graded checks: avoids_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

Data gap — cannot write the requested query without inventing tables or columns.

The three requested metrics cannot be produced at the requested grain from this catalog:

1. Unique givers (per company, first calendar month)
- Requires a recognition/giving EVENTS table with GIVER_ID + COMPANY_ID + event timestamp.
- No such table exists in the catalog. The only giving-related figures are M1_GIVES in PRODUCTION.PLG.COMPANY_COHORT_SUMMARY, which is a pre-aggregated count, not distinct givers, and carries no giver identity. Missing — cannot compute.

2. Recognition count (per company, first calendar month)
- Same problem: no recognition-events table. COMPANY_COHORT_SUMMARY.M1_GIVES is already aggregated to "first month" but cannot be recomputed, cannot be keyed to an actual calendar-month window, and cannot honor the deleted-giver rule (see below). Not derivable from events — the events source is absent.

3. Successful redemption count (per company, first calendar month)
- PRODUCTION.DEPRECATED_RECOGNITION.REDEMPTION_RECORDS_V2 is named as the redemption source (STATE = 'succeeded' only), but the catalog lists NO columns for it — no COMPANY_ID, no giver key, no event date. Without documented columns I cannot join it to a company or bound it to a first calendar month. Missing columns — cannot compute.

Additional blocked dependency:
- "Exclude deleted givers must NOT be applied to historical giving counts": this rule presupposes a givers/giving-events table carrying a deleted flag. No such table is in the catalog, so there is nothing to (correctly) leave unfiltered. The rule cannot be honored because its target table is absent.
- "First calendar month as a customer" needs a customer-start date. Candidates exist (COMPANY_COHORT_SUMMARY.FIRST_SUB_PAYMENT_DATE / SIGNUP_DATE; CHARGEBEE.SUBSCRIPTIONS.CURRENT_TERM_START), but they cannot be joined to a recognition-events table that does not exist.

What would be needed to write a correct query (none present in this excerpt):
- A recognition/giving events table: one row per give, with giver id, company id, event timestamp, and the deleted-giver flag.
- The column list for REDEMPTION_RECORDS_V2: at minimum COMPANY_ID, an event/redemption timestamp, and STATE.
- A confirmed customer-start date field to define the first calendar month.

I am not emitting SQL, because any query returning these three columns at the requested grain would require fabricating at least one table name and REDEMPTION_RECORDS_V2's columns — which the instructions prohibit. Provide the recognition-events table definition and REDEMPTION_RECORDS_V2's columns and I will write the query immediately.

crm-completeness-enrichmentPASS 1.00

? The Question

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 $0.5179 · 146s · in 10 / out 13,582 tok

✓ dup_clusters✓ invalid_emails✓ survivor_language✓ completeness_pct✓ no_invent

✓ Correct Answer (ground truth)

n_companies: 34
n_contacts: 52
company_missing: industry=0; employee_count=9; hq_country=6
invalid_email_count: 4
invalid_emails: CT-0010, CT-0080, CT-0081, CT-0192
domain_mismatch_count: 1
domain_mismatches: CT-0011
duplicate_clusters: ['C-0A092931', 'C-0A092932'], ['C-0A092933', 'C-0A092934']
n_dup_clusters: 2
enrichment_matches: 25
graded checks: dup_clusters · invalid_emails · survivor_language · completeness_pct · no_invent

Model's actual answer

show the model's full answer

Analysis complete. Here is the audit.

═══════════════════════════════════════════════
CRM EXTRACT AUDIT
═══════════════════════════════════════════════

0. SCOPE / MISSING DATA (flagged, not invented)
- NO DEALS FILE was provided. The brief asks to audit deals (owner, stage, amount, close date, why-buys) and to rank fixes by "pipeline amount at stake." There is no deals.csv, no amounts, no owners, no stages, no close dates, and no why-buys anywhere in the three files. I cannot compute deal-field completeness or pipeline dollars. Everything below is companies + contacts only. The final "top 10 by pipeline at stake" cannot be produced as specified — see Section 8.
- Files present: companies.csv (34 rows), contacts.csv (52 rows), zoominfo_enrichment.csv (25 rows). No owner/persona-title reference table, so title/persona blanks can only be flagged, not filled.

