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

CRM AUDIT REPORT
================

DATA SCOPE NOTE — deals.csv was not provided in the extract. Owner, stage, amount, close date, and why-buys cannot be audited or ranked; the "top-10 fixes by pipeline amount at stake" cannot be produced as specified. Everything below covers companies (n=34) and contacts (n=52) only.

────────────────────────────────────────
1. COMPLETENESS % PER FIELD
────────────────────────────────────────
Companies (n=34)
  industry           34/34 = 100.0%  (but 10 rows use non-standard variants: "tech", "Tech ", "health care")
  employee_count     25/34 =  73.5%
  hq_country         28/34 =  82.4%  (values inconsistent: US / USA / United States)

Contacts (n=52)
  email (valid)      48/52 =  92.3%
  title              39/52 =  75.0%
  persona            37/52 =  71.2%

Deals — file not supplied. Owner / stage / amount / close_date / why_buys completeness = UNKNOWN.

────────────────────────────────────────
2. DUPLICATE COMPANY CLUSTERS
────────────────────────────────────────
Cluster A — domain acme-corp.com
  C-0A092931  Technology / 500 / US       ← SURVIVOR (canonical values)
  C-0A092932  tech        / 510 / USA     (merge; employee_count 500 vs 510 disagreement → keep 500, ZI has no row to arbitrate)

Cluster B — domain globex.io
  C-0A092933  SaaS        / 200 / US      ← SURVIVOR (earliest alias; identical emp/country)
  C-0A092934  Technology  / 200 / US      (merge; industry disagreement SaaS vs Technology → no ZI row; recommend SaaS if product-fit filter, else Technology)

No near-duplicate name variants detected beyond shared-domain pairs (all other aliases have unique domains).

────────────────────────────────────────
3. INVALID EMAILS (4)
────────────────────────────────────────
  CT-0010  C-66D1FC   'user0@'          truncated local/host missing
  CT-0080  C-92D97D   'user0@'          truncated
  CT-0081  C-92D97D   'user1@'          truncated
  CT-0192  C-425E2A   'user2@'          truncated

────────────────────────────────────────
4. EMAIL DOMAIN MISMATCH (1)
────────────────────────────────────────
  CT-0011  C-66D1FC   email=user1@other-domain.com  vs  company domain=66d1fc.com
           → verify: personal address, wrong company link, or contact left the company

────────────────────────────────────────
5. ENRICHMENT FILL — CRM EMPTY, ZI HAS VALUE (8 fills, employee_count only)
────────────────────────────────────────
  C-EC3025 · employee_count : (empty) → 400
  C-96039F · employee_count : (empty) → 400
  C-44EA29 · employee_count : (empty) → 400
  C-D04904 · employee_count : (empty) → 400
  C-B23205 · employee_count : (empty) → 400
  C-60C75F · employee_count : (empty) → 400
  C-7BBDFA · employee_count : (empty) → 400
  C-50D386 · employee_count : (empty) → 400

hq_country fills: none available. Every CRM row missing hq_country also has an empty ZI hq_country (C-2D1F1B, C-D73B89, C-44EA29, C-D04904, C-2C60E5, C-EE9FFB) — cannot fill from this enrichment file.

────────────────────────────────────────
6. CRM ↔ ZI DISAGREEMENTS (industry, 10)
────────────────────────────────────────
All 10 are the CRM "Technology / tech / Tech " label vs ZI "Computer Software". Same underlying meaning, different taxonomy.
  C-66D1FC, C-EC3025, C-44EA29, C-92D97D, C-D04904, C-77A95A, C-AA8DDA, C-B25F40, C-60C75F, C-425E2A
  Recommend source: ZoomInfo ("Computer Software") — it is the more specific and internally consistent label. Also standardize CRM picklist to remove case/whitespace variants ("tech", "Tech ", "Technology" → one value).

