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

Section 2 · Qualification & Opportunity Scoring

2.5Multi-service detection

Built in the POC
No.
2.5
DMA's reference
Decision Book p.12
Phase
Phase 1
Autonomy
L2 · Prepare, then wait for approval
DMA's decision
Yes

What DMA asked for · Decision Book p.12

Notice when someone asking about SEO is really a PPC + SEO + reputation opportunity.

Why it matters to DMA: Surfacing the whole opportunity, not just the entry point, raises the average deal size.

In our words, from DMA's Product Decision Book v3, page 12.

How we do it

  • Every account and every chat is tagged with the DMA services that fit, from DMA's list: SEO, local search, paid search, reputation, social, web development, marketing automation, enterprise.
  • The tags come from three places: the products on past Nutshell deals, the AI's reading of the notes (kept only when it is confident), and, in the website chat, what the visitor says about their needs.
  • Fitting two or more core services raises the fit part of the score and shows as "fits several services" in the reasons, so the team sees the bigger opportunity at a glance.
  • It stays a recommendation (L2): it shapes the brief, the next step and the proposal draft, and a person decides what to offer. Proposals can only use services on DMA's approved rate card.

The flow

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

Past dealsproducts boughtNotes and chatswhat they needAI tags servicesconfident ones onlyServices that fitDMA's listFit in the scoreseveral servicesBrief and proposala person decides
Step 1 of 4

Clues from the past

Northside once bought SEO; that deal's product maps to the SEO service.

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

Where the data goes

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

  1. 1Deals, notes, chats

    Source

    Products on past deals, the notes, the visitor's words.

  2. 2Sync

    Copies Nutshell changes into the bridge database

    Brings deal products from Nutshell.

  3. 3Bridge database

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

    The service tags per account and per chat, with the evidence.

  4. 4AI

    Claude models, only through DMA's own gateway

    Tags services from the notes and chats; only confident tags are kept.

  5. 5Write gate

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

    The services go onto the lead's AI fields.

  6. 6Nutshell

    The system of record

    The team sees which services fit.

The tables behind it

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

tax.classificationsPKiduuiddimensiontextFKnode_iduuidnode_codetextconfidencenumericsourcetextIDprompt_iduuid+ 12 more columnsai.scoresPKiduuidscoresmallinttiertextreason_codesjsonbIDprompt_iduuid+ 15 more columnstax.nodesPKiduuidFKdimensiontextFKversionintegercodetextlabeltextattributesjsonb+ 7 more columns

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

TableWhat it holdsColumns
tax.classificationsService tags on each record, with the evidence and confidence.19
ai.scoresThe fit reason and its points.20
tax.nodesDMA's list of services, with a margin weight per service.13
How the tables connect (5)
ColumnPoints toKept by
tax.classifications.node_idtax.nodesThe database (foreign key)
tax.classifications.prompt_idagent.promptsThe application (by id)
ai.scores.prompt_idagent.promptsThe application (by id)
tax.nodes.dimensiontax.taxonomy_versionsThe database (foreign key)
tax.nodes.versiontax.taxonomy_versionsThe database (foreign key)

Worked example

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

Northside's services, from evidence to the score

1 / 3

What you see

1.The facts behind the tags

Account 360 shows the notes the services were read from.

localhost:13301/accounts
Account 360: the facts the services were read from.
Callout 2

What happens in the system

  • Bridge databasecrm.leads

    A past SEO deal: its product maps to the SEO service.

  • AI agentreactivation analyst

    Reads the notes; tags local search from "all three offices" and local calls.

  • Bridge databasetax.classifications

    Each tag with its source and confidence; weak tags are dropped.

Three synthetic records from the demo data, with the services the prototype tagged.

Services detected

AccountCame in forServices that fitWhy
Northside Dental GroupSEOSEO, local searchA past SEO deal; "all three offices" and local calls in the notes
Keller Law GroupPaid searchPaid search, SEOA PPC deal; notes about weak organic traffic
Summit HVACLocal searchLocal search, paid search3 locations; paid search in the notes about the busy season

In the running POC

localhost:13301/accounts
Account 360: the facts the services were read from.

1 / 3Account 360: the facts the services were read from.

  1. 1The next best action.
  2. 2Facts by note.
  3. 3The contract-end fact.

Dashboard · Accounts, Northside Dental Group open. 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
AccountsDMA AI dashboardOpen an account: facts and services that fit.

Status

Built in the POC

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

2.5 Multi-service detection · DMA AI proof