1. COMPLETENESS % PER FIELD

Companies (n=34):
- industry:        34/34 = 100.0%  (but label-inconsistent — see §6)
- employee_count:  25/34 = 73.5%   (9 blank)
- hq_country:      28/34 = 82.4%   (6 blank)

Contacts (n=52):
- email (present): 52/52 = 100.0%
- email (VALID):   48/52 = 92.3%   (4 malformed — see §4)
- title:           39/52 = 75.0%   (13 blank)
- persona:         37/52 = 71.2%   (15 blank)

Deals: NO DATA — cannot report.

2. DUPLICATE COMPANY CLUSTERS (shared domain)

Cluster A — domain acme-corp.com
  Members: C-0A092931, C-0A092932
  Conflict: employee_count 500 vs 510; industry Technology vs tech; country US vs USA
  SURVIVOR: C-0A092931 (lower/canonical alias; industry properly cased "Technology")
  Merge C-0A092932 into it. Employee count 500 vs 510 is a real conflict — neither is in enrichment (no ZI row for acme-corp.com), so keep 500 and flag for manual verification; do not invent a reconciled number.

Cluster B — domain globex.io
  Members: C-0A092933, C-0A092934
  Conflict: industry SaaS vs Technology; employee_count both 200 (agree); country both US (agree)
  SURVIVOR: C-0A092934 (industry "Technology" matches your dominant taxonomy; "SaaS" is an outlier label). Data otherwise identical, so this merge is low-risk.

No other shared-domain duplicates. (All other 30 companies have unique domains. Note: aliases like C-425E2A "Tech " vs others are label noise, not duplicates.)

3. DOMAIN MISMATCHES (valid email, but email domain ≠ company domain)
- CT-0011: user1@other-domain.com — company C-66D1FC domain is 66d1fc.com. Email is syntactically valid but points at a foreign domain. Recommend: verify contact still works at this account; likely stale/personal or job-changed. Correct to @66d1fc.com or re-verify.
(1 mismatch total.)

4. INVALID EMAILS (malformed — no domain after @)
- CT-0010: "user0@"   (company C-66D1FC / 66d1fc.com)
- CT-0080: "user0@"   (company C-92D97D / 92d97d.com)
- CT-0081: "user1@"   (company C-92D97D / 92d97d.com)
- CT-0192: "user2@"   (company C-425E2A / 425e2a.com)
All four are truncated at the "@" with no host. The row's own `domain` column suggests the intended host — recommend reconstructing as user0@<domain> only after verification; do not auto-fill a guessed local-part/host as fact.

5. ENRICHMENT FILLS (CRM blank AND ZoomInfo has a matching-domain value → fill)
All are employee_count, all sourced from ZoomInfo (zi_employee_count = 400):
  C-EC3025 → 400
  C-96039F → 400
  C-44EA29 → 400
  C-D04904 → 400
  C-B23205 → 400
  C-60C75F → 400
  C-7BBDFA → 400
  C-50D386 → 400
(8 fills.) After these, employee_count completeness → 33/34 = 97.1%. The 1 still-blank (C-93C8BF, blank count) has no ZI row — leave blank, flag for enrichment.

hq_country blanks that CANNOT be filled (no ZI value either — ZI country also blank for these): C-2D1F1B, C-D73B89, C-2C60E5, C-7BBDFA(*), C-50D386(*), C-EE9FFB. (*7bbdfa/50d386 ZI country is also blank.) Actually of the 6 CRM-blank countries, ZI supplies none → 0 country fills possible. Leave blank; flag.

6. CRM↔ENRICHMENT DISAGREEMENTS (both present, differ)

6a. Industry taxonomy mismatches — 10 rows. These are label/taxonomy differences, NOT value conflicts: CRM uses a "tech/Technology/Tech" family; ZoomInfo uses "Computer Software."
  C-66D1FC, C-EC3025, C-44EA29, C-92D97D, C-D04904, C-77A95A, C-AA8DDA, C-B25F40, C-60C75F, C-425E2A
  RECOMMENDED SOURCE: Adopt one canonical taxonomy. For a GTM CRM, recommend standardizing on ZoomInfo's "Computer Software" (consistent, machine-normalized) OR mapping all tech-family labels to a single internal value. Either way this is a normalization decision, not a factual conflict — both describe the same segment.

