Cursor launched a new automation tool designed to manage coding agents on Thursday. The system, called Automations, automatically launches agents triggered by events like new code additions, Slack messages, or timers. This aims to shift engineers from a “prompt-and-monitor” dynamic to a model where humans are looped in only when needed.
The tool addresses the complexity of overseeing dozens of coding agents simultaneously. By automating agent launches, the system seeks to reduce the manual tracking required in agentic coding environments. This moves the workflow toward a “conveyor belt” model where human intervention is targeted and specific.
We're introducing Cursor Automations to build always-on agents. pic.twitter.com/uxgTbncJlM
— Cursor (@cursor_ai) March 5, 2026
The system expands upon the existing “Bugbot” feature, which reviews new code for bugs. Using Automations, Bugbot’s capabilities have been extended to include more involved security audits and thorough reviews. “This idea of thinking harder, spending more tokens to find harder issues, has been really valuable,” said engineering lead Josh Ma.
Cursor utilizes the system for various operational tasks beyond code review. It triggers agents to query server logs immediately following PagerDuty incidents. A separate automation provides weekly summaries of codebase changes to the company’s internal Slack channel.
“It’s not that humans are completely out of the picture,” said Jonas Nelle, Cursor’s engineering chief for asynchronous agents. “They’re called in at the right points in this conveyor belt.”
The launch occurs amid competition from OpenAI and Anthropic in the agentic coding space. Ramp data indicates Cursor’s market share is holding steady at roughly 25% of generative AI clients.
Despite the competition, Cursor’s financial growth remains high. Bloomberg reported this week that Cursor’s annual revenue has grown to over $2 billion. The company’s revenue has doubled over the past three months.
Featured image credit