Other standardization needed (no ZI conflict, but CRM values are inconsistent):
  "health care" (C-7BBDFA, C-50D386) → "Healthcare"
  "US" / "USA" / "United States" → one canonical value

────────────────────────────────────────
7. COMPANIES WITH NO ENRICHMENT MATCH (9)
────────────────────────────────────────
  C-BA969B (ba969b.com), C-332637 (332637.com), C-93C8BF (93c8bf.com),
  C-EE9FFB (ee9ffb.com), C-C9BB20 (c9bb20.com),
  C-0A092931 / C-0A092932 (acme-corp.com), C-0A092933 / C-0A092934 (globex.io)
  → Re-enrich or manually source; do not invent values.

────────────────────────────────────────
8. TOP 10 FIXES BY PIPELINE AT STAKE
────────────────────────────────────────
CANNOT PRODUCE AS SPECIFIED — the extract has no deals file, so pipeline amount per company is unknown.

If the deals file is supplied, the ranking would join fixes to deal.amount by company_alias. Without it, here is a defensible substitute ranked by data-quality severity + downstream blast radius (contact-gap count + duplicate risk + enrichment gap). Flagging so you can re-rank when deals arrive:

  1.  Merge duplicate cluster acme-corp.com — keep C-0A092931, resolve 500 vs 510 headcount, retire C-0A092932. (Duplicate deal/contact risk.)
  2.  Merge duplicate cluster globex.io — keep C-0A092933, resolve SaaS vs Technology, retire C-0A092934.
  3.  C-92D97D — 2/3 contacts have truncated emails (CT-0080, CT-0081) AND 2/3 missing title AND 2/3 missing persona. Worst single-account contact quality.
  4.  C-66D1FC — CT-0010 email truncated + CT-0011 wrong-domain email; verify all three "VP People" duplicates are distinct people, not the same contact loaded 3x.
  5.  C-425E2A — CT-0192 email truncated; also standardize industry "Tech " → canonical value.
  6.  C-AA8DDA — 3/3 contacts missing title (persona set but no role verification).
  7.  Fill 8 employee_count blanks from ZI (C-EC3025, C-96039F, C-44EA29, C-D04904, C-B23205, C-60C75F, C-7BBDFA, C-50D386) — single batch update.
  8.  C-60C75F — 2/2 contacts missing persona (no threading possible for outreach).
  9.  Standardize industry picklist across 10 "tech / Technology / Tech " rows to ZI's "Computer Software" (or your canonical "Technology").
  10. Re-enrich the 9 no-match companies (BA969B, 332637, 93C8BF, EE9FFB, C9BB20, acme-corp.com x2, globex.io x2) so future fills/audits can proceed.

Please share the deals CSV (deal_id, company_alias, owner, stage, amount, close_date, why_buy) and I will re-rank these fixes by actual pipeline $ at stake.

### FILE: deals_context (not provided)

I don't have deal amount data — the request asks for "the deal and amount" for each candidate, but no deals file was provided. I'll cite deal aliases exactly and mark amounts as NOT PROVIDED.

---

### Candidate analysis

**TG-001 / Deal-EC3025 — SCIM provisioning**
- Prospect (IT Security Lead): "We need SCIM user provisioning — our security team will not approve any tool that requires manual account management."
- Product docs: "SCIM user provisioning ... NOT currently listed as supported capabilities."
- Classification: **REAL GAP** (capability absent from all tiers)
- Deal: Deal-EC3025, Amount: NOT PROVIDED

**TG-002 / 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."
- Product docs: HRIS list is Workday, BambooHR, Gusto, Rippling. "ADP Workforce Now integrations are NOT currently listed as supported capabilities."
- Classification: **REAL GAP** (integration absent from all tiers)
- Deal: Deal-D0D6B5, Amount: NOT PROVIDED

**TG-003 / Deal-CFE7F4 — Custom report builder**
- Prospect (VP People): "I tried to build a custom report combining recognition frequency with turnover and couldn't — is that possible on our current plan?"
- Product docs: Custom report builder = Enterprise tier only.
- Classification: **PLAN GATE** (capability exists on Enterprise; prospect is not on that tier)
- Deal: Deal-CFE7F4, Amount: NOT PROVIDED

**TG-004 / Deal-84DBA6 — Manager adoption of Slack recognition**
- Prospect (People Ops Manager): "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."
- Product docs: Slack integration supported on all plans; manager analytics/nudges on Pro+.
- Classification: **ROLLOUT/ENABLEMENT ISSUE** (product works; training/adoption gap)
- Deal: Deal-84DBA6, Amount: NOT PROVIDED

