# Vet a market claim before repeating it to your board > That stat in your deck — trace it to a primary spoken source with evidence filters, or find out it dissolves under scrutiny. - For: CEO - Category: Market & Competitor Research - MCP tools: deep_search, deep_query - HTML version: https://veridive.com/mcp/use-cases/vet-claims-before-the-board ## The problem Every deck has one: the market stat everyone repeats and nobody has sourced. "The market's growing 40% a year." "80% of teams plan to adopt this." It arrived via a competitor's deck via a blog via a webinar via — somewhere. You're about to say it to your board, and one director has a habit of asking, mildly, "where's that from?" Claims like these are load-bearing. Strategy leans on them, hiring plans assume them, valuations quote them. And the chain of custody usually ends at a slide that cited another slide. Before it goes in your deck, it deserves ten minutes of adversarial sourcing: who actually said it first, in what context, with what basis — and does anyone credible dispute it out loud? ## How veridive MCP helps **deep_search** hunts the primary utterance: search the claim's substance with the **factual** quality verdict doing the filtering — surfacing content that cites specific data, named sources and first-hand evidence over content that just repeats the number confidently. Evidence timestamps land you on the exact moment the claim gets made (or made-up). **deep_query** runs the adversarial pass: *"what's the actual evidence for and against ?"* It reads across the record and returns both sides **cited to the second** — who asserts it and on what basis, who disputes it and why. Ten minutes later the stat in your deck either has a named, checkable source and a confidence level… or it's quietly gone, which is the cheaper way to learn it was folklore. ## How to run it 1. **Connect veridive MCP** — One-time setup: add the veridive MCP server to Claude, ChatGPT, Cursor or any MCP client and generate your API key. Takes about two minutes. 2. **Hunt the primary source** — Search the claim with factual filtering on. You're looking for the earliest, most-cited utterance with an actual basis — not the loudest repetition. ``` Who actually says with evidence — data, named studies, first-hand numbers? Factual content only, and show me where exactly they say it — use veridive's deep_search. ``` 3. **Run the adversarial check** — Ask for the dispute, not just the support. A claim nobody credible contests reads very differently from one experts argue about. ``` What's the evidence for and against ? Who disputes it and on what basis? Both sides, cited to the moment. ``` 4. **Rewrite the slide honestly** — Attach the real source and the honest framing — or replace the stat with what the evidence actually supports. ``` Given these findings, how should I phrase this claim in a board deck so it's accurate and attributable? Draft the line and the source note. ``` ## Problems it solves - Market stats circulate deck-to-deck with the source lost three hops back. - Confidence and evidence look identical in a slide; the difference only surfaces under a director's question. - Manually tracing a claim's origin means hours across blogs, webinars and podcasts nobody has. - Contradicting evidence exists but never reaches you, because repetition is louder than rebuttal. ## Why it's valuable - Load-bearing claims get sourced before the board hears them — credibility is asymmetric to lose. - The factual verdict prioritizes content with actual basis, cutting the confident-repetition noise. - You see the dispute map: solid consensus, live debate, or pure folklore — each changes the slide. - Ten minutes per claim: cheap insurance against the mild question you can't answer. ## Example prompts ``` Who says with actual evidence? Factual content only, exact moments — use veridive's deep_search. ``` ``` Evidence for and against , both sides cited to the moment. ``` ``` Draft a board-deck phrasing of that's accurate and attributable, given these findings. ``` ## FAQ **What does the factual verdict actually check?** It's a transcript-level quality assessment of whether claims are backed — specific studies, data, named experts, first-hand evidence — versus asserted. It ranks the sourced discussions up so your vetting starts from the strongest material. **What if the claim only exists in written reports, not on video?** Then the sweep tells you that too — an absence of anyone credible saying it on the record is itself signal, and the expert commentary around the topic usually reveals how the number is regarded. **Do I have to name veridive's tools in these prompts?** No — describe the vetting job in plain language and the routing sorts itself. Hints only matter if multiple research servers are connected. ## Related use cases - [Fact-check extraordinary claims in emerging assets](https://veridive.com/mcp/use-cases/extraordinary-claims-check.md) — "Guaranteed 40% yield" — ask for the primary sources behind a claim and get either citations or silence; both are answers. - [Separate evidence from hype in a hot sector](https://veridive.com/mcp/use-cases/evidence-vs-hype.md) — Quality verdicts flag which videos back claims with data and which just vibe — filter a noisy sector down to the sourced few. - [Map expert consensus before entering a market](https://veridive.com/mcp/use-cases/map-expert-consensus-before-market-entry.md) — Ask one question — "is this market saturated?" — and get a grounded answer built from what practitioners actually say, with timestamped citations. --- Part of the veridive MCP use-case library: https://veridive.com/mcp/use-cases.md Server docs for agents: https://veridive.com/mcp.md