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 extract audit

1. DEAL DATA — NOT PROVIDED
   The request asks me to audit deal fields (owner, stage, amount, close date, why-buys) and report the top 10 fixes by pipeline amount at stake. No deals.csv was included, so those sections cannot be computed. I report only on companies and contacts.

---

2. COMPLETENESS PER FIELD

Companies (n=34)
- domain:       34/34 = 100.0%
- industry:     34/34 = 100.0%
- employee_count: 25/34 = 73.5%
- hq_country:   28/34 = 82.4%

Contacts (n=52)
- email:   52/52 = 100.0%
- title:   39/52 = 75.0%
- persona: 37/52 = 71.2%

---

3. DUPLICATE COMPANY CLUSTERS

Shared-domain clusters:

Domain: acme-corp.com
  Aliases: C-0A092931, C-0A092932
  Proposed survivor: C-0A092931 (most populated CRM row)
    C-0A092931: industry=Technology, employee_count=500, hq_country=US
    C-0A092932: industry=tech, employee_count=510, hq_country=USA

Domain: globex.io
  Aliases: C-0A092933, C-0A092934
  Proposed survivor: C-0A092933 (tie on populated fields, first alias)
    C-0A092933: industry=SaaS, employee_count=200, hq_country=US
    C-0A092934: industry=Technology, employee_count=200, hq_country=US

Note: There is no explicit company_name column, so "name variants" map directly to alias-domain duplicates in this extract.

---

4. INVALID EMAILS AND DOMAIN MISMATCHES

Invalid emails (4):
- CT-0010 | C-66D1FC | "user0@" — empty domain
- CT-0080 | C-92D97D | "user0@" — empty domain
- CT-0081 | C-92D97D | "user1@" — empty domain
- CT-0192 | C-425E2A | "user2@" — empty domain

Domain mismatches (1):
- CT-0011 | C-66D1FC | email=user1@other-domain.com, email domain=other-domain.com, company domain=66d1fc.com

---

5. ENRICHMENT FILL / CONFLICT REVIEW

ZoomInfo fills for blank CRM fields (8):

| Company | Domain | Field | CRM value | ZoomInfo value |
|---|---|---|---|---|
| C-EC3025 | ec3025.com | employee_count | (blank) | 400 |
| C-96039F | 96039f.com | employee_count | (blank) | 400 |
| C-44EA29 | 44ea29.com | employee_count | (blank) | 400 |
| C-D04904 | d04904.com | employee_count | (blank) | 400 |
| C-B23205 | b23205.com | employee_count | (blank) | 400 |
| C-60C75F | 60c75f.com | employee_count | (blank) | 400 |
| C-7BBDFA | 7bbdfa.com | employee_count | (blank) | 400 |
| C-50D386 | 50d386.com | employee_count | (blank) | 400 |

CRM vs ZoomInfo conflicts (10; all industry wording disagreements, US/USA treated as same):

| Company | Domain | Field | CRM value | ZoomInfo value |
|---|---|---|---|---|
| C-66D1FC | 66d1fc.com | industry | tech | Computer Software |
| C-EC3025 | ec3025.com | industry | Technology | Computer Software |
| C-44EA29 | 44ea29.com | industry | tech | Computer Software |
| C-92D97D | 92d97d.com | industry | Technology | Computer Software |
| C-D04904 | d04904.com | industry | Technology | Computer Software |
| C-77A95A | 77a95a.com | industry | Technology | Computer Software |
| C-AA8DDA | aa8dda.com | industry | Technology | Computer Software |
| C-B25F40 | b25f40.com | industry | Technology | Computer Software |
| C-60C75F | 60c75f.com | industry | tech | Computer Software |
| C-425E2A | 425e2a.com | industry | Tech  | Computer Software |

Recommendation on conflicts: Adopt ZoomInfo's "Computer Software" as the normalized industry value and update CRM taxonomy to prevent mixed casing/abbreviations ("tech", "Tech ", "Technology").

Missing company fields with no ZoomInfo match (7):
- C-2D1F1B (2d1f1b.com): hq_country
- C-D73B89 (d73b89.com): hq_country
- C-44EA29 (44ea29.com): hq_country
- C-D04904 (d04904.com): hq_country
- C-2C60E5 (2c60e5.com): hq_country
- C-93C8BF (93c8bf.com): employee_count
- C-EE9FFB (ee9ffb.com): hq_country

No enrichment row exists for domains 332637.com, ba969b.com, b97b4e.com, c9bb20.com, ee9ffb.com, or 2c60e5.com beyond what is shown; some fields remain unfillable.

