CONTENT CREATION

Merged PRs Since Last Tag to Deployed Changelog Microsite

When you push a new git tag, this collects every PR merged since the previous tag, rewrites the titles into human-toned release notes.

CategoryContent Creation
Enginesim
Difficultyintermediate
Triggerevent
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew git tag pushedGitHubGitHub
  • ActionList PRs merged since previous tagGitHubGitHub
  • LogicStop if no user-facing PRs in range
  • ActionRewrite and group titles into prose changelogOpenAI
  • ActionCommit changelog entry to content repoGitHubGitHub
  • OutputDeploy updated microsite to VercelVercelVercel

What it does

Turns a fresh release tag into a published, readable changelog page. It diffs the new tag against the previous one, gathers the merged pull requests in that range, groups them by type (features, fixes, chores), and rewrites the terse PR titles into prose a customer would actually understand. The result is built and deployed as a static microsite on Vercel.

When to use it

Use it when you cut releases by tagging and want a public-facing changelog without hand-writing one every sprint. Best for teams who already enforce decent PR titles and squash-merge.

How it works

  1. 1A new tag push fires the GitHub trigger.
  2. 2The flow resolves the previous tag and lists all PRs merged between the two refs.
  3. 3It checks whether any user-facing PRs exist; if the range is all internal chores, it stops without publishing.
  4. 4An LLM step rewrites and groups the titles into a dated changelog entry in friendly prose.
  5. 5The entry is committed to the changelog repo's content directory.
  6. 6Vercel builds and deploys the updated static site, and the live URL is returned.

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 VercelDeploys, runtime logs, analytics.
  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.