SUMMARIZATION

Daily release-health rollup to Confluence

Each morning, compares the last 24 hours of Sentry activity against the deploys that shipped in that window and publishes a dated release-health page to Confluence summarizing…

CategorySummarization
Enginesim
Difficultyintermediate
Triggerschedule
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerDaily morning schedule
  • ActionFetch Sentry issues active in the last 24hSentrySentry
  • LogicTag issues as new vs regressed and map to deploys
  • ActionCompose the daily release-health narrativeOpenAI
  • OutputPublish a dated Confluence pageConfluenceConfluence

What it does

This workflow produces a daily, durable record of release health. Once a day it gathers the Sentry issues that emerged or regressed in the past 24 hours, maps them to the deploys that shipped during that period, and writes a narrative rollup: which releases were clean, which introduced new error classes, and which reopened old ones. The result is published as a dated Confluence page.

When to use it

Use it when you want a searchable history of release quality rather than ephemeral Slack pings. It is useful for sprint reviews, incident retros, and onboarding, where "what did our deploys do last Tuesday?" needs a real answer.

How it works

A daily schedule kicks off the run. The flow queries Sentry for issues active in the trailing 24-hour window and tags each as new or regressed. It correlates them to the deploys recorded for that window. An OpenAI step composes the day's release-health narrative with per-release sections and a trend line versus the prior day. A new Confluence page is created under a dated parent, linking each issue back to Sentry.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect SentryErrors, performance, releases.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect ConfluenceSpaces, pages, blueprints.
  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.