**TG-005 / Deal-36C33F — Native mobile app for hourly workers**
- Rep (Alex Franklin) raised the mobile-app limitation. Prospect (HR Manager) response: "Good to know. The web version should be fine for our office staff for now."
- Per instructions, rep language does not count as prospect voice. Prospect explicitly did NOT raise this as a gap.
- Classification: **EXCLUDED — not prospect-voiced**
- Deal: Deal-36C33F, Amount: NOT PROVIDED

---

### Summary — real product gaps (prospect-voiced, active deals)

1. **SCIM user provisioning** — Deal-EC3025 (IT Security Lead, dealbreaker language: "will not approve"). Amount: NOT PROVIDED.
2. **ADP Workforce Now HRIS integration** — Deal-D0D6B5 (HRIS Manager, explicit "dealbreaker"). Amount: NOT PROVIDED.

Both are capabilities absent from every tier in the product docs excerpt, not plan gates or enablement issues.

OPENING (first 5 minutes, minute ≤ 5)
- 8 of 10 calls open with the 400-person retailer / 18% turnover / milestone-automation story (TT-001, 002, 003, 005, 006, 007, 008, 010).
- 1 opens with a security-then-pricing agenda (TT-004); 1 opens with straight pricing per prospect request (TT-009).
- 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." (TT-001, min 0)

THREE MOST COMMON OBJECTIONS + HANDLING

1) "Budget locked until next fiscal year" — 3 occurrences (TT-001, 003, 006, 010 prospect line; note: 4 raises, not 3 — see below). Recount: TT-001 min 6, TT-003 min 6, TT-006 min 6, TT-010 min 6 = 4 occurrences.
   Handle: pivots to turnover-savings ROI ($210k backfill avoidance) as finance justification.
   Quote: "Totally fair. Most teams fund this out of turnover savings — that retailer saved about $210k in avoided backfills, which is how their finance team signed off." (TT-001, min 8)

2) "Revisit next quarter / open enrollment" — 3 occurrences (TT-002, 005, 008, all min 6).
   Handle: offers a 90-day single-department pilot to generate internal data before replanning.
   Quote: "Makes sense. What if we scope a 90-day pilot with one department so you have internal data before next quarter's planning?" (TT-002, min 8)

3) "We already do recognition with spreadsheet + gift cards" — 3 occurrences (TT-004, 007, 009, all min 6).
   Handle: reframes on automation + analytics vs. manual scale ceiling.
   Quote: "Spreadsheets work until they scale — the difference is automation: milestones fire without HR lifting a finger, and you get analytics on who is being recognized." (TT-004, min 8)

(Correction: top 3 by frequency are budget-locked=4, revisit-next-quarter=3, spreadsheet-status-quo=3. Committee-approval also appears 2x on TT-004 min 11 and TT-010 min 11 but ranks 4th.)

CONCRETE NEXT STEP AGREED
- Explicit "yes, Thursday 2pm" agreement: TT-001, 002, 003, 005, 006, 008, 009 = 7 of 10 calls.
- No agreement: TT-004 (left with prospect), TT-007 ("no urgency"), TT-010 (committee wait).
- Rate: 7/10 = 70%.

Quote: "Yes, Thursday at 2pm works — send the invite and I'll bring our HRIS manager." (TT-001, min 15)

COMPETITORS RAISED BY PROSPECTS
- Awardco — TT-003, min 4 (prospect-raised: "in late talks with Awardco")
- Kudos — TT-007, min 4 (prospect-raised: "How are you different from Kudos?")
- Workhuman — TT-005, min 2 — NOT prospect-raised; Alex introduced it. Excluded from prospect-raised list.

Prospect-raised competitors: Awardco, Kudos (2 total).

DATA-MISSING NOTE
- The rep's rate here (7/10) contradicts the memory note "4/58 calls (7%)"; that prior figure is from a different dataset and does not apply to this 10-call sample.

