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

Section 9 · Buyer Psychology & Sales Method

9.2Know when to stop asking questions

Built in the POC
No.
9.2
DMA's reference
Decision Book p.21
Phase
Phase 1
Autonomy
L4 · Autonomous
DMA's decision
Yes

What DMA asked for · Decision Book p.21

Move to the meeting as soon as someone is clearly qualified and ready.

Why it matters to DMA: So a hot lead is never annoyed by questions that don't need asking.

In our words, from DMA's Product Decision Book v3, page 21.

How we do it

  • Code, not the AI, decides when enough is known: when the visitor has asked to book, or when their problem is known and the site review has been shown.
  • From that moment, the strategist's goal changes from "diagnose" to "stop asking questions and offer the 45-minute call", and the booking card is one click away.
  • The inbound score (0–100, calculated by code from what the visitor said: size, stated budget, the problem, who decides, timing and fit) goes with the lead, so a Tier A chat reaches a person fast.

The flow

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

not yetmetmetWhat we knowproblem · site · ready?Booking criteriacode decidesKeep diagnosingone questionOffer the callno more questionsBooking cardreal times
Step 1 of 4

What's known so far

The problem, the site review, whether they asked to book.

  • 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

    Keeps the running notes and the booking criteria.

  4. 4AI

    Claude models, only through DMA's own gateway

    The strategist follows the goal code sets.

  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.

Criteria met, questions stop

1 / 2

What you see

1.The review is shown

With the problem already known, the booking criteria are met.

The site review in the chat: three findings, each with its evidence.
Callout 1

What happens in the system

  • Rule enginebooking criteria

    Asked to book, or the problem is known and the review has been shown.

Right-hand values come from a real run of the POC on September 25, 2026 (trace tr_muh5sw194tot7e797019, tr_muh5sw3y109o05zmqjmp6…). Rows marked “sample” are illustrative.

The inbound score for one synthetic chat, as code computes it.

What the visitor said, and what code made of it

FactorFrom the chatReason code
SizeThree officesMulti-location
Problem"New patients are down at two offices"Stated pain
Who decides"I own the practice"Decision maker
FitLocal search and SEOFits several services
TimingBooked a callMeeting booked

In the running POC

The site review in the chat: three findings, each with its evidence.

1 / 2The site review in the chat: three findings, each with its evidence.

  1. 1The findings, with the evidence from the visitor's own site.
  2. 2Booking is one click away.

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 websiteDescribe a problem, paste the site address, and see it move to the call.

Status

Built in the POC

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

9.2 Know when to stop asking questions · DMA AI proof