6b. Employee count: ZERO true numeric disagreements between CRM and ZI (where both present, they match).
6c. HQ country: ZERO disagreements (US/USA both normalize to United States, matching ZI).

7. HYGIENE / NORMALIZATION ISSUES (no fabrication needed, formatting only)
- Country labels inconsistent: US / USA / United States all used for the same country. Standardize (recommend "United States").
- Industry labels inconsistent: "tech", "Technology", "Tech " (trailing whitespace), "SaaS" and "health care" vs "Healthcare". Trim whitespace and standardize casing/taxonomy.
- Trailing-space values ("Tech ") will break exact-match grouping/reporting — trim on ingest.

8. THE 10 FIXES WITH THE MOST PIPELINE AT STAKE
CANNOT BE PRODUCED AS ASKED. Ranking fixes by "pipeline amount at stake" requires deal amounts joined to companies/contacts. No deals file, no amounts, and no company→deal linkage were provided. I will not invent deals or dollar figures.

What I CAN give instead — the 10 highest-leverage data fixes ranked by count/verification-risk (no dollars, because none exist in the data):
  1. Add deals.csv — the entire deal audit + pipeline ranking is blocked without it. (Highest-impact missing input.)
  2. Merge acme-corp.com duplicates (C-0A092931 survivor) and resolve the 500-vs-510 headcount conflict.
  3. Merge globex.io duplicates (C-0A092934 survivor).
  4. Fix 4 malformed emails (CT-0010, CT-0080, CT-0081, CT-0192) — unreachable contacts.
  5. Verify domain-mismatched contact CT-0011 (user1@other-domain.com).
  6. Apply 8 ZoomInfo employee_count fills (EC3025, 96039F, 44EA29, D04904, B23205, 60C75F, 7BBDFA, 50D386).
  7. Standardize industry taxonomy across the 10 tech-family rows (CRM vs "Computer Software").
  8. Fill 13 blank contact titles and 15 blank personas (needs a source — not in these files).
  9. Enrich the 6 companies with no ZI row (BA969B, 332637, 93C8BF, EE9FFB, C9BB20, plus dedup remnants) and the 6 blank hq_countries ZI can't fill.
  10. Normalize country labels (US/USA→United States) and trim trailing whitespace ("Tech ").

If you send me a deals extract (alias, owner, stage, amount, close_date, why_buys + company link), I'll re-run and produce the true pipeline-weighted top-10.

I have everything I need in the provided files. Note: deal amounts were requested but no amount field exists in the data.

Analysis of each candidate (prospect voice only):

TG-001 — Deal-EC3025
Quote: "We need SCIM user provisioning — our security team will not approve any tool that requires manual account management." (Prospect, IT Security Lead)
Docs check: "SCIM user provisioning ... NOT currently listed as supported capabilities."
Classification: REAL GAP. SCIM is not offered on any tier, so it cannot be resolved by an upgrade (plan gate) or by training (enablement). It is an absent capability.

TG-002 — Deal-D0D6B5
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." (Prospect, HRIS Manager)
Docs check: "ADP Workforce Now integrations are NOT currently listed as supported capabilities." Supported HRIS are Workday, BambooHR, Gusto, Rippling only.
Classification: REAL GAP. ADP Workforce Now is not supported on any tier — not gated behind a plan, absent entirely.

TG-003 — Deal-CFE7F4
Quote: "I tried to build a custom report combining recognition frequency with turnover and couldn't — is that possible on our current plan?" (Prospect, VP People)
Docs check: "Custom report builder" = Enterprise only (Core —, Pro —, Enterprise yes).
Classification: PLAN GATE. The capability exists; it is locked to the Enterprise tier. Resolved by upgrade, not by building anything new.

TG-004 — Deal-84DBA6
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." (Prospect, People Ops Manager)
Docs check: Slack integration = supported on all plans; it is already turned on.
Classification: ROLLOUT/ENABLEMENT ISSUE. The product works; the barrier is untrained managers. Fixed by enablement, not product.

