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

Section 8 · AI Mini-Consultant — Earn the Meeting

8.2Estimated business impact

Partly built — finishing in Phase 1
No.
8.2
DMA's reference
Decision Book p.19
Phase
Phase 1
Autonomy
L2 · Prepare, then wait for approval
DMA's decision
Yes

What DMA asked for · Decision Book p.19

Put each problem in business terms (wasted spend, missed traffic, lost visibility), not technical ones.

Why it matters to DMA: Business language convinces owners far better than technical language. DMA's book adds a firm limit: it must stay defensible, with no invented numbers.

In our words, from DMA's Product Decision Book v3, page 19.

How we do it

  • Every finding already carries a "why it matters" line in business terms: new patients who can't find the practice, visitors who leave a slow page, offices missing from map results.
  • Numbers are held back on purpose. The chat's rules forbid estimating revenue, traffic, rankings or return, and the claims check blocks any figure that doesn't come from an approved source.
  • What's still to finish for Phase 1 is the sized version: an impact figure only when it can be backed, from data the prospect gives (their ad spend, their call volume) or from DMA's approved benchmarks, and only in wording DMA approves.

Already in place

  • A business-terms "why it matters" line on every finding.
  • Rules and a claims check that stop any invented number.
  • Approved-content storage, where DMA's benchmarks would live as versioned, approved claims.

What the later phase adds

  • DMA's approved benchmarks (for example, typical conversion rates by industry) entered as approved claims.
  • A sized estimate only when the visitor has given the inputs, shown with its source and as a range DMA approves.

The flow

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

Phase 1 finishFindingwith evidenceWhy it mattersbusiness termsVisitor's own numberse.g. ad spendApproved benchmarksDMA'sClaims checkno unsourced numbersReplydefensible
Step 1 of 4

A finding

The home page weighs 6 MB.

  • Stored data
  • AI
  • Person
  • Rule in code
  • Screen

Where the data goes

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

  1. 1Website and chat

    Source

    The findings, and anything the visitor says about their numbers.

  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

    The findings and approved content.

  4. 4AI

    Claude models, only through DMA's own gateway

    Writes the business-terms line; never invents a figure.

  5. 5Write gate

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

    Carries the review to the lead.

  6. 6Nutshell

    The system of record

    The rep sees the findings in business terms.

The tables behind it

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

ai.site_reviewsPKiduuidIDconversation_iduuidstatustextfindingsjsonbIDprompt_iduuid+ 13 more columnsai.kb_documentsPKdoc_keytextPKversionintegerkindtextclaimsjsonbstatustextIDapproval_iduuid+ 11 more columns

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

TableWhat it holdsColumns
ai.site_reviewsEach finding with its evidence and its "why it matters" line.18
ai.kb_documentsApproved content with its claims; benchmarks would be stored here.17
How the tables connect (3)
ColumnPoints toKept by
ai.site_reviews.conversation_idconv.conversationsThe application (by id)
ai.site_reviews.prompt_idagent.promptsThe application (by id)
ai.kb_documents.approval_idctrl.approvalsThe application (by id)

Worked example

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

From the BrightSmile Dental demo review (synthetic).

Technical finding → business terms

What the review foundWhat the visitor reads
<title>Home</title>Google shows this title in search results, so new patients searching for a dentist in Cedar Hollow are less likely to find and click the site.
3 location pages (/locations/downtown/, /locations/northgate/, /locations/lakeside/): no Google Maps link and no LocalBusiness schemaPatients can't easily get directions, and Google may not show the three offices properly in local and map results.
hero.jpg · 4.82 MB, 3200×2000, no srcset; home page total 6.10 MBA 6 MB page loads slowly on phones, and visitors leave before they see the booking options.

In the running POC

The visitor pastes their website: the review runs inside the chat and the three findings arrive as a card.

The visitor pastes their website: the review runs inside the chat and the three findings arrive as a card.

  1. 1The three findings, each with the evidence the review found on the site.
  2. 2Booking is one click away at every step.

Website chat · BrightSmile Dental demo site, after the site address. Captured from the running POC on September 25, 2026; synthetic data.

See it live

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

OpenWhereWhat to try
BrightSmile Dental demo siteDemo prospect websiteAsk the chat how much the slow page is costing you: it won't invent a number.

Status

Partly built — finishing in Phase 1

Partly built — finishing in Phase 1. The parts run in the POC today; the rule that joins them is being finished for Phase 1.

8.2 Estimated business impact · DMA AI proof