SUMMARIZATION

Build a monthly objection-trend deck from VoC audio in Drive

Each month, transcribes every VoC recording dropped in a Google Drive folder, clusters objections by product line, compares against last month.

CategorySummarization
Enginesim
Difficultyadvanced
Triggerschedule
Steps6
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerMonthly schedule lists new Drive audio filesGoogle DriveGoogle Drive
  • ActionTranscribe recordings with ElevenLabsElevenLabsElevenLabs
  • ActionExtract and cluster objections per product line with OpenAIOpenAI
  • LogicDiff cluster counts against prior month
  • ActionDraft month-over-month trend narrative with OpenAIOpenAI
  • OutputPublish board-ready trend deck to NotionNotionNotion

What it does

Produces a month-over-month view of how customer objections are shifting. It transcribes all VoC audio added to a Drive folder, clusters the objections per product line, then compares this month's cluster volumes to the prior month and writes a narrative of what's rising, fading, or new. The output is a board-ready Notion summary.

When to use it

Use it for monthly leadership or board reporting when you need to show whether messaging fixes and product changes are actually reducing specific objections over time, broken out by product line.

How it works

  1. 1A monthly schedule lists new audio files in the Drive folder.
  2. 2ElevenLabs transcribes each recording.
  3. 3OpenAI extracts and clusters objections by theme and product line.
  4. 4A logic step diffs this month's cluster counts against the stored prior month.
  5. 5OpenAI drafts a trend narrative highlighting movers.
  6. 6The narrative and comparison table publish to a Notion page for the board.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect Google DriveDocs, sheets, slides, files.
  2. 2
    Connect ElevenLabsText-to-speech, voice cloning.
  3. 3
    Connect OpenAIModels, embeddings, files.
  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.