COACHING NOTES
1) The retailer-turnover opener carries the whole first 5 minutes on 8/10 calls — it's earning next steps but not differentiating on the two competitive calls (TT-003 Awardco, TT-007 Kudos). Build a variant opener that leads with automation+analytics proof for prospects already evaluating a competitor, so the competitive frame is set before the case study lands.

2) When "budget locked" hits (4/10 calls), Alex closes with the $210k line and gets the meeting 3/4 times — but on TT-010 the same script fails against committee-gated buyers. Add a second move for committee objections specifically: propose a 30-min working session with the committee sponsor rather than a general next-step ask, which is the pattern that recovered TT-002/005/008 on the enrollment objection.

Redemptions — YTD through 2026-08

Last completed month: 2026-08 (today is 2026-09-08). All 378 rows in the file fall within 2026-01 through 2026-08, so the YTD-through-last-completed-month window equals the full file.

Headline metrics
- Redemption count: 378
- Spend: $27,846.00
- Unique redeemers (distinct user_key): 235
- Redemptions per redeemer: 378 / 235 = 1.61

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

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

Note on the tie: GB and NL are tied at 17 redemptions each; both are listed. The next country (SG) has 12.

Q3 support themes — read from ticket body text, not tags. 80 tickets, 24 distinct accounts. Ranked by ARR exposure.

Broad patterns (multi-account):

1. HRIS provisioning failures — 12 tickets / 15.0% share / 3 accounts / $114,000 ARR
Bodies: "HRIS provisioning is not creating accounts…", "HRIS sync skipped 12 new hires…", "New employees are not being provisioned from our HRIS sync." All three of these accounts are $30K+ ARR (C-0B2213A9 $36K, C-0DDFC9A7 $48K, C-0F6C0F34 $30K).
Sample: IC-460053, IC-460054.
Recommendation: Escalate to eng as a P1 — silent-fail provisioning (log shows no errors) is a churn risk at the top three ARR bands after C-0E9C27D1; add a sync-diff alert and a proactive outreach to all three accounts this week.

2. Redemption / checkout / gift-card failures — 18 tickets / 22.5% / 7 accounts / $68,800 ARR
Bodies: "Checkout spins forever…", "Gift card order errored out but the points were still deducted," "Redemption failed at checkout and the gift card code never arrived," "Redemption failed twice today; gift card email never showed up." Recurring on C-0B827671, C-0CEF69FD, C-0F876796, C-0FCCD2DF, C-14264ABD.
Sample: IC-460021, IC-460022.
Recommendation: Ship checkout retry + points-refund-on-failure fix and audit the gift-card email queue; this is the highest-volume broad pattern and touches 7 mid-tier accounts.

3. Points not posting / recognition-to-balance lag — 20 tickets / 25.0% / 9 accounts / $31,100 ARR
Bodies: "Points not posting for our whole team after the weekend," "Two recognitions I sent show as delivered but the points never arrived," "Points from last week's recognition are still not posting…", "Missing points — my balance has not updated since Tuesday."
Sample: IC-460001, IC-460002.
Recommendation: Highest volume + widest account spread (9 accts, all SMB tier <$5K); investigate the weekend/async posting job — recognition-delivered-but-points-missing is the core product promise and drives NPS damage even at low ARR.

4. Slack integration instability — 14 tickets / 17.5% / 4 accounts / $18,900 ARR
Bodies: "Slack integration stopped syncing recognitions…", "Recognitions no longer post to Slack; the sync toggle resets itself," "Slack slash command returns an error for everyone on our team," "The Slack app disconnected and re-auth does not stick."
Sample: IC-460039, IC-460040. C-0BA71F12 and C-10A56B0F are repeat filers.
Recommendation: The self-resetting sync toggle and non-sticky re-auth suggest a token-refresh/OAuth-scope bug — reproduce and patch; Slack is the primary UX surface for these accounts.

