CONTENT CREATION

Collect merged PRs into a weekly changelog draft in Notion

Every Friday, gathers the week's merged pull requests labeled "changelog," groups them into Added / Fixed / Changed sections.

CategoryContent Creation
Enginesim
Difficultyintermediate
Triggerschedule
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerEvery Friday afternoon
  • ActionFetch PRs merged this week with changelog labelGitHubGitHub
  • LogicDeduplicate and order by merge time
  • ActionGroup into Added/Fixed/Changed and rewriteOpenAI
  • OutputCreate weekly changelog draft in NotionNotionNotion

What it does

This workflow assembles your changelog so you do not have to scroll through commit history on release day. On a weekly schedule it queries GitHub for pull requests merged in the last seven days that carry a "changelog" label, reads each PR's title and description, and hands the set to OpenAI. The model groups the changes into Added, Fixed, and Changed sections, rewrites terse PR titles into reader-friendly one-liners, and drops anything that is internal-only. The result is created as a draft Notion page titled with the week's date range, ready for an editor to trim and publish.

When to use it

Use it when changelog writing is a Friday scramble and entries get forgotten because nobody captured them at merge time. It fits teams that label release-worthy PRs and want a structured first draft generated from the actual merged work, not from memory. The label filter keeps noise out, so chores and refactors never leak into customer-facing notes.

How it works

  1. 1A schedule trigger fires every Friday afternoon.
  2. 2GitHub returns all PRs merged in the past week carrying the "changelog" label, with titles and bodies.
  3. 3A logic step deduplicates and orders the PRs by merge time.
  4. 4OpenAI groups them into Added / Fixed / Changed and rewrites each into clean changelog prose.
  5. 5A new draft page is created in your Notion changelog database for editorial review.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect GitHubRepos, issues, pull requests, actions.
  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.