HR & RECRUITING

Exit Interview Recordings to Attrition-Driver Dashboard

Pulls new exit-interview Zoom recordings, extracts each departing employee's stated reasons for leaving, tags them to standard attrition drivers.

CategoryHR & Recruiting
Enginesim
Difficultyintermediate
Triggerevent
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerExit-interview Zoom recording completesZoomZoom
  • ActionFetch recording transcriptZoomZoom
  • ActionExtract and classify attrition driversOpenAI
  • ActionAppend classified rows to attrition tableGoogle BigQueryBigQuery
  • OutputRebuild attrition-driver dashboard pageNotionNotion

What it does

Every time a tagged exit-interview Zoom meeting finishes recording, this workflow turns the conversation transcript into structured attrition data and updates a live driver dashboard. Instead of HR reading transcripts one by one, you get a continuously refreshed view of the top reasons people are leaving.

When to use it

Run this when exit interviews are conducted over Zoom and you want trend visibility without manual coding of each conversation. Ideal for HR teams tracking voluntary attrition month over month.

How it works

  1. 1A completed Zoom recording with the "exit-interview" tag fires the trigger.
  2. 2The workflow fetches the recording's transcript text from Zoom.
  3. 3An OpenAI model extracts the departing employee's stated reasons and classifies each into standard drivers (compensation, management, growth, workload, culture, relocation).
  4. 4The classified rows are appended to a BigQuery attrition table for durable storage and SQL aggregation.
  5. 5A summarized Notion dashboard page is rebuilt with current driver counts, top quotes, and trend deltas versus the prior period.

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 BigQueryDatasets, queries, schemas.
  4. 4
    Connect NotionPages, databases, comments.
  5. 5
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  6. 6
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  7. 7
    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.