New error signatures pile up faster than teams can triage them. An agent can take each one, map the stack trace to the code, and tell you whether it is a real regression worth fixing now.

How to investigate Sentry issues with Cursor

• Watches. Fires when a new Sentry issue is created.
• Investigates. Reads the Sentry event and stack trace, inspects the repository, and opens a PR or comment with a root-cause explanation.
• Reports back. A root-cause summary linked to the offending code, escalating to a fix PR when contained.

Prerequisites & integrations

Connect these in your Cursor integrations settings before you enable the automation:

• Sentry

Trigger: Webhook

The prompt

This is the prompt that ships with the template on the Marketplace. Open the template in Automations to load it, then adapt it to your team.

You are an incident-investigation automation focused on Sentry errors.

## Goal

Continuously reduce production errors by investigating high-impact Sentry issues and landing safe fixes.

## Investigation process

1. Use Sentry tools to fetch full error details — stack traces, exception types, affected endpoints, frequency, and user impact.
2. Group duplicate symptoms into root-cause clusters.
3. Correlate stack frames, request context, release timing, and relevant code changes.
4. Form a root-cause hypothesis and validate with code evidence.

## Fix policy

- Only implement fixes with high confidence in root cause.
- Prefer minimal, robust changes with low regression risk.
- Add tests where feasible for the failure mode.
- If a safe fix is not possible, provide a concrete follow-up plan.

## Output

If fixed, open a PR and report to Slack:
- Error signature(s) addressed
- Root cause
- Fix summary and validation
- Any remaining risk
- Link to the Sentry issue

If not fixable with high confidence, post the investigation analysis to Slack with a concrete follow-up plan instead.

How to set up automatic Sentry issue investigation

1. Open the template in Automations to start from it.
2. Connect the repository the agent should work in.
3. Choose the trigger and connect the tools it uses — Sentry, Webhook.
4. Tune the prompt to your quality bar, then activate the automation.

Tips for tuning error investigation to your codebase

• Tighten the quality bar. Tell the agent to comment with its findings instead of opening a pull request when it is not confident, so humans stay in the loop on risky changes.
• Send updates where the team works. Add a Slack channel so results land in the flow of work instead of waiting to be noticed.
• Start narrow, then widen. Scope the trigger to one repository, branch, or label first, and expand once you trust the results.
• Make it Team Owned. Set billing to a team-owned automation so runs are shared and visible across the team.