Cursor now supports automations that run based on triggers and instructions you define.

Cursor

Cursor is launching Cursor Automations, a feature that lets developers build always-on AI agents triggered by schedules or events like Slack messages, GitHub PRs, Linear issues, or PagerDuty incidents. These cloud-based agents run in sandboxes, use configured MCPs and models, verify their own output, and can learn from past runs. Use cases demonstrated include automated security reviews on every push to main, agentic code ownership with risk-based PR routing, incident response with automated root cause analysis and fix PRs, weekly changelog digests, test coverage generation, and bug report triage. Rippling engineers are already using it to build personal task dashboards and automate Jira/Confluence workflows. Agents can be configured via templates or custom webhooks.

Build agents that run automatically · Cursor

# Upgrading the software engineering pipeline