Skip to content

Automate Sentry

Turn your Sentry issues into updates your team actually reads. A brand-new error can go straight to Slack, yesterday's issues arrive as a morning list with event counts, Friday brings a release digest with the new issues each deploy introduced, and the top unresolved errors get a plain-English explanation. Say what you want to your AI assistant, confirm the steps it lays out, and the automation then keeps working unattended.

Try asking

Create a ClickRuntime automation: every weekday at 9am, email me the Sentry issues first seen in the last 24 hours in my web-frontend and api projects, sorted by event count.

Paste it into your assistant. It tells you what it will send or change before it runs live.

Build your own

Build any Sentry automation you can describe

The ideas above are ready-made starting points, not a fixed list. Describe what Sentry should do in your own words, with your conditions, other apps or an AI step, and your assistant writes it, tests it and runs it on ClickRuntime.
  • Your own rules

    Conditions, thresholds, filters and exceptions, written the way you'd explain them to a colleague.

  • Any number of apps

    One automation can read from one app and update several others. Over 248 apps are ready, and anything with an API works too.

  • AI where it helps

    Summaries, classification, extraction and drafts use ClickRuntime's built-in AI, with no extra key.

  • On a schedule or on each event

    Runs as often as every 5 minutes, or the moment an app sends an event, and keeps track of what it already handled.

For example, ask your assistant

Every hour, check Sentry for new issues affecting more than 50 users and send me only those with an AI summary of the stack trace.

When a new Sentry issue appears in production, post it to our #errors Slack channel with the culprit and event count.

When a Sentry issue passes 100 events in an hour, create a Jira bug with the stack trace, post it to Slack, and page the on-call person in PagerDuty.

Beyond chat

Have Sentry work when you're not in the chat

Connecting Sentry to ChatGPT or Claude lets you ask about it while you chat. ClickRuntime handles the part that should happen on its own: checks on a schedule and actions on each new event, set up from the same chat and running after you close it.

Setup

Connect Sentry

Sentry is connected with a token from an internal integration you create in your own organization. It belongs to the org, so it keeps working if the person who set it up leaves.

Sentry

Developer / Error monitoring

  1. In Sentry, go to Settings, then Developer Settings, then Custom Integrations, and choose Create New Integration, then Internal Integration.
  2. Name it and pick the scopes your automations need, for example project:read, event:read and org:read, then save.
  3. Copy the token straight away, since Sentry only shows it once. A personal token from User settings, then Personal Tokens, also works.
  4. Save the token as a secret on Connections & secrets in the ClickRuntime dashboard. If you use Sentry's EU region or a self-hosted server, tell your assistant the host.

Good to know

Sentry limits that affect automations

  • Only org Managers and Owners can create an internal integration; other members can use a personal token instead.
  • Org auth tokens (starting sntrys_) are meant for CI and come with fixed permissions, so they suit release uploads rather than reading issues.
  • The integration token is displayed a single time. If you lose it, create a new one and replace the secret.

FAQ

Questions about automating Sentry

What can ClickRuntime read from Sentry?
Whatever the token's scopes cover. With `project:read`, `event:read` and `org:read` it can list issues, read their latest events and look up releases and their new-issue counts.
How fast do new-issue alerts arrive?
An internal integration can send an issue-created webhook to a ClickRuntime link, so the Slack post goes out as soon as Sentry fires it. Without the webhook, the automation polls on a schedule instead.
Does it work with the EU region or self-hosted Sentry?
Yes. EU accounts use `de.sentry.io` and self-hosted installs use your own host; mention which one when you set the automation up.
Does the error explanation need my own AI key?
No. The weekly summary of top errors uses the AI that comes with every ClickRuntime plan. The digests and alerts work without AI at all.
Can it resolve or assign issues?
The automations here only read from Sentry and report what they find. They don't change issue status.
Is this a Sentry connector for ChatGPT or Claude?
Not for chatting with Sentry data. A chat connector lets your assistant read and change Sentry while you're in the conversation. ClickRuntime is for the work that should happen without you: you set up an automation from the chat once, and it keeps running on a schedule or on each Sentry event.

Tell your assistant what Sentry should do

Free plan. No credit card.