CONTENT CREATION

Turn shipped Linear issues into localized ReadMe changelog drafts

When a Linear issue moves to Done with a customer-facing label, draft a localized release note per locale and stage each as a hidden ReadMe changelog entry.

CategoryContent Creation
Enginesim
Difficultyintermediate
Triggerevent
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerLinear issue moved to DoneLinearLinear
  • LogicProceed only if customer-facing label present
  • ActionDraft and localize note per localeOpenAI
  • ActionStage hidden ReadMe changelog entry per localeReadMeReadMe
  • OutputSlack approval request linking staged draftsSlack

What it does

Listens for Linear issues that reach a Done state and carry a "customer-facing" label. It writes a clear release note from the issue title and description, localizes it for each market, and stages each as a hidden (unpublished) changelog entry in ReadMe. A Slack approval request links every staged entry so a reviewer can publish with one action.

When to use it

Use this when your product changelog lives in ReadMe and your team treats a Linear issue hitting Done as the signal that something shipped. It bridges issue tracking and public docs while keeping a human gate before anything goes live.

How it works

  1. 1A Linear issue transitioning to Done with the customer-facing label triggers the flow.
  2. 2The flow checks the label and skips internal-only issues.
  3. 3An LLM drafts a customer-facing note from the issue summary, then localizes it per configured locale.
  4. 4Each localized note is created as a hidden ReadMe changelog entry tagged with its locale.
  5. 5A Slack message requests review and links every staged draft for approval and publish.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect LinearIssues, projects, cycles, triage.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect ReadMeAPI docs, changelog, auth.
  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.