CONTENT CREATION

Slack-Approved Changelog Before It Goes Live

Drafts a changelog from PRs merged since the last tag, posts it to Slack for one-click approval, and only deploys to the microsite once a maintainer approves.

CategoryContent Creation
Enginesim
Difficultyintermediate
Triggerevent
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew git tag pushedGitHubGitHub
  • ActionDraft grouped changelog from merged PRsOpenAI
  • ActionPost draft to Slack with approve buttonsSlack
  • LogicBranch on approve vs request-changes
  • ActionCommit approved entry to repoGitHubGitHub
  • OutputDeploy and post live link to SlackVercelVercel

What it does

Puts a human checkpoint between your release and your public changelog. It builds the draft from merged PRs, posts the rendered preview into a Slack channel with Approve and Edit actions, and holds the deploy until someone signs off. Approved entries publish to the Vercel microsite automatically.

When to use it

Use it when changelog copy is customer-facing enough that a person should eyeball it before it ships, but you still want the assembly fully automated. Ideal for teams with a release captain rotation.

How it works

  1. 1A new tag push triggers the flow.
  2. 2It collects PRs merged since the previous tag and drafts a grouped changelog.
  3. 3The draft is posted to Slack with Approve and Request-changes buttons.
  4. 4The flow branches on the response: approval continues, a change request stops and pings the author.
  5. 5On approval, the entry is committed to the changelog repo.
  6. 6Vercel deploys the microsite and the live link is posted back to the Slack thread.

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 SlackChannels, DMs, threads, mentions.
  4. 4
    Connect VercelDeploys, runtime logs, analytics.
  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.