# Answering a commercial question, end to end

The question is answered from your own sources where they cover it, and refused where they do not. A refusal is not silence: everything answerable is answered, the commercial part goes to a person with the conversation attached, and the promise to come back becomes a dated commitment rather than a phrase.

- **Status:** Available
- **Audience:** both
- **Channels:** email, whatsapp, phone
- **In the app:** #/inbox, #/needs-you, #/knowledge
- **Last verified:** 2026-09-10
- **Canonical:** https://connectbyjbrh.com/docs/workflows/commercial-question/

## The stages

1. Trigger — a customer asks what something costs, how fast it can be done, or what is guaranteed.
2. User or external event — the question arrives as mail, a WhatsApp message or speech on a live call.
3. Authentication and workspace resolution — the workspace is entered before any source is read, so the answer is grounded in your Knowledge and nobody else's.
4. Ingest or request — the message is canonicalised, or the call is in session with its instructions already loaded.
5. Canonical record — the question is part of the thread or the call record, attached to the Person it came from.
6. Reasoning — the answerable and the commercial parts of the question are separated. Most questions are a mixture, and the mixture is why a blanket refusal would be the wrong design.
7. Knowledge, memory and rules — grounded facts are selected within a budget of roughly 2,000 characters and four facts; a figure no source carries is refused rather than approximated.
8. Autonomy and approval — the commercial part is escalated whatever the channel's autonomy says. Autonomy governs sending, not authority over terms.
9. Action through a provider — the answerable reply goes out, or waits for approval, under the ordinary send boundary.
10. Result — the customer has an answer to what could be answered and a clear statement that a person is handling the rest.
11. Relationship, timeline and memory — the exchange lands on the person's timeline, and the deal, where one exists, is marked as waiting.
12. Audit, usage and Needs You — the refusal is recorded with the rule that produced it, and the question appears in Needs You for a person to decide.

## Where the answer comes from

| The part asked | Source | What the customer gets |
|---|---|---|
| Anything your sources cover | Knowledge, quoted rather than inferred | A direct answer, with the condition attached where the term is conditional |
| Anything about this customer specifically | Contact-tier memory, resolved narrowest-first | An answer that matches what was agreed with them before |
| Anything nobody has decided | Nothing — this is the refusal | A statement that a person is deciding, and a promise with a date on it |

Arithmetic across sources is not grounding. Deriving a bulk figure from a unit figure is invention with a calculation in front of it, and it is refused in the same way an outright guess is.

## On a live call

The turn-based carrier path produces each sentence and can check it before it is spoken. The realtime speech-to-speech path has no such seam: the model speaks to the caller directly, so the rule lives in the instructions the session opened with, and enforcement is honest about being detection rather than prevention.

- Lines that priced something are counted, using the same expression the carrier path applies to each sentence, so the two paths agree on what a price is.
- A call with a non-zero count is visible afterwards, with its transcript, and is the right thing to listen to before deciding whether that workspace belongs on the realtime path.
- The instructions can be corrected and the correction takes effect on the next call, not the current one.
- This asymmetry is documented rather than smoothed over, because a page claiming identical guarantees on both paths would be false.

> **Note** The turn-based path is the conservative choice for a workspace whose commercial exposure on the phone is high, and choosing it is a legitimate answer to this risk.

## The human decision, and stopping the repeat

1. Open the item in Needs You. The customer's words, the conversation and the deal are attached to it.
   - Result: You are deciding a commercial matter with its context in front of you rather than reconstructing it.
2. Decide, edit the reply so it says what you decided, and approve.
   - Result: Your words go out through the same boundary a person's own send uses, and the state is uncertain until the provider acknowledges it.
3. Clear the review on the deal.
   - Result: It returns to the ordinary board; the audit keeps the fact that it was raised and who answered.
4. If the decision should hold for everyone, add it to Knowledge; if only for this customer, write it as memory against them.
   - Result: The next identical question is answered from a source instead of escalating — which is the only step that changes tomorrow.

> **Careful** A decision typed into one reply governs one reply. The most common failure in this whole flow is answering well and writing nothing down, then meeting the same question next week.

## Questions

### How long does the customer wait?

As long as the queue takes, which is why Needs You is ranked rather than chronological. Nothing is in flight meanwhile: a held reply is no reply, and the clock the customer is counting keeps running.

### Can I let Connect answer this class of question by itself?

By putting the terms in Knowledge, yes — then the answer is grounded and no escalation is needed. What cannot be granted is permission to state terms that no source carries.

### Does the refusal look evasive to a customer?

It reads as an answer to everything answerable plus a named person taking the rest, with a date. Most people find that better than a figure that turns out to be wrong, and it is certainly better than a figure your business did not agree to.

## Related

- [Price, SLA and warranty: what Connect may say](https://connectbyjbrh.com/docs/sales/safe-sales/)
- [Escalating a commercial decision](https://connectbyjbrh.com/docs/sales/commercial-escalation/)
- [Knowledge in Connect](https://connectbyjbrh.com/docs/knowledge/)
- [Connect would not give a price](https://connectbyjbrh.com/docs/troubleshooting/connect-refused-to-quote/)
- [Why a sales agent should refuse to answer](https://connectbyjbrh.com/research/safe-refusals-in-sales/)
- [The realtime voice engine](https://connectbyjbrh.com/docs/phone/realtime-engine/)

## What this page is based on

- docs-source/sources/CHANNELS.md §6 — safe_sales, price_spoken and escalation
- docs-source/sources/GENERAL.md §5, §6 and §11 — Needs You, memory tiers and measured budgets
- Connect capability registry (docs-source/facts.py) — safe_sales, realtime_voice