Find a podcast or YouTube appearance for an executive
Surfaces one verified podcast, YouTube, or conference appearance per executive with URL, date, and the stated topic — the raw material for the strongest opener in cold outreach. The triple identity check (name, company, title) makes it safe to run across thousands of prospects unattended.
You are an executive-research specialist running inside an enrichment pipeline. You find public podcast episodes, YouTube interviews, webinar recordings, and conference talks featuring a specific person — the single highest-converting personalization asset that almost nobody mines at scale, because a real listened-to reference is unfakeable.
Work from the executive's full name, their company name, and their job title as provided to you. All three matter: names collide constantly, and the company plus title is how you confirm identity.
Rules:
- The person must be a featured guest or speaker, not merely mentioned or in the audience.
- Confirm identity: the episode description or content must connect the person to the provided company (or a clearly recent former role if the appearance predates a job change — flag that).
- Prefer the most recent appearance. Within the last 18 months is ideal; older is acceptable if clearly the same person.
- Extract the key topic from the episode title and description, not from assumptions about what they probably discussed.
OUTPUT CONTRACT — follow exactly:
Return a single JSON object:
{"show_name": "<podcast, channel, or event name>", "episode_title": "<as published>", "date": "<YYYY-MM-DD or YYYY-MM if only month is shown>", "url": "<direct link to the episode or video>", "format": "<podcast | youtube | webinar | conference-talk>", "key_topic": "<under 15 words, from the title or description>", "identity_note": "<empty string, or a flag like \"appearance predates current role\">"}
- Return ONLY the JSON. No markdown fences, no commentary.
- If no confirmable appearance exists, return exactly: NOT_FOUND
- Never return a different person with the same name. When in doubt, NOT_FOUND.How to use it
- 1
Copy the prompt into Claude, ChatGPT, or any LLM with web access — or into a Clay Claygent column.
- 2
In Clay, map three columns as inputs: full name, company name, and job title — the prompt's identity check needs all three, so don't run it on name alone.
- 3
Spot-check every URL in a 15-row sample; a wrong-person hit here is the most embarrassing failure in outbound.
- 4
Write openers that reference the key_topic specifically, and consider actually listening to the top-priority accounts' episodes before sending.
Best practices
Run this only on decision-maker tiers — VPs and founders appear on shows; individual contributors rarely do, and credits burn fast on NOT_FOUND rows.
Reference a specific idea, not the appearance itself: 'your point about pipeline coverage on the RevOps podcast' beats 'I saw you were on a podcast'.
Respect the identity_note flag — referencing a talk from someone's previous company without acknowledging the move reads as automated research.
Example: what this looks like in practice
An AE selling a data platform works 300 target accounts with named VP-level champions. She runs this prompt over the champion list: 74 come back with appearances, mostly niche industry podcasts with a few hundred listens each — exactly the shows where a guest remembers every listener. Her opener for one CFO: 'Your line on the Manufacturing Metrics podcast about inventory data lagging two weeks stuck with me — is that still the bottleneck?' That email gets a same-day reply and a meeting. Across the 74-account segment she books 11 meetings; the identity check returns NOT_FOUND for a same-named VP at a different firm that a name-only search would have confused.
Best fit
This prompt is one gear in a bigger machine. We orchestrate 35+ tools into outbound systems our clients own , and re-earn the results every month.
Book your free ICP review → →Frequently asked questions
Why are podcast appearances such strong cold email personalization?
Because they're proof of listening, not scraping. Anyone can quote a LinkedIn headline; referencing a specific point from a 40-minute episode signals real investment, and executives on niche shows notice every listener. Reply rates on appearance-based openers routinely run 2–3x standard personalization — and at scale, an agent can find the appearances even if you only listen to the best ones.
How do I avoid referencing the wrong person with the same name?
Never search on name alone. This prompt requires name, company, and title, and instructs the agent to confirm the connection in the episode description before returning anything — defaulting to NOT_FOUND when uncertain. Then spot-check URLs on a sample. A wrong-person reference is worse than no personalization, so the contract is deliberately conservative.
What hit rate should I expect when searching executives for media appearances?
Roughly 10–30% for VP-and-above titles at companies with any public presence, lower for ICs and very small firms. That sounds thin, but the segment it produces is gold: treat appearance-found rows as a priority tier with hand-finished copy, and let the other rows flow through your standard personalization waterfall.
More personalization at scale (clay & claygents) prompts
Generate a cold email first line from scraped research data
The workhorse of AI-personalized outbound: converts whatever research your enrichment waterfall produced into one 12–22-word observation-led first line per row. The swap-test rule and fact-invention ban are what separate lines that read researched from the AI slop prospects now delete on sight.
Turn a Claygent website scrape into a personalized one-liner
Produces a sub-25-word, website-specific opening line for every row in a Clay table — no human in the loop. The output contract forces plain text only and a NOT_FOUND fallback, so unreachable sites and thin homepages return a filterable sentinel instead of a hallucinated compliment that ends up in a prospect's inbox.
Analyze a pricing page for sales-relevant intelligence
Extracts a structured pricing profile from any pricing page: model, tier count, exact displayed prices, free-offer type, and a one-line read on their sales motion. At scale it segments prospect lists by how companies charge — which predicts budget, buying process, and which of your angles will land.