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

Section 9 · Buyer Psychology & Sales Method

9.5BANT-lite for smaller deals

Built in the POC
No.
9.5
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

Use a shorter qualification for smaller and local prospects.

Why it matters to DMA: Don't over-qualify small prospects: capture them and keep them moving.

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

How we do it

  • Qualification in the chat is short by design: two or three natural questions, never a form. The note-taker fills the BANT-lite fields as they come up: budget (stated, none, unknown), who decides, timing and the problem.
  • Code turns those fields into the inbound score and tier; missing fields count as neutral, and a chat with too little evidence can't be Tier A.
  • For an executive who wants it short, the method switches to BANT-lite outright: the fewest questions and two-sentence replies.

The flow

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

Two or three questionsnatural, not a formBANT-lite fieldsbudget · authority · timing· needInbound scorecode, 0–100Leadtier and reasons
Step 1 of 4

A few natural questions

What the business does, what isn't working, what they've tried.

  • AI
  • Stored data
  • Rule in code
  • Nutshell

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 running notes with the BANT-lite fields.

  4. 4AI

    Claude models, only through DMA's own gateway

    Fills the fields; code scores them.

  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.

The BANT-lite fields after a short synthetic chat.

Four fields, three questions

FieldValue
BudgetUnknown (counted as neutral)
AuthorityDecision maker
NeedStated: fewer calls this year
TimingSoon

In the running POC

The visitor describes the problem; the AI reflects it back and asks one question.

The visitor describes the problem; the AI reflects it back and asks one question.

  1. 1The visitor's own words: no form fields.
  2. 2One reflection, one question.

Website chat · BrightSmile Dental 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 websiteA short chat is enough to be scored and booked.

Status

Built in the POC

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

9.5 BANT-lite for smaller deals · DMA AI proof