TG-005 — Deal-36C33F
The native-mobile-app statement ("we don't have a native mobile app for hourly workers yet") is spoken by Alex Franklin, the rep — not prospect voice, so it does not qualify as a candidate. The only prospect line here ("The web version should be fine ... for now") raises no gap.
Classification: EXCLUDED (rep language, not prospect voice).

Missing data: No deal amount field is present in transcripts_gaps.csv, so amounts cannot be reported for any deal without inventing numbers.

════════════════════════════════════════
SUMMARY — TRUE PRODUCT GAPS (real gaps only)
════════════════════════════════════════

1. Deal-EC3025 — SCIM user provisioning
Prospect (IT Security Lead): "We need SCIM user provisioning — our security team will not approve any tool that requires manual account management."
Amount: NOT IN DATA.

2. Deal-D0D6B5 — ADP Workforce Now integration
Prospect (HRIS Manager): "Our payroll runs on ADP Workforce Now and I don't see ADP anywhere in your integration list — that's a dealbreaker for us."
Amount: NOT IN DATA.

show the model's full answer

Rep: Alex Franklin. Basis: 10 calls (TT-001 through TT-010).

WHAT HE LEADS WITH (first five minutes)
His minute-0 opener is a scripted customer-proof story in 7 of 10 calls, quoted once:
"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." (TT-001, TT-002, TT-003, TT-005, TT-006, TT-007, TT-008, TT-010)
The other 3 open differently: an agenda ("I put together a short agenda — security review first, then pricing." TT-004), a competitor jab ("And unlike Workhuman, our pricing includes the full rewards catalog with no extra margin." TT-005 min 2 — this call has both), and a pricing-first callback ("You asked for straight pricing last time, so let's start there." TT-009).

THE THREE MOST COMMON OBJECTIONS AND HOW HE HANDLES THEM

1. Budget locked / no line item (4 calls: TT-001, TT-003, TT-006, TT-010)
Objection: "Honestly, budget is locked until next fiscal year — I can't add a new line item right now."
Handling: "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." (funds-it-from-savings reframe)

2. Revisit next quarter / open enrollment (3 calls: TT-002, TT-005, TT-008)
Objection: "This is good, but can we revisit it next quarter? Open enrollment starts in October and we're underwater."
Handling: "Makes sense. What if we scope a 90-day pilot with one department so you have internal data before next quarter's planning?" (pilot to create urgency + data)

3. Status quo (spreadsheet + gift cards) (3 calls: TT-004, TT-007, TT-009)
Objection: "We already do recognition with a spreadsheet and quarterly gift cards — why would we change?"
Handling: "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." (automation + analytics contrast)

NEXT-STEP AGREEMENT RATE
7 of 10 = 70%.
Arithmetic: agreed = TT-001, TT-002, TT-003, TT-005, TT-006, TT-008, TT-009 (7). Not agreed = TT-004, TT-007, TT-010 (3). 7 ÷ 10 = 0.70 = 70%. The agreed line each time: "Yes, Thursday at 2pm works — send the invite and I'll bring our HRIS manager."

COMPETITORS A PROSPECT RAISED
Only two, each once (competitors mentioned by the rep himself are excluded):
- Awardco — TT-003 (Deal-547B2B): "We're also in late talks with Awardco — their rewards catalog looks bigger than yours."
- Kudos — TT-007 (Deal-EDC141): "How are you different from Kudos? Our CEO used them at her last company."
(Note: Workhuman appears in TT-005 but was named by the rep, not a prospect, so it is not counted here.)

show the model's full answer

WEEKLY REWARDS REPORT — REDEMPTION SECTION

Last completed month: 2026-08 (August 2026). Data spans 2026-01 through 2026-08; all 378 rows fall within this window, so none were excluded.

Redemption count: 378

Spend: $27,846.00

Unique redeemers: 235 (distinct user_key)

Redemptions per redeemer: 1.61
  Arithmetic: 378 redemptions / 235 redeemers = 1.6085

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

Top 5 countries by redemptions (count):
  1. US — 244
  2. CA — 24
  3. AU — 21
  4. GB — 17
  5. NL — 17

Note: GB and NL are tied at 17 redemptions each; both are shown in ranks 4–5. The next country (SG) has 12.

