SUMMARIZATION

On-demand release notes: summarize any tag range into a Confluence page

Trigger this with two tags and it pulls every PR merged between them, drafts grouped release notes with breaking-change callouts, and publishes a versioned page to Confluence.

CategorySummarization
Enginesim
Difficultyintermediate
Triggerwebhook
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerWebhook: from-tag, to-tag, target spaceHTTP webhook
  • ActionList PRs merged between the two tagsGitHubGitHub
  • LogicError out if range contains no PRs
  • ActionGroup and draft notes with breaking-change calloutsOpenAI
  • OutputPublish versioned page to ConfluenceConfluenceConfluence

What it does

Generates release notes for an arbitrary version range on demand. You hand it a 'from' and 'to' tag; it gathers the PRs merged in that window, writes grouped notes, surfaces any breaking changes as a dedicated callout, and publishes a versioned page in your Confluence release-notes space.

When to use it

When you need to backfill notes for a range, document a hotfix series, or assemble notes that span multiple tags ad hoc — without waiting for an automatic release event. Useful for docs and support teams owning the Confluence knowledge base.

How it works

  1. 1A webhook trigger receives the 'from' tag, 'to' tag, and target space.
  2. 2The flow lists all PRs merged between the two tags from GitHub.
  3. 3An OpenAI step groups PRs into Features, Fixes, and Breaking Changes and writes the notes.
  4. 4A logic step verifies at least one PR was found, returning an error response if the range is empty.
  5. 5A versioned release-notes page is created in the chosen Confluence space.

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 ConfluenceSpaces, pages, blueprints.
  4. 4
    Connect HTTP webhookTrigger any URL on agent actions.
  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.