Check an AI literature search with a field expert and a foundational book
KINDA — AI can help, with a person in the loop.
1 method on the page: 1 agent.
Methods
Let the AI find studies, then test its framing with a person who knows the field and the field's foundational book, and stop when checking costs more than writing
Steps
- Ask the LLM to find studies, datasets and nuanced evidence on your question.
- Don't treat its framing as settled. It can support nearly any premise.
- Take the findings to a person with real expertise in the field, such as a former lab colleague or a teammate.
- Get the foundational book or textbook that the field and the LLM both cite. Use it to anchor your reading.
- If checking the AI output takes more effort than writing your own answer, stop and go to the expert.
- Use it when you use an AI model as a research librarian for studies and datasets on a question you need to get right.
- Note: Steps from OpenTacit, which credits Ben Stolovitz (CC BY 4.0).
Run this method with your agent
Download .mdCopied 0
--- name: "check-ai-literature-searches-with-an-expert-method" description: "Use when you need to Check an AI literature search with a field expert and a foundational book. Let the AI find studies, then test its framing with a person who knows the field and the field's foundational book, and stop when checking costs more than writing" --- # Let the AI find studies, then test its framing with a person who knows the field and the field's foundational book, and stop when checking costs more than writing Job: [Check an AI literature search with a field expert and a foundational book](https://aiagents.org/canai/check-ai-literature-searches-with-an-expert) ## Need - AI agent ## Steps 1. Ask the LLM to find studies, datasets and nuanced evidence on your question. 2. Don't treat its framing as settled. It can support nearly any premise. 3. Take the findings to a person with real expertise in the field, such as a former lab colleague or a teammate. 4. Get the foundational book or textbook that the field and the LLM both cite. Use it to anchor your reading. 5. If checking the AI output takes more effort than writing your own answer, stop and go to the expert. 6. Use it when you use an AI model as a research librarian for studies and datasets on a question you need to get right. 7. Note: Steps from OpenTacit, which credits Ben Stolovitz (CC BY 4.0). ## Credit Method author OpenTacit (Ben Stolovitz; CC BY 4.0) Source: https://opentacit.com/t/ground-ai-literature-searches-with-a-human-expert-and-a-foundational-book/
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/check-ai-literature-searches-with-an-expert - 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": "check-ai-literature-searches-with-an-expert",
"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"
}