Confidential · © 2026 Space-O Technologies Inc. · Prepared exclusively for DMA. Please do not copy, save or share.

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

20.12Extract facts from email threads

Designed for Phase 2
No.
20.12
DMA's reference
Decision Book p.38
Phase
Phase 2
Autonomy
L2 · Prepare, then wait for approval
DMA's decision
Yes

What DMA asked for · Decision Book p.38

Extract facts from e-mail threads.

Why it matters to DMA: Budgets, dates and objections are often written, not said.

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

How we do it

  • Scheduled for Phase 2 in DMA's book.
  • The call scribe's reader and checks run on each e-mail thread: facts with exact quotes, promises with dates, all proved by code before they are kept.

Already in place

  • The scribe's extraction and quote checks (20.1–20.4).
  • E-mail replies are already stored and classified by the reply handler.

What the later phase adds

  • Reading each thread for facts and promises, with the same one-click approval.

The flow

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

E-mail threadstoredRead + checkedquotes provedFacts, tasksone approval
Step 1 of 3

A thread

"We can start in November, budget is $4k."

  • Stored data
  • AI
  • Screen

Where the data goes

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

  1. 1E-mail

    Source

    E-mail threads with prospects.

  2. 2Sync

    Copies Nutshell changes into the bridge database

    Not involved.

  3. 3Bridge database

    A copy of the CRM data, plus what the AI works out

    Facts with quotes.

  4. 4AI

    Claude models, only through DMA's own gateway

    Reads and quotes; code proves.

  5. 5Write gate

    The only way back into Nutshell: checked, approved when needed, sent once

    Changes wait for one approval.

  6. 6Nutshell

    The system of record

    Nutshell is not changed.

The tables behind it

Drawn from the POC's database catalogue: structure only, no data.

ai.extracted_factsPKiduuidfact_keytextvaluejsonbconfidencenumericevidence_quotetextobserved_attimestampstatustextIDprompt_iduuid+ 7 more columns

PK primary keyFK reference the database enforces (solid line)ID reference kept by id (dashed line)

TableWhat it holdsColumns
ai.extracted_factsFacts the AI found, each with the exact quote it came from and a confidence.15
How the tables connect (1)
ColumnPoints toKept by
ai.extracted_facts.prompt_idagent.promptsThe application (by id)

Worked example

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

A designed example (synthetic).

From a reply

Said
"We can start in November, budget is $4k a month."
Facts
Timeline: November · Budget: $4,000 a month

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.

Status

Designed for Phase 2

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.

20.12 Extract facts from email threads · DMA AI proof