LEAD GENERATION

Podcast Back-Catalog Guest Scrape to Airtable Research Queue

Crawls a podcast's entire back catalog once, extracts every past guest, dedupes them, and builds a scored research queue in Airtable for the SDR team to work through.

CategoryLead Generation
Enginesim
Difficultyintermediate
Triggermanual
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerManual run started with podcast feed URL
  • ActionCrawl full archive and extract guests per episodeApify
  • ActionEnrich each unique guest with firmographicsExa
  • LogicScore fit and dedupe repeat guests
  • OutputBuild scored research queue in AirtableAirtableAirtable

What it does

Mines a podcast's full episode archive in a single pass and turns years of guests into one organized, deduplicated research queue in Airtable. Each guest gets a fit score based on company size and role so the team works the best-fit prospects first.

When to use it

Use this once when onboarding a new target podcast, or when you adopt a show with a deep archive. It is the bulk-import counterpart to the live episode monitors: instead of trickling in new guests, you seed the pipeline with the entire historical roster in one run.

How it works

  1. 1A manual run starts the archive crawl with the podcast's feed URL.
  2. 2Apify paginates the full episode list and extracts guest names per episode.
  3. 3Exa enriches each unique guest with company, headcount, and title.
  4. 4A scoring step assigns a fit score and routes anyone below threshold to a parked status.
  5. 5A dedupe filter collapses repeat guests across episodes into one record.
  6. 6Airtable creates rows in the research queue with score, source episodes, and status.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect ApifyActors, scrapers, datasets.
  2. 2
    Connect ExaNeural search across the web.
  3. 3
    Connect AirtableBases, tables, views, automations.
  4. 4
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  5. 5
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  6. 6
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.