Podcast guest intake

The questions

Each question carries an extraction hint: plain language telling the AI what to pull out of the answer. That's how a spoken ramble becomes a structured row in your inbox.

1. 1Give us your 30-second pitch: who are you and what do you talk about?

   Voice · 45s

   AI extracts: name_or_brand: string, topic: string, credential: string|null

2. 2Tell us one specific story you would tell on the show that our audience has not heard before.

   Voice · 120s

   AI extracts: story_summary: string, is_specific_anecdote: boolean (vs generic talking points)

3. 3What should listeners be able to do differently after your episode?

   Voice · 60s

   AI extracts: listener_takeaway: string, actionable: boolean

4. 4What is your recording setup?

   Choice

   Dedicated mic + quiet room / Headset or earbuds / Laptop or phone mic

   AI extracts: selected setup tier

5. 5Drop links: your site, socials, and one previous appearance if you have one.

   Text

   AI extracts: urls: string[], has_prior_appearance: boolean

What the AI scores for

This rubric ships with the template and feeds the 1 to 100 score on every submission. It's yours to edit, and the AI writes its reasoning out next to each score.

This is an audition as much as an application: the recording itself is evidence. High: sounds natural and energetic, tells one concrete first-person story with real details, and names a clear listener takeaway. Medium: credible background but generic talking points, or reads a prepared bio instead of talking. Low: vague self-promotion, no actual story, or the pitch is clearly a mass template with no reference to this show. Do not penalize accents or modest setups; do flag monotone script-reading.

Try it live

This is a real, working copy of the template. Answer it by voice if you like: submissions here are demo data, processed and then discarded.

Prefer a full tab? Open /f/tmpl-podcast →