AI & RAG

Release breaking-change broadcast to Slack with cited diffs

When a new API version is released on GitHub, parses its changelog for breaking changes and deprecations, summarizes them grounded in the exact diff.

CategoryAI & RAG
Enginesim
Difficultyintermediate
Triggerevent
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew release published on GitHubGitHubGitHub
  • ActionFetch release changelog and diff against previous tagGitHubGitHub
  • LogicIsolate breaking changes and deprecations; stop if none
  • ActionSummarize each breaking change grounded in the diffOpenAI
  • LogicConfirm every item maps to a real diff citation
  • OutputBroadcast cited upgrade alert to SlackSlack

What it does

When a new release is published on GitHub, this workflow reads its changelog, extracts only the breaking changes and deprecations, summarizes each grounded in the exact diff lines, and posts a concise upgrade alert to Slack so consuming teams know what to fix before they upgrade.

When to use it

Use it when downstream teams keep getting surprised by breaking changes in a shared API or SDK. This turns every release into a proactive, sourced heads-up instead of a postmortem.

How it works

  1. 1A GitHub release-published event triggers the workflow.
  2. 2The workflow fetches the release's changelog and the diff against the previous tag.
  3. 3A logic step isolates the breaking-change and deprecation entries; if none exist, it stops quietly.
  4. 4An OpenAI model summarizes each breaking change grounded in the retrieved diff, quoting the affected lines.
  5. 5A logic step confirms every summarized item maps to a real diff citation.
  6. 6The workflow broadcasts the cited upgrade alert to the engineering Slack channel.

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
    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.