# Market Lookout

Know which competing products changed and whether those changes matter to your business.

Category inspiration: The Spy Network, from the supplied @unicodef1wn chart.
Cabinet treatment: New crew with public, attributed research.
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 |
|---|---|---|
| [Competitor Brief](../specialists/competitor-brief.md) | Published manual role | Compare dated public product, price, and hiring information. |
| [Researcher](https://botcabinet.com/bots/researcher/) | Existing Cabinet Bot | Check important claims against their original sources. |
| [Search Presence](../specialists/search-presence.md) | Published manual role | Check a fixed set of search and AI-answer observations. |

Use Scout to suggest an additional public source only after the list owner approves it. No impersonation, covert newsletter signups, private scraping, or personal employee profiles.

## When a crew helps

Change detection, fact checking, and search observations require different evidence. A simple price comparison can remain one Researcher task.

## Bring these inputs

Named competitors, approved public pages or snapshots, prior dated records, exact questions, region, and what decision the report should help.

## 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. Competitor Brief returns changes with dates and source records.
2. Researcher checks the strongest claims and challenges unsupported inferences.
3. Search Presence returns separate, dated observations against the approved questions.
4. Researcher combines the checked changes and Search Presence observations into one report, preserving the original source records and unknowns. The person decides whether to act on its proposed response.

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

### Researcher

Keep the existing Bot's role and boundaries. For this crew: Check important claims against their original sources. Check a defined question against the original approved records. Return evidence, source references, and gaps. Label supplied snapshots separately from current live research. 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 records: a rival's same per-seat monthly plan moves from $29 on Oct 1 to $39 on Oct 5. Its new job advert is Enterprise Sales Lead. One supplied AI answer incorrectly describes your paid plan as free. Prepare a change report and a correction request without doing new searches.

## Check the result

- Reports the $10 change without mixing annual and monthly prices.
- Keeps the hiring advert separate from a confirmed roadmap.
- Identifies the wrong price claim and preserves the supplied-observation label.
- Makes no private inquiry or automatic website change.

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

Up to five named competitors and five exact questions per approved manual run. No subscription signups or scheduled monitoring.

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 dated comparison with source notes and corrections worth reviewing.


## 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.