---

6. TOP 10 FIXES BY PIPELINE AMOUNT AT STAKE

Cannot be computed — deals.csv was not provided. Without deal amount and company mapping, no pipeline value can be assigned to any fix.

---

PROPOSED FIXES (priority order, limited to available data)

1. Merge duplicate company clusters
   - acme-corp.com: keep C-0A092931, deprecate C-0A092932, reconcile employee_count 500 vs 510.
   - globex.io: keep C-0A092933, deprecate C-0A092934, reconcile industry SaaS vs Technology.

2. Fix invalid emails
   - CT-0010, CT-0080, CT-0081, CT-0192: complete or replace partial emails.

3. Fix domain mismatch
   - CT-0011: reverify email user1@other-domain.com against C-66D1FC or associate with the correct company.

4. Fill blank employee_count from ZoomInfo
   - C-EC3025, C-96039F, C-44EA29, C-D04904, C-B23205, C-60C75F, C-7BBDFA, C-50D386.

5. Normalize industry conflicts to "Computer Software"
   - C-66D1FC, C-EC3025, C-44EA29, C-92D97D, C-D04904, C-77A95A, C-AA8DDA, C-B25F40, C-60C75F, C-425E2A.

6. Title backfill on contacts (13 missing)
   - Example aliases: CT-0000, CT-0022, CT-0041, CT-0060, CT-0072, CT-0082, CT-0092, CT-0120, CT-0121, CT-0122, CT-0132, CT-0162, CT-0170, CT-0171, CT-0172, CT-0180, CT-0181. (Exact list from CSV.)

7. Persona backfill on contacts (15 missing)
   - Example aliases: CT-0000, CT-0022, CT-0041, CT-0060, CT-0070, CT-0072, CT-0081, CT-0082, CT-0092, CT-0110, CT-0171, CT-0172, CT-0180, CT-0181. (Exact list from CSV.)

8. Employee-count gaps with no enrichment (1)
   - C-93C8BF (93c8bf.com): employee_count missing, no ZoomInfo row.

9. HQ-country gaps with no enrichment (5 plus others)
   - C-2D1F1B, C-D73B89, C-44EA29, C-D04904, C-2C60E5, C-EE9FFB are missing hq_country; only some have enrichment rows but those rows themselves lack hq_country.

10. Request deals.csv
    - Required to compute pipeline-at-stake ranking, deal-field completeness, and tie fixes to revenue impact.

---

I can rerun the pipeline-amount ranking immediately if you provide deals.csv.

**Real product gaps (prospect-raised, confirmed missing in product docs)**

| Deal alias | Prospect line (quoted) | Gap | Product docs basis | Amount |
|---|---|---|---|---|
| Deal-EC3025 | "We need SCIM user provisioning — our security team will not approve any tool that requires manual account management." | SCIM user provisioning | "SCIM user provisioning ... are NOT currently listed as supported capabilities." | Not provided in source data |
| Deal-D0D6B5 | "Our payroll runs on ADP Workforce Now and I don't see ADP anywhere in your integration list — that's a dealbreaker for us." | ADP Workforce Now integration | "ADP Workforce Now integrations are NOT currently listed as supported capabilities." | Not provided in source data |

**Other candidates classified**

| Deal alias | Prospect line | Classification | Why |
|---|---|---|---|
| Deal-CFE7F4 | "I tried to build a custom report combining recognition frequency with turnover and couldn't — is that possible on our current plan?" | Plan gate | Custom report builder exists but is Enterprise-only, per plan table. |
| Deal-84DBA6 | "We turned on the Slack integration in July, but half our managers still haven't given a single recognition — nobody ever trained them on it." | Rollout/enablement issue | Slack integration is supported on all plans; problem is manager training/adoption. |
| Deal-36C33F | — | Not a prospect-raised gap | The mobile-app limitation was disclosed by rep Alex Franklin, not raised by the prospect. The prospect responded that the web version would suffice. Rep language excluded per instruction. |

**Note:** Deal amounts are not present in `transcripts_gaps.csv` (columns are `transcript_id, deal_alias, speaker, line_text` only), so amounts are listed as missing.

