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

Section 15 · Deal Autopsy & Sales Coaching

15.2Find patterns across hundreds of deals

Designed for Phase 2
No.
15.2
DMA's reference
Decision Book p.29
Phase
Phase 2
Autonomy
L1 · Recommend
DMA's decision
Yes

What DMA asked for · Decision Book p.29

Find patterns across hundreds of deals, for example "we lose too many enterprise SEO proposals because we lack proof in that vertical".

Why it matters to DMA: It turns single loss reasons into strategic problems DMA can fix.

In our words, from DMA's Product Decision Book v3, page 29.

How we do it

  • Scheduled for Phase 2, after 15.1.
  • Code, not the AI, counts the loss reasons by service, vertical, deal size, source and rep, and flags combinations that are far above the average.
  • The AI then writes each flagged pattern as one plain sentence, citing the counts and two or three 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.
  • Service lanes and verticals are already recorded for every account by the audit.

What the later phase adds

  • The counts by segment and the "far above average" rule.
  • One plain sentence per pattern, with the numbers and examples.

The flow

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

Loss reasonsfrom 15.1Countsby service, vertical…Above average?flag itOne sentencewith the numbers
Step 1 of 4

All the reasons

Every lost deal has its reason from 15.1.

  • Stored data
  • Rule in code
  • Routing
  • AI

Where the data goes

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

  1. 1Nutshell

    Source

    Won and lost deals, notes and calls.

  2. 2Sync

    Copies Nutshell changes into the bridge database

    Mirrors outcomes as they close.

  3. 3Bridge database

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

    Reason codes with their evidence; the patterns found.

  4. 4AI

    Claude models, only through DMA's own gateway

    Reads notes and summaries; code counts the patterns.

  5. 5Write gate

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

    Not involved: this is analysis, nothing is written to Nutshell.

  6. 6Nutshell

    The system of record

    Unchanged.

The tables behind it

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

crm.leadsPKiduuidnametextstatustextvalue_amountnumericoutcome_idtextclosed_attimestamp+ 20 more columnscrm.outcomesPKiduuidnametextkindtext+ 10 more columnsai.extracted_factsPKiduuidfact_keytextconfidencenumericevidence_quotetextIDprompt_iduuid+ 10 more columns

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

TableWhat it holdsColumns
crm.leadsDeals mirrored from Nutshell, with outcome, value and close date.26
crm.outcomesNutshell's outcome list (won, lost and their reasons).13
ai.extracted_factsFacts from the notes with their evidence quotes.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 pattern (synthetic example).

Pattern

Finding
Enterprise SEO proposals are lost on weak proof three times as often as others.
Numbers
11 of 17 enterprise SEO losses cite missing vertical proof, against 18% across all losses.
Examples
Lakeview Orthodontics, Summit Legal Group, Pinecrest Clinics

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.

15.2 Find patterns across hundreds of deals · DMA AI proof