Cursor announced the launch of Automations, a system designed to create always-running AI agents that automatically monitor, review, and maintain codebases. The new feature allows developers to configure agents that operate continuously in the background, triggered by events such as Slack messages, newly created issues, merged pull requests, or PagerDuty incidents.
The company said Automations are intended to address a growing imbalance in modern software development. While AI coding agents have dramatically increased the amount of code developers can produce, related processes such as code review, monitoring, and maintenance have not advanced at the same pace. Cursor’s Automations aim to close that gap by deploying agents that automatically handle those tasks.
When an automation is triggered, the system launches an agent in a cloud sandbox environment. The agent follows predefined instructions, interacts with configured models and integrations, and verifies its own output. These agents also have access to memory tools that allow them to learn from previous runs and improve over time.
Cursor highlighted several internal use cases for Automations, particularly around code review and monitoring. For example, a security review automation runs whenever code is pushed to the main branch, analyzing code changes for potential vulnerabilities and flagging high-risk issues to engineers via Slack notifications. Another automation evaluates pull requests by classifying their risk level based on factors such as infrastructure impact and complexity. Low-risk pull requests may be automatically approved, while higher-risk changes are assigned to human reviewers.
The company also said Automations can significantly speed up incident response. When triggered by a PagerDuty alert, an automation launches an agent that investigates logs via integrations with monitoring tools, analyzes recent code changes, and proposes fixes, which are shared with engineers through Slack and pull requests.
Beyond code review and incident response, Cursor noted that Automations can handle routine engineering tasks and internal workflows. These include generating weekly summaries of codebase changes, identifying gaps in test coverage, and triaging bug reports by checking for duplicates and creating issues in project management systems.
The system has also begun to see adoption outside Cursor. At Rippling, engineers are using automations to aggregate meeting notes, action items, GitHub pull requests, and Slack messages into centralized dashboards. Additional automations generate Jira issues from Slack threads and summarize discussions into documentation platforms.
Cursor said these capabilities enable teams to build what it describes as a “software factory,” where AI agents continuously monitor and improve a codebase using cloud infrastructure, integrations, and configurable workflows.
KEY QUOTES:
“We’re introducing Cursor Automations to build always-on agents. These agents run on schedules or are triggered by events like a sent Slack message, a newly created Linear issue, a merged GitHub PR, or a PagerDuty incident.”
Jack Pertschuk, Jon Kaplan & Josh Ma — Authors Of Cursor Product Announcement
“I love that automations work for both quick wins and more complex workflows. I can schedule the obvious stuff in seconds, but I still have full flexibility to catch any webhook or plug into custom MCPs when I need to.”
Trent Haines — Software Engineer At Decagon
“Automations have made the repetitive aspects of my work easy to offload. By making automations to round up tasks, deal with doc updates, and respond to Slack messages, I can focus on the things that matter. Anything can be an automation!”
Tim Fall — Senior Staff Software Engineer At Rippling
“We built our software factory using Cursor Automations with Runlayer MCP and plugins. We move faster than teams five times our size because our agents have the right tools, the right context, and the right guardrails.”
Tal Peretz — Co-Founder Of Runlayer
