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

Section 9 · Buyer Psychology & Sales Method

9.7Dynamic Sales Methodology Orchestration

Partly built — finishing in Phase 1
No.
9.7
DMA's reference
Decision Book p.22
Phase
Phase 1
Autonomy
L3 · Act within rules
DMA's decision
Yes

◆ Amended in v3 of the book.

What DMA asked for · Decision Book p.22

Choose and blend consultative, Sandler, Challenger and BANT-lite selling from the signals in the conversation, and change approach as new evidence appears.

Why it matters to DMA: The AI should know when to use each method and when to switch. DMA's book builds it only on signals the chat already produces (committee-aware MEDDIC stays in Phase 2).

In our words, from DMA's Product Decision Book v3, page 22.

How we do it

  • Every turn, the conversation service recomputes the signals and passes them to the strategist: buyer type, what is still missing, objections raised, the inbound score, and whether the booking criteria are met.
  • What runs today: the method is chosen each turn (consultative by default, BANT-lite for an executive who wants it short); each buyer type has its own approach (shorter path, evidence first, teach first); objections switch to DMA's approved answers; and meeting the booking criteria switches from diagnosing to closing.
  • To finish for Phase 1: one method rule set that also weighs the score, deal size and multi-service fit, kept as data DMA approves, and a record of which method each reply used so reporting can compare them.

Already in place

  • The per-turn signals: buyer type, objections, services that fit, the inbound score and the booking criteria.
  • A method chosen every turn (consultative or BANT-lite), and approaches per buyer type and per objection.
  • Versioned, approved instructions with a test suite before any change goes live.

What the later phase adds

  • A method rule set that also uses the score, deal size and multi-service fit.
  • The chosen method recorded on each reply, for reporting.

The flow

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

Signalsbuyer type · objections ·scoreMethod choiceevery turnConsultativedefaultBANT-liteshortReplyadapted
Step 1 of 5

Signals are recomputed

After every exchange.

  • Stored data
  • Rule in code
  • AI
  • Screen

Where the data goes

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

  1. 1Website chat

    Source

    What the visitor writes.

  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 per-turn signals and notes.

  4. 4AI

    Claude models, only through DMA's own gateway

    Follows the method chosen for the turn.

  5. 5Write gate

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

    Writes the lead, its score and the summary if the visitor books or leaves an email.

  6. 6Nutshell

    The system of record

    The rep sees the summary and the score.

The tables behind it

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

conv.conversationsPKiduuidchanneltextstagetextIDagent_version_iduuidstarted_attimestamp+ 17 more columnsconv.messagesPKiduuidFKconversation_iduuidseqintegerIDparticipant_iduuidsender_kindtextsent_attimestampmetajsonbIDdecision_iduuidIDagent_version_iduuid+ 12 more columnsctrl.decision_logPKiduuidPKoccurred_attimestampIDagent_version_iduuidIDrun_iduuidtooltextdecision_typetextIDconversation_iduuidpolicy_resulttextreason_codesjsonb+ 19 more columns

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

TableWhat it holdsColumns
conv.conversationsOne row per chat: its stage and the AI version that ran it.22
conv.messagesEvery line of the chat, encrypted.21
ctrl.decision_logEvery reply and check, with the model, tokens and cost.28
How the tables connect (8)
ColumnPoints toKept by
conv.conversations.agent_version_idagent.agent_versionsThe application (by id)
conv.messages.conversation_idconv.conversationsThe database (foreign key)
conv.messages.participant_idconv.participantsThe application (by id)
conv.messages.decision_idctrl.decision_logThe application (by id)
conv.messages.agent_version_idagent.agent_versionsThe application (by id)
ctrl.decision_log.agent_version_idagent.agent_versionsThe application (by id)
ctrl.decision_log.run_idagent.runsThe application (by id)
ctrl.decision_log.conversation_idconv.conversationsThe application (by id)

Worked example

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

How the approach shifted in one synthetic chat.

Turn by turn

TurnNew signalApproach
1Nothing known yetConsultative: ask about the business
2"Every agency promised us the world" (skeptic)Lead with evidence from their site
3"We already have an agency" (objection)DMA's approved answer
4Problem known, review shownStop asking, offer the call

In the running POC

A law-firm owner describes the problem: the strategist answers like a consultant, not a brochure.

1 / 2A law-firm owner describes the problem: the strategist answers like a consultant, not a brochure.

  1. 1The visitor's problem, in their own words.
  2. 2A short reply that reflects the problem and asks one question.

Website chat · Harbor & Finch Law demo site. 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 websiteChange your tone mid-chat and see the approach change.

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.

9.7 Dynamic Sales Methodology Orchestration · DMA AI proof