError; retrying
11) 2026-09-03T14:03:48Z api-gateway 502 upstream timeout calling reward-service
12) 2026-09-03T14:04:13Z api-gateway 502 upstream timeout calling reward-service
13) 2026-09-03T14:04:22Z sidekiq RewardGiveJob failed: Redis::TimeoutError; retrying
14) 2026-09-03T14:04:45Z web-app Give form submission failed: upstream 502
15) 2026-09-03T14:05:16Z api-gateway 502 upstream timeout calling reward-service
16) 2026-09-03T14:05:26Z sidekiq RewardGiveJob failed: Redis::TimeoutError; retrying
17) 2026-09-03T14:05:42Z web-app Give form submission failed: upstream 502
18) 2026-09-03T14:06:47Z sidekiq RewardGiveJob failed: Redis::TimeoutError; retrying
19) 2026-09-03T14:06:49Z web-app Give form submission failed: upstream 502
20) 2026-09-03T14:06:52Z api-gateway 502 upstream timeout calling reward-service
21) 2026-09-03T14:22:10Z reward-service Redis connection restored; resuming job processing

Service and job involved
reward-service, RewardGiveJob

Datadog query to confirm first error
@timestamp:2026-09-03T14:01:12Z AND @service:reward-service AND @message:"Redis::TimeoutError: Connection to Redis at redis-primary:6379 timed out after 5s"

Logs do not show
- Any error from redis-primary itself
- Any Redis CPU/memory metrics
- Any network connectivity checks or packet loss between reward-service and redis-primary
- Any sidekiq queue depth before 14:02:30Z
- Any application-level retry logic from web-app or api-gateway beyond the 502 responses
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 $0.0027 · 4s · in 16,838 / out 252 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
- recognition_streaks_v2 (on): Controls streak tracking for recognition. Enabled for 42 companies in segment beta_companies.
- points_budget_guardrails (on): Enforces points budget rules. Enabled for all 220 companies.
- slack_dm_nudges (on): Sends Slack DM nudges. Enabled for 87 companies in segment region_na.
- redeem_flow_redesign (off): Renders new redeem flow component. Targeted to 12 companies via targeted_list. Code reference present.
- analytics_dashboard_v3 (on): Uses AnalyticsV3 dashboard. Enabled for 65 companies in segment tier_three.
- ms_teams_app_v2 (off): Installs Teams app v2. Targeted to 9 companies via targeted_list. Code reference present.
- legacy_give_modal (off): No code reference found. Targeted to 14 companies in segment legacy_plan.
- survey_boosters_q3 (on): No code reference found. Enabled for 7 companies in segment legacy_plan.
- paused_offboard_cleanup (off): No code reference found. No targets (0 companies).
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 $0.0004 · 4s · in 534 / out 154 tok
✓ green✓ yellow✓ red✓ non_solicit_caught✓ clause_quoted✓ correct_labels

✓ Correct Answer (ground truth)

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

Model's actual answer

show the model's full answer
- NDA-1 — [PARTY A] and Bonusly: GREEN. No embedded non-solicit/non-compete; carve-outs are standard and complete; governing law is Delaware (neutral). No red flags.

- NDA-2 — [PARTY B] and Bonusly: YELLOW. Embedded non-solicit clause (18 months post-term) drives counsel review. Governing law is Delaware (neutral). Carve-outs are standard.

- NDA-3 — [PARTY C] and Bonusly: RED. One-way confidentiality, missing carve-outs, embedded non-compete (3 years), and governing law is Republic of Ireland (non-standard jurisdiction). Requires full legal review.