All 80 tickets classified, no UNCLASSIFIED remainder. Ranked by ARR exposure (distinct-account ARR, not summed per ticket).

QUARTER SUPPORT-TICKET SYNTHESIS (80 tickets, Jun 1 – Aug 29 2026)

Method: I ignored the CSV `tag` column and clustered on the ticket body text. "ARR affected" = sum of each DISTINCT account's ARR (counted once per account, not once per ticket) — summing per-ticket would double-count repeat filers. Share = theme count / 80.

Ranked by ARR exposure:

────────────────────────────────────────
1. HRIS Provisioning failures  ← BROAD PATTERN, top exposure
   Count: 12 | Share: 15.0% (12/80) | Distinct accounts: 3
   ARR affected: $114,000  (48,000 + 36,000 + 30,000)
   Accounts: C-0DDFC9A7 ($48k), C-0B2213A9 ($36k), C-0F6C0F34 ($30k)
   Ticket ids: IC-460059, IC-460060
   Symptom: HRIS sync silently skips new hires; provisioning log shows no errors.
   Recommendation: Escalate to eng as a P1 — three of your largest accounts affected; add sync-failure alerting instead of relying on a clean log.

────────────────────────────────────────
2. Redemption / Checkout failures  ← BROAD PATTERN, widest account spread
   Count: 18 | Share: 22.5% (18/80) | Distinct accounts: 7
   ARR affected: $68,800
   (11,000 + 10,700 + 10,300 + 9,600 + 9,600 + 8,900 + 8,700)
   Accounts: C-14264ABD, C-0B827671, C-0B0F1BAB, C-0FCCD2DF, C-0D9CA315, C-0CEF69FD, C-0F876796
   Ticket ids: IC-460025, IC-460024
   Symptom: Checkout hangs, redemptions fail, gift-card email/code never delivered — and in several cases points are deducted anyway.
   Recommendation: Prioritize — money-losing (points debited on failed orders); audit the checkout-to-fulfillment handoff and auto-refund deducted points.

────────────────────────────────────────
3. Billing / Invoice errors  ← SINGLE-ACCOUNT NOISE (high $, one logo)
   Count: 16 | Share: 20.0% (16/80) | Distinct accounts: 1
   ARR affected: $52,000
   Account: C-0E9C27D1 ($52k) — all 16 tickets are this one account
   Ticket ids: IC-460069, IC-460078
   Symptom: One account: recurring seat-count discrepancy (billed 200, licenses 150), wrong-tier renewal charges, "third invoice in a row."
   Recommendation: NOT a product-wide trend — a single churn-risk escalation; assign an AM/billing owner to fix the seat record and issue credits before renewal.

────────────────────────────────────────
4. Points Not Posting  ← BROAD PATTERN, highest volume / lowest $ each
   Count: 20 | Share: 25.0% (20/80) | Distinct accounts: 9
   ARR affected: $31,100
   (4,500 + 4,500 + 4,200 + 3,500 + 3,400 + 2,900 + 2,900 + 2,700 + 2,500)
   Accounts: C-0BF20542, C-0D0B047C, C-0D6CC8E3, C-0D3278C7, C-0D284E42, C-21FEBCBB, C-0B2895EF, C-0BE96399, C-0DD0626C
   Ticket ids: IC-460004, IC-460001
   Symptom: Recognitions show delivered but points/balance never update; often "after the weekend."
   Recommendation: Investigate the recognition→ledger posting job (weekend batch suspected); highest ticket volume but smallest accounts — fix for CSAT, not revenue.

────────────────────────────────────────
5. Slack Integration  ← BROAD PATTERN, lowest exposure
   Count: 14 | Share: 17.5% (14/80) | Distinct accounts: 4
   ARR affected: $18,900  (5,400 + 5,200 + 4,400 + 3,900)
   Accounts: C-10A56B0F, C-8C2E8F00, C-0B843542, C-0BA71F12
   Ticket ids: IC-460041, IC-460047
   Symptom: Sync stops, toggle resets itself, app disconnects/re-auth doesn't stick, slash command errors team-wide.
   Recommendation: Fix OAuth token persistence (re-auth not sticking is the root); bundle the fix with a status-page note to the four affected accounts.

