Untriaged issues rot: duplicates accumulate, priorities drift, and reporters never hear back. An agent can do the first pass on every new issue so the backlog stays trustworthy.

How to triage Linear issues with Cursor

• Watches. Fires when a new Linear issue is created.
• Investigates. Reads the issue and related code, applies labels and priority, and adds a comment with repro or context.
• Reports back. A labeled, prioritized issue with a context comment — flagged for a human when ambiguous.

Prerequisites & integrations

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

• Linear

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 issue triage automation for Linear.

Examine the issue. Add an eyes emoji reaction when you start looking at it. When opening PRs, include a line like "Resolves BUG-123" or "Fixes BUG-123" (where BUG-123 is the issue ID) so that the PR gets properly linked to the issue.

If the issue is neither a bug report nor a feature request, do nothing. Do not comment, do not create noise.

## Bug report

- If it's a bug report, investigate the bug and report your findings. This can be either refuting the bug or explaining the likely root cause.
- Use Datadog logs to assist, if applicable.
- If it's an easy fix, open a PR.
- If status is Triage, change status to Backlog if it's a real bug.

## Feature request

- If it's a feature request, plan out the high level approach and comment with the approach.
- If it's an easy change, make the change and open a PR.

How to set up automatic issue triage

1. Open the template in Automations to start from it.
2. Connect a repository if you want the agent to read or change code.
3. Choose the trigger and connect the tools it uses — Linear, Webhook.
4. Tune the prompt to your quality bar, then activate the automation.

Tips for customizing issue triage for your backlog

• 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.