Last 10 calls: TT-001 through TT-010 (Deal-D348E1, Deal-5408B0, Deal-547B2B, Deal-403845, Deal-C61CF7, Deal-60C2C2, Deal-EDC141, Deal-D9A12F, Deal-1E2498, Deal-84DBA6).

What the rep leads with (first 5 minutes):
- 8 of 10 calls: the 400-person retailer / 18% turnover story.
  - 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, Alex Franklin, minute 0)
- Deal-403845 (TT-004): security review + pricing agenda.
  - Quote: "I put together a short agenda — security review first, then pricing."
- Deal-1E2498 (TT-009): straight pricing.
  - Quote: "You asked for straight pricing last time, so let's start there."

Three most common objections and how handled:
1. "Budget is locked until next fiscal year" — 4 of 10 calls (TT-001, TT-003, TT-006, TT-010).
   - Response: tie to turnover savings / $210k backfill example.
   - 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, Alex Franklin, minute 8)

2. "Can we revisit it next quarter?" — 3 of 10 calls (TT-002, TT-005, TT-008).
   - Response: propose a 90-day single-department pilot to generate internal data before planning.
   - 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, Alex Franklin, minute 8)

3. "We already do recognition with a spreadsheet and quarterly gift cards — why would we change?" — 3 of 10 calls (TT-004, TT-007, TT-009).
   - Response: contrast manual process with automation + analytics.
   - 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, Alex Franklin, minute 8)

Concrete next step agreed rate:
- Rep asks "Should we lock the next step..." on 7 calls and gets yes (TT-001, TT-002, TT-003, TT-005, TT-006, TT-008, TT-009).
- No concrete next step on 3 calls: TT-004 ("I'll leave it with you"), TT-007 ("Fair enough"), TT-010 ("Understood, thanks for the candor").
- Rate: 7 / 10 = 70%.

Competitors raised by prospects:
- Awardco — Deal-547B2B (TT-003): "We're also in late talks with Awardco — their rewards catalog looks bigger than yours."
- Kudos — Deal-EDC141 (TT-007): "How are you different from Kudos? Our CEO used them at her last company."
- Workhuman was mentioned only by the rep, not a prospect, so it is excluded.

Coaching notes:
1. The "lock the next step" close is strong when used (70% success), but the rep skips it entirely on calls where the prospect signals delay or committee approval — exactly the moments where a concrete next step matters most. Add a soft commit even when the answer is "not yet," e.g., a calendar hold for a follow-up call or a named stakeholder to loop in.
2. Status-quo ("spreadsheet and gift cards") and timing ("next quarter") objections are both handled with a one-size-fits-all message. Test tying the response to the specific deal's context — for example, asking how many hours HR currently spends per month on the spreadsheet before pitching automation.

Redemption section — weekly rewards report (last completed month: 2026-08)

- **Reporting period:** 2026-01-01 through 2026-08-31
- **Redemption count:** 377
- **Redemption spend:** $27,771.00
- **Unique redeemers:** 235
- **Redemptions per redeemer:** 377 / 235 = 1.60

**Provider mix (% of spend)**
- custom: $10,873.00 = 39.15%
- Tremendous: $8,430.00 = 30.36%
- Snappy: $5,238.00 = 18.86%
- TangoCard: $3,230.00 = 11.63%
- **Total:** 100.00%

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

**Q2 support-ticket synthesis (ranked by ARR exposure, not volume)**

5 themes found. Billing-and-invoice errors is single-account noise but material ARR, so retained as its own theme.

| Rank | Theme | Count | Share | Distinct accounts | ARR affected | Sample ticket IDs | One-line recommendation |
|---|---:|---:|---:|---:|---:|---:|---|
| 1 | HRIS provisioning failures | 10 | 13.0% | 3 (C-0B2213A9, C-0DDFC9A7, C-0F6C0F34) | **$114,000** | IC-460059, IC-460062 | Audit HRIS sync logs against silent skips; add provisioning status dashboard for admins. |
| 2 | Redemption and checkout failures | 18 | 23.4% | 7 (C-0B827671, C-0CEF69FD, C-0F876796, C-0FCCD2DF, C-14264ABD, C-0D9CA315, C-0B0F1BAB) | **$68,800** | IC-460025, IC-460035 | Fix checkout timeout path and restore deducted points before retry; introduce rollback + retry queue. |
| 3 | Billing and invoice errors | 15 | 19.5% | 1 (C-0E9C27D1) | **$52,000** | IC-460071, IC-460069 | Escalate single-account billing accuracy review; reconcile seat count and renewal tier before next invoice run. |
| 4 | Points not posting / balance not updating | 20 | 26.0% | 9 (C-0D3278C7, C-0BE96399, C-0D0B047C, C-0BF20542, C-0D284E42, C-0D6CC8E3, C-0DD0626C, C-0B2895EF, C-21FEBCBB) | **$31,100** | IC-460004, IC-460001 | Trace async points ledger pipeline; surface delivery-vs-credit mismatch to users instantly. |
| 5 | Slack integration failures | 14 | 18.2% | 4 (C-0B843542, C-0BA71F12, C-10A56B0F, C-8C2E8F00) | **$18,900** | IC-460041, IC-460049 | Harden OAuth re-auth flow and stop the sync toggle from self-resetting after reconnect. |

