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

Section 16 · Management Intelligence — Ask the Business Questions

16.2Why aren't we closing X?

Designed for Phase 3
No.
16.2
DMA's reference
Decision Book p.31
Phase
Phase 3
Autonomy
L1 · Recommend
DMA's decision
Yes

◆ Amended in v3 of the book.

What DMA asked for · Decision Book p.31

Answer "why aren't we closing X?" by analysing CRM history and conversations for a vertical or service.

Why it matters to DMA: DMA's amendment treats it as part of management intelligence, answered from the connected CRM and deal data.

In our words, from DMA's Product Decision Book v3, page 31.

How we do it

  • Scheduled for Phase 3, on top of the deal autopsy (section 15).
  • The workspace assistant gets one more read-only tool: given a vertical or service, it returns the win rate, the top loss reasons with evidence, and how long deals sat in each stage, all computed in code.
  • The assistant explains the result in plain words and names the examples; it cannot change anything.

Already in place

  • The team workspace already answers plain-English questions through read-only tools (16.1).
  • Lost deals are already coded with a reason and a quoted note.

What the later phase adds

  • A read-only "why aren't we closing" tool over the autopsy data.
  • Stage-duration figures per vertical and service.

The flow

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

Questionvertical or serviceWorkspace assistantpicks the toolAutopsy toolcomputed in codeAnswerwith evidence
Step 1 of 3

The question

"Why aren't we closing legal PPC?"

  • Person
  • AI
  • Rule in code
  • Screen

Where the data goes

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

  1. 1Team workspace

    Source

    The question.

  2. 2Sync

    Copies Nutshell changes into the bridge database

    Keeps deals and outcomes current.

  3. 3Bridge database

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

    Loss reasons, stage history, outcomes.

  4. 4AI

    Claude models, only through DMA's own gateway

    Explains the computed result.

  5. 5Write gate

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

    Not involved: read-only.

  6. 6Nutshell

    The system of record

    Unchanged.

The tables behind it

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

crm.lead_stage_historyPKlead_iduuidPKstage_idtextPKentered_attimestampexited_attimestampseconds_in_stagebigint+ 2 more columnscrm.leadsPKiduuidnametextstatustextvalue_amountnumeric+ 22 more columns

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

TableWhat it holdsColumns
crm.lead_stage_historyHow long each deal spent in each stage.7
crm.leadsDeals with outcome and value.26

Worked example

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

A designed answer (synthetic example).

"Why aren't we closing legal PPC?"

Win rate
18% over the last 12 months, against 31% for all PPC
Top reason
Price: 6 of 11 losses, e.g. "went with a cheaper freelancer"
Where it stalls
Proposal stage: 23 days on average, against 9 for all PPC

In the running POC

There is no screen for this one yet: it is designed for Phase 3, as DMA's book decides. The parts listed under “Already in place” run in the POC today.

Status

Designed for Phase 3

Designed for Phase 3. DMA's book schedules this for Phase 3 (decision: later). The design is ready and builds on parts that already run in the POC.

16.2 Why aren't we closing X? · DMA AI proof