SUMMARIZATION

Weekly Customer-Call Theme Rollup to Notion Digest

Every Friday, pulls the week's call transcripts from Google Drive, clusters them into recurring themes with an LLM, and publishes a ranked product-insights digest to Notion.

CategorySummarization
Enginesim
Difficultyintermediate
Triggerschedule
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerWeekly schedule fires Friday 3pm
  • ActionList week's transcripts in Drive folderGoogle DriveGoogle Drive
  • ActionRead transcript text and metadataGoogle DriveGoogle Drive
  • ActionCluster calls into named themes with countsOpenAI
  • LogicDrop single-mention themes as noise
  • OutputPublish ranked digest to Notion databaseNotionNotion

What it does

Turns a week of raw sales- and success-call transcripts into a single, skimmable product-insights digest. It reads every transcript saved to a Drive folder during the week, extracts the topics customers actually raised, groups them into themes (pricing pushback, missing integrations, onboarding friction, etc.), counts how often each theme appeared, and writes a ranked summary page to Notion.

When to use it

Run it when your team records customer calls (Gong, Fireflies, Zoom) and the transcripts land in a shared Drive folder, but nobody has time to read 30 of them. Ideal for PMs and founders who want a Monday-ready read on what customers are asking for, without manual tagging.

How it works

  1. 1A weekly schedule fires Friday afternoon.
  2. 2Google Drive lists every transcript modified in the last 7 days from the calls folder.
  3. 3Each transcript's text is read and concatenated with call metadata.
  4. 4OpenAI clusters the corpus into named themes with example quotes and a frequency count.
  5. 5A logic step drops themes mentioned in only one call as noise.
  6. 6The ranked digest is published as a new dated Notion page under the Product Insights database.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect Google DriveDocs, sheets, slides, files.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect NotionPages, databases, comments.
  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.