Single-account concentration (noise vs. broad pattern):

5. Billing / invoice / seat-count / renewal-tier errors — 16 tickets / 20.0% / 1 account / $52,000 ARR
All 16 tickets are C-0E9C27D1. Four distinct complaints: seat count they never approved, charged 200 seats vs. 150 licensed, "third invoice in a row with the same seat-count error," annual renewal at wrong tier price. This is not a broad pattern — it is one $52K account in a 3-month billing dispute.
Sample: IC-460065, IC-460066.
Recommendation: Executive-sponsor + billing-ops joint call this week; issue credit memo and rebuild the account's billing record — 16 tickets on the same unresolved dispute is a hard churn signal, and this is your #2-ranked ARR exposure entirely from one account.

show the model's full answer

Weekly Marketing Goals Update — Q3-2026 (Day 66/92, 71.7% elapsed)

Pace rule: on-pace threshold = 71.7% of target for higher_better metrics (i.e., actual ≥ 0.717 × target = on/ahead). For lower_better (MIA rate), on-pace = actual ≤ target.

SQMs
- QTD actual: 230
- Target: 300
- Delta: 230 − 300 = −70 (76.7% of target)
- Pace threshold: 0.717 × 300 = 215.1 → 230 ≥ 215.1 → ON PACE

SQOs
- QTD actual: 84
- Target: 120
- Delta: 84 − 120 = −36 (70.0% of target)
- Pace threshold: 0.717 × 120 = 86.0 → 84 < 86.0 → BEHIND (by 2)

DS2s
- QTD actual: 40
- Target: 75
- Delta: 40 − 75 = −35 (53.3% of target)
- Pace threshold: 0.717 × 75 = 53.8 → 40 < 53.8 → BEHIND (by 13.8)

Closed-lost MIA rate
- QTD actual: 5 / 25 = 0.20 (20.0%)
- Target: ≤ 0.10 (10.0%)
- Delta: 0.20 − 0.10 = +0.10 (2.0× the ceiling)
- Pace: BEHIND (lower_better; actual exceeds ceiling)

Same-quarter closes
- QTD actual: 10
- Target: 20
- Delta: 10 − 20 = −10 (50.0% of target)
- Pace threshold: 0.717 × 20 = 14.3 → 10 < 14.3 → BEHIND (by 4.3)

Active pipeline coverage
- QTD actual: $3,000,000
- Target: $4,000,000
- Delta: −$1,000,000 (75.0% of target)
- Coverage is a point-in-time stock metric, not a cumulative flow, so pace-vs-days-elapsed does not strictly apply. Against target: BEHIND by $1.0M / 25.0%.

What moved this week: Not answerable from the data provided — the files contain only QTD snapshots with no week-over-week deltas, no prior-week values, and no dated activity records. Cannot cite what moved without the underlying weekly data.

Q1: Yes. Customer data is encrypted at rest using AES-256. [P1]

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

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

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

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

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

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

Q8: Unanswerable from the provided excerpts. ISO 27001 certification status is not addressed. Would require the Bonusly security/compliance certifications inventory or trust portal certifications page.

Q9: Unanswerable from the provided excerpts. No uptime SLA percentage is stated. Would require the Master Services Agreement or Service Level Agreement document.

Q10: Unanswerable from the provided excerpts. HIPAA BAA policy is not addressed. Would require the Bonusly HIPAA/regulated-data policy or legal team's BAA stance document.

NDA-1 — GREEN (standard approval)
Reasoning: Mutual, 2-year term with 3-year survival, standard carve-outs (a)–(e), Delaware law, no license/exclusivity — quote: "Carve-outs: information that (a) is or becomes publicly available through no breach, (b) was known prior to disclosure, (c) is received from a third party without duty of confidence, (d) is independently developed, or (e) must be disclosed by law or court order."

NDA-2 — YELLOW (counsel review)
Reasoning: Embedded 18-month non-solicit with no "general solicitation / job board" carve-out — quote: "During the term of this Agreement and for eighteen (18) months thereafter, neither party shall solicit for employment or hire any employee of the other party with whom it came into contact under this Agreement."

NDA-3 — RED (full legal review)
Reasoning: One-way in Discloser's favor, 5-year term, 3-year non-compete, Republic of Ireland exclusive jurisdiction, and zero confidentiality carve-outs — quote: "For a period of three (3) years following the Effective Date, Recipient shall not, directly or indirectly, engage in or provide services to any business that competes with Discloser's business."