────────────────────────────────────────
Cross-cutting notes
- Volume vs. exposure diverge sharply: "Points Not Posting" is #1 by volume (25%) but only 4th by ARR; "HRIS Provisioning" is 4th by volume but #1 by ARR. Triage by exposure.
- The single biggest concentration of risk is not a broad pattern at all — it's one $52k account (C-0E9C27D1) generating 20% of all tickets. That is a retention fire, not a roadmap signal.
- Counts sum to 80 (12+18+16+20+14); every ticket was classified from text with none left over.

Data caveats: ARR is provided per ticket and is identical across each account's rows, so I treated it as an account-level figure. There is no ticket status/resolution field, so I cannot report open vs. resolved or time-to-close.

I need to flag a data problem before giving you the update.

The weekly instruction requires reporting "what moved THIS WEEK," but the data provided is quarter-to-date snapshots only. There are no weekly deltas, no prior-week snapshot, and no week-tagged records. I cannot compute what moved this week from this data. I'll state that explicitly rather than invent it.

Everything else is computable. Here it is.

═══════════════════════════════════════════
WEEKLY MARKETING GOALS UPDATE — Q3-2026
═══════════════════════════════════════════
Quarter: 2026-07-01 to 2026-09-30
Days elapsed: 66 of 92 = 71.7% of quarter elapsed
Pace benchmark: on-track QTD = 71.7% of a higher-better target; on/behind/ahead judged vs that line.

Time fraction: 66 / 92 = 0.7174 (71.7%)

───────────────────────────────────────────
1) SQMs (higher better)
   QTD actual: 230
   Target:     300
   Delta:      230 − 300 = −70
   Attainment: 230 / 300 = 76.7%
   Expected-by-now: 0.7174 × 300 = 215.2
   230 vs 215.2 → +14.8 above pace line
   PACE: AHEAD

2) SQOs (higher better)
   QTD actual: 84
   Target:     120
   Delta:      84 − 120 = −36
   Attainment: 84 / 120 = 70.0%
   Expected-by-now: 0.7174 × 120 = 86.1
   84 vs 86.1 → −2.1 below pace line
   PACE: BEHIND (marginal)

3) DS2s (higher better)
   QTD actual: 40
   Target:     75
   Delta:      40 − 75 = −35
   Attainment: 40 / 75 = 53.3%
   Expected-by-now: 0.7174 × 75 = 53.8
   40 vs 53.8 → −13.8 below pace line
   PACE: BEHIND

4) Closed-lost MIA rate (lower better)
   Numerator (MIA):   5
   Denominator (total closed-lost): 25
   Rate: 5 / 25 = 0.20 (20.0%)
   Target: 0.10 (10.0%)
   Delta:  0.20 − 0.10 = +0.10 (+10.0 pts) — wrong direction
   (Ratio metric: no time-proration applied.)
   PACE: BEHIND (2× the target rate)

5) Same-quarter close count (higher better)
   QTD actual: 10
   Target:     20
   Delta:      10 − 20 = −10
   Attainment: 10 / 20 = 50.0%
   Expected-by-now: 0.7174 × 20 = 14.3
   10 vs 14.3 → −4.3 below pace line
   PACE: BEHIND

6) Active pipeline coverage against target (higher better)
   QTD actual: $3,000,000
   Target:     $4,000,000
   Delta:      3,000,000 − 4,000,000 = −$1,000,000
   Coverage/attainment: 3,000,000 / 4,000,000 = 75.0%
   Expected-by-now: 0.7174 × 4,000,000 = $2,869,600
   3,000,000 vs 2,869,600 → +$130,400 above pace line
   PACE: AHEAD

───────────────────────────────────────────
SUMMARY TABLE
───────────────────────────────────────────
Metric              QTD        Target     Delta         Pace
SQMs                230        300        −70           Ahead
SQOs                84         120        −36           Behind (marginal)
DS2s                40         75         −35           Behind
Closed-lost MIA %   20.0%      10.0%      +10.0 pts     Behind
Same-qtr closes     10         20         −10           Behind
Active pipeline     $3.0M      $4.0M      −$1.0M        Ahead

───────────────────────────────────────────
WHAT MOVED THIS WEEK
───────────────────────────────────────────
I cannot report what moved this week. The data provided is a single quarter-to-date snapshot with no weekly granularity — there is no prior-week snapshot, no week-stamped records, and no time series — so week-over-week movement is not derivable from these files. To produce this section, provide either last week's snapshot of the same metrics or a dated/weekly breakdown.

