Section 20 · Sales Rep Work Elimination / Zero-Entry CRM

20.13Extract facts from call/meeting transcripts

Built in the POC

What DMA asked for · Decision Book p.38

Extract facts from call and meeting transcripts into the account's history.

Why it matters to DMA: The book places this in Phase 2; it is built already, as part of the call scribe.

In our words, from DMA's Product Decision Book v3, page 38.

Every logged call adds its facts to the account, each with the prospect's words and a confidence: budget, services, timing, incumbent, decision maker, objections.
Facts from calls sit next to facts from old notes (20.11), so the account's brief and next best action use both.

It plays on its own while it's on screen; hover or use the controls to pause or step through.

Step 1 of 4

Logged

A call on the account.

The same six stages on every page. Nothing reaches Nutshell except through the write gate.

1Call transcript
Source
A call transcript: pasted, or a Zoom .vtt / .txt file dropped on the account (text only, 512 KB at most).
2Sync
Copies Nutshell changes into the bridge database
Reads the account, people and open deals from the mirror, to match the call to the right company.
3Bridge database
A copy of the CRM data, plus what the AI works out
The run, the facts with their quotes and the e-mail draft are stored; the transcript is kept encrypted.
4AI
Claude models, only through DMA's own gateway
The fast model reads the call and copies exact words; code checks every quote, date and amount. The conversation model drafts the follow-up.
5Write gate
The only way back into Nutshell: checked, approved when needed, sent once
Every change waits as one batch for one approval, then leaves through the write gate with 30 seconds to undo.
6Nutshell
The system of record
The note, the tasks and the fields appear on the deal, marked as written by DMA AI.

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
ai.extracted_facts	Facts the AI found, each with the exact quote it came from and a confidence.	15
ai.scribe_runs	One row per logged call: the transcript's fingerprint, the account it matched, the extraction and the approval batch it produced.	24

How the tables connect (3)

Column	Points to	Kept by
ai.extracted_facts.prompt_id	agent.prompts	The application (by id)
ai.scribe_runs.conversation_id	conv.conversations	The database (foreign key)
ai.scribe_runs.approval_id	ctrl.approvals	The database (foreign key)

Synthetic demo data: every name, business and number is made up.

The facts kept from one call.

Fact	Value	What the prospect said
Budget	$6,000 a month	"We can do about six thousand a month now across the three shops."
Services	Paid search and Google Business listings	"If we took over paid search and your Google Business listings, what budget are you thinking?"
Timeline	Decide by October 15	"I want to decide by October 15 so we're running before the winter rush."
Incumbent	Nephew runs Google Ads	"My nephew runs our Google Ads in his spare time."
Decision maker	Greg Hollis owns all three shops	"Just me. I own all three shops, so it's my call."
Objection	Won't sign longer than month to month	"I won't sign anything longer than month to month."

localhost:13301/approvals

The CRM updates from one logged call, waiting for one-click approval (a real run on synthetic data).

1The call's changes; the facts kept are listed below the tasks.
2The follow-up e-mail, drafted and claim-checked; approving saves it, it never sends.
3One click approves the whole batch; each line can also be edited or dropped.

Dashboard · Approvals, the CRM updates from one call transcript. Captured from the running POC on September 25, 2026; synthetic data.

Opens the exact screen in the running POC, in a new tab.

Open	Where	What to try
Accounts → Log a call	DMA AI dashboard	Open an account and paste or drop a Zoom transcript.
Today	DMA AI dashboard	The accounts worth a call today, each with why now.

Built in the POC

Built in the POC. This capability runs in the POC today, on synthetic data, end to end.