Section 15 · Deal Autopsy & Sales Coaching
15.4Management problem detection
Designed for Phase 2- No.
- 15.4
- DMA's reference
- Decision Book p.30
- Phase
- Phase 2
- Autonomy
- L1 · Recommend
- DMA's decision
- Yes
What DMA asked for · Decision Book p.30
Tell whether the real problem is lead quality, sales execution, pricing, proof, speed or fit.
Why it matters to DMA: The highest-level insight in the coaching cluster; it tells DMA where to invest next.
In our words, from DMA's Product Decision Book v3, page 30.
How we do it
- Scheduled for Phase 2, on top of 15.1 and 15.2.
- Code groups the loss reasons and patterns into the book's six problem areas and compares each with the win side (15.5).
- The result is a short ranked list for leadership, each area with its share of lost value and two example deals.
Already in place
- The audit already classifies every lost deal into a lost-reason code (price, timing, existing agency, no budget, competitor, poor fit, other), quoting the note it came from, or "not enough evidence" when the notes don't say.
- The backtest already replays the scoring against past outcomes and reports how well the score ranked the accounts that revived and the deals that were won (Measurement; synthetic history in the POC).
What the later phase adds
- The mapping from reasons to the six problem areas.
- A ranked list by lost value, for leadership.
The flow
It plays on its own while it's on screen; hover or use the controls to pause or step through.
Inputs
The loss reasons and patterns.
- Stored data
- Rule in code
- Screen
Where the data goes
The same six stages on every page. Nothing reaches Nutshell except through the write gate.
- 1Nutshell
Source
Won and lost deals, notes and calls.
- 2Sync
Copies Nutshell changes into the bridge database
Mirrors outcomes as they close.
- 3Bridge database
A copy of the CRM data, plus what the AI works out
Reason codes with their evidence; the patterns found.
- 4AI
Claude models, only through DMA's own gateway
Reads notes and summaries; code counts the patterns.
- 5Write gate
The only way back into Nutshell: checked, approved when needed, sent once
Not involved: this is analysis, nothing is written to Nutshell.
- 6Nutshell
The system of record
Unchanged.
The tables behind it
Drawn from the POC's database catalogue: structure only, no data.
PK primary keyFK reference the database enforces (solid line)ID reference kept by id (dashed line)
| Table | What it holds | Columns |
|---|---|---|
| crm.leads | Deals mirrored from Nutshell, with outcome, value and close date. | 26 |
| crm.outcomes | Nutshell's outcome list (won, lost and their reasons). | 13 |
| ai.extracted_facts | Facts from the notes with their evidence quotes. | 15 |
How the tables connect (1)
| Column | Points to | Kept by |
|---|---|---|
| ai.extracted_facts.prompt_id | agent.prompts | The application (by id) |
Worked example
Synthetic demo data: every name, business and number is made up.
A designed ranking (synthetic example).
Where lost value comes from
| Area | Share of lost value |
|---|---|
| Speed (slow first follow-up) | 34% |
| Proof (no vertical case study) | 27% |
| Pricing | 19% |
| Fit, lead quality, execution | 20% |
In the running POC
There is no screen for this one yet: it is designed for Phase 2, as DMA's book decides. The parts listed under “Already in place” run in the POC today.
See it live
Opens the exact screen in the running POC, in a new tab.
| Open | Where | What to try |
|---|---|---|
| Measurement | DMA AI dashboard | The backtest of the scoring against past outcomes (synthetic in the POC). |
Status
Designed for Phase 2. DMA's book schedules this for Phase 2. The design is ready and builds on parts that already run in the POC.