One structural note the QTD data does support: top-of-funnel volume (SQMs, pipeline $) is pacing ahead of the elapsed-time line, but mid-funnel conversion is not — SQOs, DS2s, and same-quarter closes all sit below pace, and the closed-lost MIA rate is running at 20% against a 10% target. That pattern points to a conversion/qualification gap downstream of lead volume rather than a lead-generation shortfall, but I cannot attribute any of it to this week specifically.

No dedicated brand-voice file. Bonusly's brand voice is well-established (warm, upbeat, human, celebratory, plainspoken — recognition-culture positivity without corporate stiffness). I'll write in that register. All numbers trace directly to the extracts.

---

Week of 2026-08-31 — GTM Digest

Marketing
It was a spirited week for the team, even if the scoreboard came up a touch short. Marketing generated 46 SQMs against a target of 52, landing 6 shy of goal (52 − 46 = 6, about 88% attainment). The bright spot: our webinar channel carried the load, delivering 18 of those 46 SQMs — a solid 39% of everything sourced. Efficiency held steady too, with cost per SQM on paid search staying flat at $150. Plenty to build on as we chase that target next week.

Sales
Big moves from the Sales crew. The team converted 14 SQOs and booked 9 DS2 meetings, keeping the top of funnel humming. New pipeline created rang in at $310,000 — real fuel for the quarters ahead. And they didn't just fill the funnel, they closed it: 3 same-quarter deals landed this week. Momentum is trending in the right direction.

Customer Success
CS kept the good vibes flowing where it counts most — with our customers. The team saved 2 renewals this week, protecting relationships and revenue in one motion. Even better, team NPS climbed to 61, a strong signal that the experience we're delivering is landing. One thing to keep our eyes on: 3 red-flag accounts remain open heading into next week, so they'll get our full attention.

PLG
Our self-serve engine kept humming. PLG welcomed 412 new signups this week, with activation coming in at 31%. Where the magic really happened: 38 companies hit their aha moment of 10 recognition gives — the point where recognition starts becoming a habit rather than a one-off. That's 38 teams one step closer to a culture of appreciation. Onward.

---

Word count: ~290 words. Every figure ties directly to week_extracts.md. Arithmetic shown for Marketing (gap to target: 52 − 46 = 6; ~88% attainment; 18/46 ≈ 39%). No contact names, performance commentary, or compensation included.

partner-digest-sectionPASS 1.00

? The Question

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 $0.0309 · 7s · in 2 / out 552 tok

✓ all_partners✓ pipeline_amount✓ quiet_one_line

✓ Correct Answer (ground truth)

roster: partner_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)
per_partner_pipeline: {"Apex Rewards Co": {"count": 2, "amount": 275000}, "HRCloud Partners": {"count": 1, "amount": 140000}, "CultureBridge": {"count": 2, "amount": 135000}}
partner_sourced_pipeline: count=5; amount=550000
quiet_partners: Recogniq, KudosWave, PeopleFirst Advisors, TotalPerk
active_no_deals: WorkWell Group
rule: every roster partner named exactly once; quiet partners get one line; no partners outside roster.
graded checks: all_partners · pipeline_amount · quiet_one_line

Model's actual answer

show the model's full answer

Partner Digest — 2026-08-24 to 2026-09-04

ACTIVE PLAYS

Apex Rewards Co — Co-webinar locked for 09-15. Two partner-sourced opps this period, both in DS1 (UTM Source = Partner confirmed).
Sourced pipeline: 2 deals / $275,000
  Deal-DDAAF2 $180,000 + Deal-2CF33E $95,000 = $275,000

HRCloud Partners — Integration referral cleared security review; opp moved to DS2. One partner-sourced opp this period.
Sourced pipeline: 1 deal / $140,000
  Deal-F1CDA5 $140,000

