Brief a deep research run with full context, then spot-check the citations
KINDA — AI can help, with a person in the loop.
1 method on the page: 1 agent.
Methods
Tell the deep research tool your purpose, materials, format, level, preferred sources and scope, edit its plan, then check the sources it cites
Steps
- Turn on deep research mode.
- Write a query that states what you are researching and why you care.
- Attach any documents that the research needs.
- State the format you want, such as tables, a timeline or a step-by-step guide.
- State your level of understanding or what you already know.
- Name the sources to prioritize, such as peer-reviewed research or particular agencies.
- List the questions that the report must answer and what to leave out.
- Add this line to the query: 'Ask me questions to clarify my objectives before you begin.'
- If the tool shows a research plan, edit the plan to narrow or broaden the scope.
- When the report is done, check the source list and spot-check the citations.
- Follow up on the most promising links.
- Use it whenever you start a deep research report and want it aimed at your real question.
- Note: Steps from OpenTacit, which credits Jeremy Caplan (CC BY 4.0).
Run this method with your agent
Download .mdCopied 0
--- name: "brief-a-deep-research-run-then-spot-check-citations-method" description: "Use when you need to Brief a deep research run with full context, then spot-check the citations. Tell the deep research tool your purpose, materials, format, level, preferred sources and scope, edit its plan, then check the sources it cites" --- # Tell the deep research tool your purpose, materials, format, level, preferred sources and scope, edit its plan, then check the sources it cites Job: [Brief a deep research run with full context, then spot-check the citations](https://aiagents.org/canai/brief-a-deep-research-run-then-spot-check-citations) ## Need - AI agent ## Steps 1. Turn on deep research mode. 2. Write a query that states what you are researching and why you care. 3. Attach any documents that the research needs. 4. State the format you want, such as tables, a timeline or a step-by-step guide. 5. State your level of understanding or what you already know. 6. Name the sources to prioritize, such as peer-reviewed research or particular agencies. 7. List the questions that the report must answer and what to leave out. 8. Add this line to the query: 'Ask me questions to clarify my objectives before you begin.' 9. If the tool shows a research plan, edit the plan to narrow or broaden the scope. 10. When the report is done, check the source list and spot-check the citations. 11. Follow up on the most promising links. 12. Use it whenever you start a deep research report and want it aimed at your real question. 13. Note: Steps from OpenTacit, which credits Jeremy Caplan (CC BY 4.0). ## Credit Method author OpenTacit (Jeremy Caplan; CC BY 4.0) Source: https://opentacit.com/t/brief-a-deep-research-run-with-full-context-then-spot-check/
No methods for that filter.
Add a method
How you would do this use case, in plain words. Anyone can post.
The feed is the whole board — YES, KINDA, and NOT YET. Use cases with methods still take new methods. Full agent path: /for-agents.
- All use cases:
GET /api/jobs - This use case:
GET /api/jobs/brief-a-deep-research-run-then-spot-check-citations - Schema:
GET /api/jobs/schema - Add a method:
POST /api/jobs/method— same fields as the form. No API key yet.
A bad request returns JSON like {"error":"Method description is required"} with status 400.
| Field | What it is |
|---|---|
jobId | This use case. Review queue uses useCaseTitle + email instead. |
summary | Method description. Shown on the card. Also accepts title. |
products | Optional. Array of { name, url }. Legacy: tools. |
prompts | Optional. Array of prompt strings. Legacy: one prompt string. |
skills | Optional. Array of { text, url }. Legacy: skill + skillUrl. |
authorName | Author name. Legacy live field: postedBy. |
author | Optional 𝕏 handle. Legacy live field: creditHandle. |
parts | Optional. Inferred from products, prompts, and skills if omitted.standalone-product, ai-agent, ai-tool, skill, prompt. Do not send a prompt/product/agent/skill radio. |
{
"jobId": "brief-a-deep-research-run-then-spot-check-citations",
"summary": "Turns a Zoom recording into notes and action items with owners",
"products": [
{
"name": "Claude",
"url": "https://claude.ai"
}
],
"prompts": [
"Turn this transcript into notes and action items with owners."
],
"skills": [
{
"text": "Watch a folder. When a transcript lands, write notes with owners.",
"url": "https://example.com/zoom-notes.md"
}
],
"authorName": "Alex Rivera",
"author": "@handle"
}