PROJECT MANAGEMENT

Scan Notion Meeting Notes for Action Items and Open ClickUp Dependency Tasks

On a schedule, parses recently edited Notion meeting-notes pages for action items that one team owes another and creates a ClickUp task for each, with due date and owner mapped.

CategoryProject Management
Enginesim
Difficultyintermediate
Triggerschedule
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerSchedule: scan recently edited Notion pages
  • ActionFetch meeting-notes pages edited since last runNotionNotion
  • LogicLLM extracts cross-team action items with owner and due dateOpenAI
  • LogicDe-duplicate against existing ClickUp tasks by source id
  • OutputCreate ClickUp dependency tasks with owner and due dateClickUpClickUp

What it does

Periodically pulls Notion pages edited since the last run (meeting notes, planning docs), extracts action items phrased as cross-team handoffs, and opens a ClickUp task for each in a shared "Cross-Team Dependencies" list. Each task carries the owner, the requesting team as a custom field, the due date, and a backlink to the source Notion block.

When to use it

When decisions and handoffs get buried in meeting notes nobody revisits, and dependencies surface only when something is already late. Ideal for teams whose source of truth is Notion docs rather than chat.

How it works

  1. 1A schedule fires (e.g. hourly during work hours).
  2. 2The flow queries Notion for pages in the meeting-notes database edited since the last run.
  3. 3An LLM reads each page and extracts action items that are commitments between teams, with owner and due date.
  4. 4Already-tracked items are de-duplicated against existing ClickUp tasks by source block id.
  5. 5A ClickUp task is created per new commitment, with owner, due date, requesting-team custom field, and a Notion backlink.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect NotionPages, databases, comments.
  2. 2
    Connect ClickUpDocs + tasks + chats in one workspace.
  3. 3
    Connect OpenAIModels, embeddings, files.
  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.