Turning a public report or dataset into story leads
A 200-page budget, a court filing, or a regulator's report lands in your inbox and the news could be on page 140. Journalists use AI for story research (22%) to get through dense public documents faster — reading for structure, contradictions, and numbers that do not add up. The output is a to-do list of leads to verify, never a set of facts to publish.
You are a research assistant helping a reporter find leads in a long public document. Work strictly from the document text I paste — treat everything you produce as an unverified lead I will confirm myself. Document (public record): {{document_text}} What I am looking into: {{beat_or_angle}} Produce: 1. A one-paragraph plain-language summary of what the document is and covers. 2. Up to eight potential story leads. For each: the claim or figure, the exact page or section where it appears, and why it might be newsworthy. 3. Any internal contradictions or figures that do not reconcile, quoting both places. 4. A list of what is notably missing or unexplained. Rules: - Cite a page or section reference for every claim. If you cannot point to where something is in the document, do not include it. - Use only the document. Do not add background, context, or figures from your own knowledge — if outside context is needed, write [VERIFY: needs external reporting] instead. - Do not infer intent or wrongdoing; describe only what the document states.
Fill in your details and the prompt updates live — then copy.
Summary: This is the city's proposed FY2027 operating budget, covering department allocations, headcount, and capital projects. Leads (verify each against the document and by reporting) - Housing assistance line cut 18%, from $6.2M to $5.1M (p. 84). Newsworthy if services shrink. [VERIFY: needs external reporting on service impact] - Senior management pay pool up 9% (p. 112), same year as the housing cut — worth asking the finance director to reconcile. - Contradiction: Executive summary says "no reduction to frontline services" (p. 3), but the housing line falls 18% (p. 84). Quote both to the city. Missing: No explanation for the $1.1M housing reduction anywhere in the document.
The full workflow
- Confirm the document is a public record before pasting it, and paste the full text
- Run the prompt to surface candidate leads with page references
- Open the cited page for every lead and read it in context yourself
- Report each promising lead out — call the source, get the other side, pull the underlying data
- Publish only what you have independently confirmed, not what the AI summarized
Watch out for
AI summaries invent figures and misread tables, and models are overconfident on document questions. Treat every lead as unverified until you have read the cited page and confirmed it by reporting — the AI's read is a pointer, not a source.
Only paste genuinely public records here. Court filings, budgets, and published reports are fair game; sealed documents, embargoed material, and anything from a confidential source are not — under Reuters' rules, unpublished material does not go into open AI tools.
Where this comes from
Every use case on this site is grounded in real reports from working journalists — not invented by us.