Cursor Automations, the always-on agent platform from Cursor, is expanding with a new generation of autonomous systems that streamline code review, incident response, and other engineering workflows.
The platform runs AI agents on schedules or in response to development events. These triggers include merged pull requests on GitHub, newly created issues in Linear, messages sent in Slack, incidents reported through PagerDuty, and custom webhook events. Cursor aims to help engineering teams keep up with the speed of software delivery by scaling code review, monitoring, and maintenance with autonomous agents.
“Automations are great for reviewing changes. They can catch and fix everything from style nits and inconsistencies to security vulnerabilities and performance regressions,” the company said in its announcement.
Three core automation systems
Cursor identified three high-impact automation categories integrated in its engineering pipeline:
Security review
Triggered on every push to the main branch, this agent audits code changes for security issues, skips items already discussed in pull requests, and posts high-risk findings to Slack. Because the agent operates asynchronously, it does not delay developer workflows.
Agentic codeowners
This system assesses pull request risk based on blast radius, technical complexity, and infrastructure impact. Low-risk changes are approved automatically, while higher-risk updates prompt reviewer assignments based on contribution history. Decisions are summarized in Slack and logged to Notion via MCP integrations so teams can review and refine agent behavior over time.
Incident response
When PagerDuty detects an incident, an automation launches an agent that uses Datadog integrations to investigate logs and examine recent code changes. The agent notifies on-call engineers in Slack with monitoring details and proposes a fix through an automated pull request.
Routine workflow automations
Cursor has also deployed agents for routine tasks and cross-tool coordination. Each morning, agents review recently merged code to identify areas lacking test coverage. Others triage bug reports by identifying duplicates, creating issues in Linear, investigating root causes, and posting summaries. Another automation publishes a weekly Slack digest of repository activity from the prior seven days.
