# Deal Desk

Keep sales follow-ups, deal questions, and overdue next steps from getting lost.

Category inspiration: The Closing Room, from the supplied @unicodef1wn chart.
Cabinet treatment: Expand Sales Meeting Desk rather than add a duplicate follow-up crew.
Version: 0.1 · October 6, 2026.
Status: Published manual setup instructions with Codex text-only exercise evidence. Native imports, tools, and Bot-to-Bot handoffs remain untested.

Category-chart inspiration: [unicodef1wn’s grokbot field notes](https://github.com/unicodef1wn/grokbot-field-notes). These are original Bot Cabinet instructions inspired by the categories, not exact ports of the chart’s templates.

## Bots and jobs

| Bot | Treatment | Job |
|---|---|---|
| [Client Deliverables](https://botcabinet.com/bots/client/) | Existing Cabinet Bot | Turn approved meeting notes into a recap and follow-up draft. |
| [Deal Reviewer](../specialists/deal-reviewer.md) | Published manual role | Check the opportunity against agreed deal requirements. |
| [Pipeline Review](../specialists/pipeline-review.md) | Published manual role | Find overdue next steps and duplicated pipeline records. |
| [Call Coach](../specialists/call-coach.md) | Published manual role | Offer one evidence-based improvement from an approved call transcript. |

Keep Sales Meeting Desk's Scout, Researcher, Planner, and Editor for preparation and proposal review. Call coaching is optional; use only recordings or transcripts authorized for this purpose.

## When a crew helps

This extends a continuing sales process with separate deal, portfolio, and coaching questions. One meeting recap can stay with Client Deliverables.

## Bring these inputs

Authorized meeting notes or transcript, deal criteria, approved prices and terms, dated CRM export, stage definitions, and next-step owners.

## Set up and run

1. Select only the roles this job needs. Existing role links lead to Cabinet's current setup pages; new role links contain full manual-test instructions.
2. Put each selected role in its own conversation or Bot. Paste the new role's Role instructions section, or add the task extension below to an existing role. These files are not native import archives or add-to-app links.
3. Start with the fictional first task below. Supply the same approved source records to each role that needs them. A copied handoff alone is not evidence for a factual claim.
4. Pass reviewed results in the order below. If your app lacks Bot-to-Bot handoff, copy the small handoff yourself. Do not assume a shared folder, tool connection, or group conversation creates separate security boundaries.
5. Record each actual answer and failed attempt. Review before connecting real accounts or adding a schedule. Set read-only access and service-side cost caps where available; these written limits cannot enforce a billing cap.

## Who passes what to whom

1. Client Deliverables drafts a recap from the original meeting notes.
2. Deal Reviewer identifies missing buying decisions and checks promises.
3. Pipeline Review checks the broader opportunity list without counting duplicates.
4. Call Coach returns optional private practice feedback; the person approves messages, terms, and record changes.

Use this handoff:

- Task and current version:
- Approved source records:
- Result and its status: draft, checked, or approved:
- Unresolved questions:
- Next owner and action:
- External action awaiting specific approval:

If a role cannot finish, it returns the missing input or failed attempt. The next role must not manufacture a success record.

## Task extensions for existing Bots

### Client Deliverables

Keep the existing Bot's role and boundaries. For this crew: Turn approved meeting notes into a recap and follow-up draft. Prepare a recap, proposal, or other client draft from approved records. Preserve exact commitments and keep unresolved decisions visible. Send nothing without approval. Use only the input assigned to you for this task. Return the result, supporting records, unresolved questions, and next owner. A handoff does not approve an external action.

## First task

Fictional meeting: Jordan will evaluate; no budget recorded; follow-up proposed 'next week.' Agreed deal criteria: confirmed buying authority, confirmed budget, and an exact date for the next action. Pipeline: deal D1 appears twice at $1,000, inactive for 20 days; D2 is $2,000, inactive three days. All amounts are USD. The rule says stale after 14 days. Prepare the recap, questions, and unique-value report.

## Check the result

- Keeps budget, authority, and exact follow-up date unresolved.
- Returns $3,000 in unique open value and flags D1 as stale.
- Describes open value separately from revenue.
- Sends nothing and changes no deal stage.

Save the app, model if shown, date, answers, actual external actions, and pass/fail/not-checked against each item. A written checklist or a favorable review does not prove a runtime pass.

## Limits for this sample

One supplied meeting and up to ten pipeline rows for the sample. No recordings collected, CRM writes, or messages sent.

Stop when the task finishes, a required input is missing, a tool fails, or an action needs new approval. No automatic retries. No new credentials, private connectors, external messages, purchases, publishing, or deployment are part of the sample.

## Finished output

A follow-up draft, deal questions, pipeline report, and optional call practice.


## Exercise evidence

The [collection record](../specialists/collection.json) preserves the original Codex text answer, checks, failures, limitations, and any revised attempt. These records are instruction exercises, not native-app validation. Proposed operational tests remain unrun where the record says so.