Cursor has launched a new tool called Automations, designed to automatically launch coding agents triggered by codebase additions, Slack messages, or timers, aiming to simplify managing multiple agents.
The system is intended to manage the complexity of overseeing multiple agents and expands on existing features to handle security audits and thorough reviews. According to Cursor, the system runs hundreds of automations per hour, including incident response triggered by PagerDuty to query server logs and weekly codebase summaries sent to Slack.
Automations builds on the existing Bugbot feature, which reviews new code for bugs. Using Automations, Cursor has expanded that system to more involved security audits. The company emphasizes that while humans are still involved in the process, they are not always the initiators, instead being called in at specific points.
“It’s not that humans are completely out of the picture,” said Jonas Nelle, Cursor’s engineering chief for asynchronous agents. “It’s that they aren’t always initiating. They’re called in at the right points in this conveyor belt.”
The launch comes as OpenAI and Anthropic have made significant updates to their agentic coding tools in the past month, intensifying competition in the space. Despite this, Ramp data shows Cursor’s market share holding steady since May, with roughly 25% of generative AI clients subscribing to Cursor.
Earlier this week, Bloomberg reported Cursor’s annual revenue grew to more than $2 billion, doubling over the past three months.
