CUSTOMER SUPPORT

Weekly digest of shipped fixes mapped to the tickets they closed

On a schedule, compile the week's Sentry issues resolved in deploys, link each to the support tickets it affected.

CategoryCustomer Support
EngineSim + Paperclip
Difficultyadvanced
Triggerschedule
Steps6
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerWeekly schedule fires
  • ActionQuery Sentry issues resolved in deploys this weekSentrySentry
  • ActionCount linked Zendesk tickets per issueZendeskZendesk
  • ActionAgent writes non-technical changelog entriesOpenAI
  • ActionPublish entries to Notion changelogNotionNotion
  • OutputPost impact-ranked recap to SlackSlack

What it does

Turns a week of shipped fixes into two artifacts: a public-facing changelog entry of what got fixed, and an internal recap of how many tickets each fix cleared. It aggregates rather than notifying per-event, giving stakeholders the big picture.

When to use it

Use it when individual fix-live replies are already handled elsewhere and you instead want a periodic rollup for a status page, changelog, or weekly support-engineering sync. Good for reporting resolution impact.

How it works

  1. 1A weekly schedule triggers the workflow.
  2. 2The flow queries Sentry for all issues resolved in deploys over the past seven days.
  3. 3For each issue it counts the linked Zendesk tickets to measure customer impact.
  4. 4An agent writes a clear, non-technical changelog entry per fix from the issue title and notes.
  5. 5It publishes the compiled entries to a Notion changelog page.
  6. 6It posts an internal Slack recap ranking fixes by tickets cleared, for the team sync.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect SentryErrors, performance, releases.
  2. 2
    Connect ZendeskTickets, queues, knowledge base.
  3. 3
    Connect NotionPages, databases, comments.
  4. 4
    Connect SlackChannels, DMs, threads, mentions.
  5. 5
    Connect OpenAIModels, embeddings, files.
  6. 6
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  7. 7
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  8. 8
    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.