Check whether a health claim or headline holds up
KINDA — AI can help, with a person in the loop.
1 method on the page: 1 prompt.
Methods
Paste into a general LLM and check whether a health claim or headline holds up.
LLMPrompt
Prompt
Copied 0
Help me figure out whether a health claim I saw is trustworthy. **The claim or headline:** [PASTE IT] **Where I saw it:** [e.g. "news site", "influencer video", "supplement ad", "a friend's message"] **Link or details of the study it mentions (if any):** [PASTE] **Why it matters to me:** [e.g. "thinking of changing my diet", "worried about my child"] Walk through: 1. What exactly is being claimed, restated in one neutral sentence. 2. Source check: who's making it, do they sell something, is a real study named. 3. Study check (if there is one): was it in people or animals/cells, how many people, did it show cause or just a link, how big was the effect in absolute terms, and was it a single study or consistent with others. 4. Red flags: "miracle", "doctors hate this", one-size-fits-all promises, personal stories as proof, urgency to buy. 5. What reputable public health bodies generally say on this topic, framed as something for me to verify on their official sites. Return: a verdict (looks solid / overstated / misleading / can't tell), the 3 biggest reasons, and what I'd need to see to be more confident. Do not invent study details, numbers, or quotes. If information is missing, mark [NOT PROVIDED]. Before acting on any health claim, especially stopping a treatment, talk to my doctor.
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/health-claim-check - 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": "health-claim-check",
"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"
}