Sentry, run by an agent.
An AI agent that monitors, triages, and summarizes your Sentry error activity.
What needs your approval
Sentry never changes anything without you.
Some read-only Sentry operations run on their own so your agent can gather what it needs. Anything that creates, edits or deletes waits for your approval.
A real run
An example of how a run works, including the approval step. Not a Sentry run.
Google Ads
Paid search
example
Connecting Sentry
About 5 minutes- Auth
- API key
- Setup
- About 5 minutes
Where to get access
Create a Sentry Auth Token at Settings > Auth Tokens with scopes: org:read, project:read, project:write, team:read, team:write, event:write.
docs.sentry.ioWhat it runs on its own schedule
- review new issues
0 * * * * - daily error digest
0 9 * * *
Example tasks
Real work people hand to an agent that uses Sentry.
- Generate a daily error digest and post it to Slack with the top 5 issues by frequency
- Monitor for new high-severity issues and create a Linear ticket automatically
- Summarize error trends for a release and surface regressions introduced by recent deploys
- Triage a spike in errors by grouping related issues and identifying the common root cause
Questions
Common questions about putting an agent on Sentry.
Put an agent on Sentry.
Connect it, give it one task, see the first run today.
Try for free