CONTENT CREATION

Weekly localized changelog digest as per-locale email drafts

On a weekly schedule, collect the week's merged changelog entries, group them into a single customer digest, localize it per market.

CategoryContent Creation
Enginesim
Difficultyintermediate
Triggerschedule
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerWeekly schedule
  • ActionFetch changelog entries merged in last 7 daysGitHubGitHub
  • LogicStop if no customer-facing entries this week
  • ActionGroup into digest and localize per marketOpenAI
  • OutputCreate per-locale Gmail draft for reviewGmailGmail

What it does

Once a week it gathers every changelog entry merged in the last seven days, rolls them into one readable "what shipped this week" digest, and produces a localized version for each market. Instead of sending, it saves a Gmail draft per locale so your marketing or success team reviews and hits send.

When to use it

Use this when you batch customer communication into a weekly cadence rather than per-release, and you send regional update emails. It turns scattered merge messages into a single polished, market-specific digest without anyone hand-collating the week's changes.

How it works

  1. 1A weekly schedule triggers the run.
  2. 2The flow queries the repository for changelog entries merged in the trailing 7 days.
  3. 3If nothing customer-facing shipped, it stops without creating empty drafts.
  4. 4An LLM groups the entries by theme into one digest, then localizes it for each configured market.
  5. 5For each locale it creates a Gmail draft to that region's list, subject and body localized, ready for a reviewer to send.

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 GmailRead, draft, send, label.
  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.