SUMMARIZATION

Monthly voice-of-customer trend rollup with month-over-month shifts

Once a month, reads the archive of weekly VoC briefs in Notion, computes which themes are rising or fading.

CategorySummarization
Enginesim
Difficultyintermediate
Triggerschedule
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerMonthly first-business-day schedule
  • ActionRead trailing-month VoC briefs from NotionNotionNotion
  • LogicAggregate counts, compute month-over-month deltas
  • ActionDraft rising/fading/new theme narrativeOpenAI
  • OutputPost trend digest to leadership SlackSlack

What it does

Elevates weekly customer themes into a monthly trend story leadership can act on. It reads the month's archive of voice-of-customer briefs already stored in Notion, aggregates theme frequencies across all weeks, and compares them to the prior month to surface what is accelerating, what is cooling, and what is brand new. OpenAI then writes a short narrative explaining the shifts, which lands in a leadership Slack channel.

When to use it

Use this when weekly briefs are piling up but no one is connecting the dots across time, and leadership keeps asking "is this getting better or worse?" It turns a stack of snapshots into a directional read on customer sentiment and demand.

How it works

  1. 1A monthly schedule triggers the rollup on the first business day.
  2. 2It reads all weekly VoC brief pages from the Notion archive database for the trailing month.
  3. 3A logic step aggregates theme counts and computes month-over-month deltas versus the prior period.
  4. 4OpenAI drafts a narrative of rising, fading, and emerging themes with representative evidence.
  5. 5The summary posts to a leadership Slack channel as a threaded digest.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect NotionPages, databases, comments.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect SlackChannels, DMs, threads, mentions.
  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.