CultureBridge — Lunch-and-learn produced two sourced opps, both early stage.
Sourced pipeline: 2 deals / $135,000
  Deal-096E1D $60,000 + Deal-067213 $75,000 = $135,000

WorkWell Group — Wants to restart the joint playbook in Q4; planning call booked for 09-09. No sourced deals this period.
Sourced pipeline: 0 deals / $0

QUIET PARTNERS

Recogniq — No activity this period.
KudosWave — No activity this period.
PeopleFirst Advisors — No activity this period.
TotalPerk — No activity this period.

TOTALS

Partner-sourced pipeline: 5 deals / $550,000
  $275,000 + $140,000 + $135,000 + $0 = $550,000

All 8 roster partners accounted for (4 active, 4 quiet). All 5 deals in partner_deals.csv attributed.

rfp-answer-from-policyPASS 1.00

? The Question

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 $0.0348 · 11s · in 2 / out 708 tok

✓ answered_count✓ unanswerable_flagged✓ citations✓ no_guess

✓ Correct Answer (ground truth)

answered_count: 7
answer_map: {"Q1": ["P1"], "Q2": ["P1"], "Q3": ["P2"], "Q4": ["P3"], "Q5": ["P4"], "Q6": ["P5"], "Q7": ["P6"]}
unanswerable: Q8, Q9, Q10
valid_citation_ids: P1, P2, P3, P4, P5, P6, P7, P8
rule: unanswerable items must be flagged and the document that would answer them named; do not guess.
graded checks: answered_count · unanswerable_flagged · citations · no_guess

Model's actual answer

show the model's full answer

Q1. Is customer data encrypted at rest? If so, how?
Yes. Customer data is encrypted at rest using AES-256. [P1]

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

Q3. Do you hold a SOC 2 report, and can we obtain a copy?
Yes. Bonusly maintains a SOC 2 Type II report, renewed annually. It is available to prospects under NDA. [P2]

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

Q5. Where is your subprocessor list published and how are changes notified?
The current subprocessor list is maintained at trust.bonusly.com. Customers receive 30 days notice before a new subprocessor is added. [P4]

Q6. Do you support SAML single sign-on?
Yes. SAML 2.0 single sign-on (and SCIM user provisioning) is available on the Enterprise plan. [P5]

Q7. What is your production backup schedule and retention?
Production databases are backed up daily. Backups are encrypted and retained for 35 days. [P6]

Q8. Do you hold an ISO 27001 certification?
Unanswerable from the provided excerpts. The excerpts reference a SOC 2 Type II report [P2] but do not mention ISO 27001. This would be answered by an ISO 27001 certificate or the certification section of the Trust portal / compliance documentation.

Q9. What is your contractual uptime SLA percentage?
Unanswerable from the provided excerpts. No uptime or availability commitment is stated. This would be answered by the Service Level Agreement (SLA) or the Master Services Agreement.

show the model's full answer

NDA-1 — [PARTY A] and Bonusly: GREEN — Mutual, standard 2-year term with all five standard carve-outs present ("(a) is or becomes publicly available through no breach... (e) must be disclosed by law or court order"), Delaware law, no embedded restrictive covenants; nothing beyond a routine mutual NDA.

NDA-2 — [PARTY B] and Bonusly: YELLOW — Embedded non-solicit: "During the term of this Agreement and for eighteen (18) months thereafter, neither party shall solicit for employment or hire any employee of the other party with whom it came into contact under this Agreement" — a hiring/HR restriction beyond confidentiality that warrants counsel review (otherwise mutual, standard carve-outs, Delaware law).

NDA-3 — [PARTY C] and Bonusly: RED — Multiple red flags compounding: a three-year non-compete ("Recipient shall not, directly or indirectly, engage in or provide services to any business that competes with Discloser's business"), one-way terms in Discloser's favor with a long 5-year term, foreign governing law/exclusive jurisdiction ("the laws of the Republic of Ireland, and the parties submit to the exclusive jurisdiction of its courts"), AND "No confidentiality carve-outs are stated" — the missing carve-outs alone create unbounded confidentiality exposure.