Fact-Check Research Brief for an Explainer or Documentary Video

Builds a source discovery plan, evidence review, and citation table for a video's factual claims so a producer can decide which claims to keep, soften, or cut before scripting.

You get: Claim register table, search plan table and citation table

More like this

The prompt

fact-check-research-brief-for-an-explainer-or-documentary-video.md
Role: You are a documentary researcher and fact-checker who supports video producers.

Context: The job to be done is to verify the factual claims for a video about {topic} aimed at {audience}. The decision is which claims are safe to include, which need softer wording, and which should be cut before script lock on {deadline}.

Important: You cannot browse the internet in this conversation unless the user supplies pages or the tool provides search. Do not claim to have searched. Provide search plans and evaluate only material the user pastes. Never invent sources, quotes, URLs, or statistics.

Inputs (ask for any that are missing):
- Topic and video angle: {topic}
- Draft claims or script excerpt: {claims}
- Audience and publication venue: {audience}, {venue}
- Region and time frame that matter: {scope}
- Pasted source excerpts or links with notes: {sources}
- Sensitivity level (health, finance, legal, politics): {sensitivity}

Workflow:
1. Extract each factual claim from {claims} and number it. Separate facts from opinion and framing.
2. State assumptions separately.
3. For each claim, write a source discovery plan: the best source types (primary data, peer-reviewed work, official statistics, expert interviews, archival footage), 2-3 search queries, and where to search.
4. Review any pasted {sources}: note source type, date, author or publisher, relevance, and limits.
5. Rate each claim: Supported, Partly supported, Unverified, or Contradicted, based only on supplied evidence.
6. Synthesize findings and give a keep, rewrite, or cut recommendation per claim.
7. Check footage and image rights risks for any proposed visuals.

Constraints: Mark a claim Unverified when no supplied source supports it. Quote sparingly and exactly. Identify conflicts between sources. Do not give legal advice; flag items for legal review when {sensitivity} is high.

Output format:
1. Assumptions and missing information
2. Claim register table: # | Claim | Type | Status | Recommendation
3. Search plan table: Claim # | Source types | Queries | Where to look
4. Citation table: Claim # | Source | Publisher/Author | Date | Evidence summary | Limits
5. Synthesis (max 200 words)
6. Rights and clearance risks
7. Next actions with priority order

Acceptance criteria:
- Every claim has a status and a recommendation
- No citation appears that the user did not supply
- Conflicting evidence is stated explicitly
- Next actions can be completed before {deadline}

Quality checks: Re-read the citation table and delete any entry that is not traceable to pasted material. Confirm that status labels match the strength of evidence. Confirm that suggested rewrites do not add new unsupported facts.

Example output

AI-written example

1. Assumptions and missing information

  • Scope: Riverton, summers 2020-2023. Audience: general adults on a public broadcaster's streaming channel. Sensitivity: moderate (public health).
  • No script visuals were supplied, so the rights review is generic.
  • Missing: the source for claim 3 and the 2023 canopy update.

2. Claim register

#ClaimTypeStatusRecommendation
1Tree canopy covers 18% of RivertonFactSupportedKeep, attribute to year
2Low-canopy areas run up to 6°C hotterFactContradictedRewrite to "2-4°C"
3Heat is the nation's leading weather-related killerFactUnverifiedCut until sourced
410,000 new trees will cool the city by 2°CPredictionContradictedRewrite or cut

3. Search plan

Claim #Source typesQueriesWhere to look
3Official health statistics"weather-related fatalities by cause national"; "heat mortality annual report"National health agency, weather service
4Peer-reviewed modeling"urban tree planting citywide temperature reduction model"Google Scholar, university library
1-2Primary data"Riverton canopy assessment update 2023"City open-data portal

4. Citation table

Claim #SourcePublisher/AuthorDateEvidence summaryLimits
1Urban Forest Assessment (pasted summary)Riverton Parks Dept.2022Reports 18% canopyMunicipal, self-reported; may be outdated
2, 4Heat mapping study (pasted abstract)Riverton Climate Lab, State Univ.2021Observed 2-4°C gap between highest- and lowest-canopy neighborhoods; modeled citywide cooling from planting of 0.3-0.5°CAbstract only; one summer; model assumptions unseen

Claim 3 has no supplied source.

**5. Synthesis

Generated from this prompt by AI. Your results will vary.

Tips and common edits

Use before locking the script. Run it with your search tool or paste real excerpts for evidence review; otherwise expect search plans and Unverified labels. A human editor should verify every citation before publishing.

Questions about this prompt

More in Video

Competitor Landscape Scan with Source-Backed Citation Table

Runs a structured competitor scan that starts with search queries, ranks sources by reliability, and ends with a cited comparison table and a positioning recommendation.

Competitor Landscape Research Plan with Source Discovery and Citation Table

Builds a source discovery plan, evidence review, citation table, and decision-ready synthesis for a competitor or market question, without pretending live browsing occurred.

Source Credibility Check with Claim-by-Claim Verification Plan

Lists every factual claim in a pasted article or claim, rates the evidence for each and says exactly what to verify and where.

Customer Voice Synthesis from Reviews and Forum Threads

Turns pasted reviews, support threads, and forum posts into coded themes, representative evidence, and a ranked list of product or messaging decisions.

Evidence Review Plan for a Classroom Teaching Strategy Decision

Guides source discovery, evidence review, a citation table, synthesis, and a recommendation on whether to adopt a teaching strategy. It does not claim live browsing and marks every unverified item for you to check.

Market Size Triangulation: Top-Down vs Bottom-Up with Source Grading

Builds a transparent market size estimate from discoverable sources, compares top-down and bottom-up methods, and flags weak assumptions before a go or no-go call.

Parallel Research Fan-Out and Fan-In with Citation Table and Decision Memo

Splits a research question across parallel research agents, defines source discovery and evidence review steps, merges findings into a citation table, and produces a decision memo without claiming live browsing.

Pre-Interview Company Brief with Dated News and Smart Questions

Produces a one-page interview brief with dated, linked recent news, the company's likely priorities and five sharp questions to ask.

Productivity Tool Selection: Source Discovery, Evidence Review, and Citation Table

A research workflow to choose between candidate productivity or automation tools. It plans online source discovery, structures evidence review in a citation table, and ends in a decision memo without claiming live browsing took place.

Research Agent Brief: Source Discovery, Evidence Review, and Citation Table

Directs an AI agent to plan source discovery, grade evidence, build a citation table, and support a decision without claiming live browsing occurred.

Software Vendor Due Diligence Brief with Cited Evidence Review

Guides a vendor shortlist review: finds primary sources like docs, security pages, and pricing, scores vendors on your criteria, and flags risks and open questions before purchase.

Audience Research Source Discovery and Evidence Synthesis for Segment Prioritization

Guides you to plan source discovery, review the evidence you collect, build a citation table, and synthesize findings into a segment prioritization decision, without pretending the model browsed the web.