CONTENT CREATION

Publish localized release notes to a Notion docs database on GitHub Release

When you publish a GitHub Release, generate a localized customer-facing note for each locale and create one draft page per locale in a Notion release-notes database.

CategoryContent Creation
Enginesim
Difficultyintermediate
Triggerevent
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerGitHub Release publishedGitHubGitHub
  • ActionStructure release body into customer noteOpenAI
  • ActionTranslate structured note per localeOpenAI
  • ActionCreate draft Notion page per locale (Status: Needs Review)NotionNotion
  • OutputSlack summary linking all new draft pagesSlack

What it does

Triggers on a published GitHub Release, takes the release body and tag, and turns it into clean customer-facing notes localized for each of your markets. It writes one draft page per locale into a Notion database so your docs and localization reviewers can edit in place before flipping each page to Published.

When to use it

Use this when your public release notes live in Notion and you cut releases via GitHub's Releases UI. It removes the copy-paste-translate loop and keeps every locale version in a single structured database with status tracking.

How it works

  1. 1Publishing a GitHub Release fires the trigger with the tag and release notes body.
  2. 2An LLM converts the raw release body into a structured customer note (highlights, fixes, breaking changes).
  3. 3The flow loops over your configured locales and translates the structured note into each.
  4. 4For every locale it creates a Notion page in the release-notes database with properties Version, Locale, and Status = Needs Review.
  5. 5It posts a single Slack summary linking all the new Notion draft pages for the reviewer.

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
    Connect SlackChannels, DMs, threads, mentions.
  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.