**Arithmetic**
- Total tickets with body text: 77 of 79 (2 rows with empty `body_text` excluded because themes must be read from text, not tags).
- Total unique accounts exposed: 24.
- Total unique ARR exposed across all themes: $284,800.
- Shares are `theme count / 77`.
- ARR affected is the sum of unique account ARR per theme (a single account’s ARR counted once even if it filed multiple tickets).

**Pattern vs. noise**
- Broad patterns: HRIS provisioning, redemption/checkout, points posting, and Slack span 3+ accounts each.
- Single-account noise: Billing and invoice errors are concentrated entirely in **C-0E9C27D1** ($52K ARR), so it is a narrow but high-exposure issue rather than a quarter-wide pattern.

Q3-2026 update (66 of 92 days elapsed = 71.7% of quarter)

Metric                          | QTD actual | Target   | Delta       | Pace vs. elapsed
--------------------------------|------------|----------|-------------|-----------------
SQMs                            | 230        | 300      | -70         | ahead   (230/300 = 76.7% vs 71.7% elapsed)
SQOs                            | 84         | 120      | -36         | behind  (84/120 = 70.0% vs 71.7% elapsed)
DS2s                            | 40         | 75       | -35         | behind  (40/75 = 53.3% vs 71.7% elapsed)
Closed-lost MIA rate            | 20.0%      | 10.0%    | +10.0 pp    | behind  (5/25 = 0.20, above 0.10 target)
Same-quarter close count        | 10         | 20       | -10         | behind  (10/20 = 50.0% vs 71.7% elapsed)
Active pipeline coverage        | $3.0M      | $4.0M    | -$1.0M      | ahead   ($3.0M/$4.0M = 75.0% vs 71.7% elapsed)

Arithmetic:
- Days elapsed share = 66 / 92 = 71.7%
- Closed-lost MIA rate = 5 / 25 = 0.20 = 20.0%
- Active pipeline coverage = $3,000,000 / $4,000,000 = 0.75x

What moved this week: No week-over-week data was provided, so I cannot report what specifically moved this week. The figures above are cumulative QTD totals as of 66 days into Q3-2026.

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, and it 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 subprocessor list is maintained at trust.bonusly.com, and 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. The policy excerpts do not address ISO 27001 certification. A current certification register or compliance attestation letter would answer this.

Q9. Unanswerable. The policy excerpts do not state a contractual uptime SLA percentage. The service-level agreement or master subscription agreement would answer this.

Q10. Unanswerable. The policy excerpts do not address HIPAA or willingness to sign a Business Associate Agreement. A compliance statement, BAA policy, or sales/legal contract representative would answer this.

**NDA-1 — [PARTY A] and Bonusly**
GREEN — Standard mutual NDA with conventional 2-year term, 3-year survival, complete carve-outs, Delaware governing law, and no hidden restrictions.

**NDA-2 — [PARTY B] and Bonusly**
YELLOW — Embedded employee non-solicit requires counsel review.
Clause: "During the term of this Agreement and for eighteen (18) months thereafter, neither party shall solicit for employment or hire any employee of the other party with whom it came into contact under this Agreement."

**NDA-3 — [PARTY C] and Bonusly**
RED — Full legal review required due to broad non-compete, missing carve-outs, and non-standard Ireland jurisdiction.
Clause (non-compete): "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."
Clause (missing carve-outs): "No confidentiality carve-outs are stated in this Agreement."
Clause (governing law): "This Agreement shall be governed by and construed in accordance with the laws of the Republic of Ireland, and the parties submit to the exclusive jurisdiction of its courts."