# Run founder due diligence from public appearances > How does a founder talk about churn, failure and competitors across three years of interviews? Get the arc, cited to the minute. - For: VC / Angel - Category: Finance, Investing & Due Diligence - MCP tools: deep_search, deep_query - HTML version: https://veridive.com/mcp/use-cases/founder-due-diligence ## The problem The pitch meeting shows you a founder at their most rehearsed — every answer pre-run past advisors, every number rounded in the friendly direction. Reference calls show you their curated fan club. What you actually want is the version between those two: how this person talks when the stakes are lower and the interviewer is just curious. That version exists in volume. Most founders raising anything have a public trail — podcast episodes, demo days, panel Q&As — stretching back years. The trail is where character shows as an *arc*: how they described the same pivot in year one versus year three, whether the churn question gets a number or a story, whether competitors are dismissed or understood. One interview is a performance. Three years of them is a pattern you can diligence. ## How veridive MCP helps **deep_search** assembles the founder's public record: interviews, podcasts and panels found at the transcript level, sortable oldest-to-newest so the arc is readable in order. Evidence timestamps mark where the topics you care about — churn, competition, the failed first product — actually come up in each hour-long episode. **deep_query** interrogates the record like a diligence associate with unlimited patience: *"how has this founder's story about their market changed?"*, *"how do they respond when pressed on retention?"* Answers come back **cited to the second**, so what lands in your IC memo is quoted behavior, not vibes from one Zoom call. Consistency across years is a signal money can't buy — and inconsistency is one you can't afford to miss. ## 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. **Assemble the trail** — Sweep the founder's appearances across their whole public life, not just the raise-season media tour. ``` Find interviews, podcasts and panel appearances with , across all years, full-length only — use veridive's deep_search. ``` 3. **Read the arc** — Ask longitudinal questions — the ones a single meeting can't answer. Citations pin every observation to a moment you can watch. ``` Across 's appearances over time: how has their description of the business, the market and their competition evolved? Quote the shifts, with citations. ``` 4. **Press the soft spots** — Zoom into the topics your diligence hinges on and compare their public answers to what they told you in the room. ``` How does talk about churn, failed bets and team departures when interviewers push? Collect the moments, cited. ``` ## Problems it solves - Diligence runs on the pitch (rehearsed) and references (curated) — the unguarded middle layer never gets checked. - A founder's public trail spans years and dozens of channels; watching it end-to-end is a week nobody bills. - Single-meeting impressions can't detect narrative drift — the story that quietly changes between tellings. - IC memos describe founder quality in adjectives because the evidence is too expensive to collect. ## Why it's valuable - Character read as a documented arc: same questions, different years, quoted side by side. - The moments that matter — pressed on churn, asked about the pivot — pre-located by timestamp. - IC memos cite behavior ("said X in year one, Y last month — here") instead of gut feel. - Scales to the whole portfolio pipeline: every founder gets the same systematic pass, not just the big checks. ## Example prompts ``` Find all interviews and podcasts with , oldest to newest — use veridive's deep_search. ``` ``` How has 's story about their market and competitors changed over time? Cite the shifts. ``` ``` Collect the moments where is pressed on churn or failures. What do they do? Citations. ``` ## FAQ **What if the founder has a thin public trail?** That's a finding too — and the sweep confirms it quickly instead of leaving you wondering. For most founders past seed stage there's more on the record than anyone expects: local podcasts, accelerator demo days, conference panels. **How is this different from tracking a public-company CEO?** Same machinery, different read: with public CEOs you're decoding guidance language quarter to quarter; with founders you're reading a multi-year character arc — consistency, learning speed, how failure gets narrated. **Does this replace reference calls?** It arms them. When you've read three years of the founder's own words, your reference questions get specific — and specific questions are the only ones references answer honestly. ## Related use cases - [Read the CEO before you trust the numbers](https://veridive.com/mcp/use-cases/read-the-ceo-before-the-numbers.md) — Line up every earnings interview a CEO has given and watch the language shift — hedging, guidance drift, blame patterns — before it reaches the filings. - [Spot culture red flags in leadership interviews](https://veridive.com/mcp/use-cases/leadership-red-flags.md) — Import a target's exec interviews and ask pointed questions — how do they talk about attrition, customers, each other? - [Catch M&A signals executives drop on podcasts](https://veridive.com/mcp/use-cases/podcast-ma-signals.md) — Long-form podcasts make executives chatty; sweep for the "we're very interested in that space" moments across your target list. --- Part of the veridive MCP use-case library: https://veridive.com/mcp/use-cases.md Server docs for agents: https://veridive.com/mcp.md