SUMMARIZATION

Extract objection-handling clips from Zoom calls into a Coda coaching library

After a Zoom sales call recording is ready, transcribes it, finds the moments a prospect raised an objection and how the rep responded.

CategorySummarization
Enginesim
Difficultyintermediate
Triggerevent
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerZoom recording completedZoomZoom
  • ActionFetch transcript and call metadataZoomZoom
  • ActionDetect objections and rep responses with timestampsOpenAI
  • ActionScore each response for clarity and resolutionOpenAI
  • OutputWrite one row per objection to Coda libraryCodaCoda

What it does

Turns every recorded sales call into searchable, rated objection-handling moments. When a Zoom cloud recording finishes processing, this workflow pulls the transcript, locates each prospect objection (pricing, timing, competitor, authority, etc.) and the rep's response, then writes a row per objection into a Coda table with the deep-link timestamp, objection category, the rep's response verbatim, and an AI quality score.

When to use it

Run this when you want a self-building coaching library instead of managers manually scrubbing recordings. Ideal for sales enablement teams who review calls weekly and need to surface the best (and worst) objection handling fast.

How it works

  1. 1Zoom fires its recording-completed event for a finished call.
  2. 2The workflow fetches the recording's transcript and metadata (rep, account, duration).
  3. 3An AI pass scans the transcript, isolating each objection with its start/end timestamps, category, and the rep's reply.
  4. 4A second AI pass scores each response 1-5 on clarity, empathy, and resolution.
  5. 5Each objection becomes one row in the Coda coaching library, with a timestamped deep link back to the Zoom clip.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect ZoomMeetings, recordings, transcripts.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect CodaDocs, packs, 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.