\n<\/p>\n
As agentic coding spreads, the working life of a software engineer has become dazzlingly complex. A single engineer might oversee dozens of coding agents at once, launching and guiding different processes as necessary. <\/p>\n
It\u2019s a lot to keep track of, and human engineers\u2019 attention has quickly become the limiting resource.<\/p>\n
Cursor launched a new tool Thursday aimed at keeping that chaos in check. Called Automations, the new system gives users a way to automatically launch agents within their coding environment, triggered by a new addition to the codebase, a Slack message, or a simple timer. As Cursor describes it, it\u2019s a way to review and maintain all the new code created by agentic tools \u2014 without tracking dozens of agents at once.<\/p>\n
At the most basic level, Automations are a way for engineers to break out of the \u201cprompt-and-monitor\u201d dynamic that defines most agent-based engineering. Instead of launching agents with a human prompt, Cursor\u2019s Automation framework lets you launch agents automatically \u2014 and loop humans in whenever they\u2019re needed.<\/p>\n
\u201cIt\u2019s not that humans are completely out of the picture,\u201d Jonas Nelle, Cursor\u2019s engineering chief for asynchronous agents told TechCrunch in an interview. \u201dIt\u2019s that they aren\u2019t always initiating. They\u2019re called in at the right points in this conveyor belt.\u201d<\/p>\n
One early example is Bugbot<\/a>, a long-standing Cursor feature that the team sees as a predecessor to the broader Automation system. The Bugbot system is triggered every time an engineer makes an addition to the codebase, and reviews the new code for bugs and other issues. Using Automations, Cursor has been able to expand that system to more involved security audits and more thorough reviews.<\/p>\n \u201cThis idea of thinking harder, spending more tokens to find harder issues, has been really valuable,\u201d said\u00a0 engineering lead Josh Ma.<\/p>\n Techcrunch event<\/p>\n \n\t\t\t\t\t\t\t\t\tSan Francisco, CA<\/span> Cursor estimates that it runs hundreds of automations per hour, reaching far beyond simple code review. The system is also used for incident response, with PagerDuty incidents initiating an agent that can immediately query server logs through an MCP connection. A separate automation offers weekly summaries of changes to the codebase on Cursor\u2019s company Slack.<\/p>\n \u201cIn the abstract, anything that an automation kicks off, a human could have also kicked off,\u201d said Nelle. \u201cBut by making it automatic, you change the types of tasks that models can usefully do in a codebase.\u201d<\/p>\n The new system comes amid intense competition in the agentic coding space, with both OpenAI<\/a> and Anthropic<\/a> having made significant updates to their agentic coding tools in the past month.\u00a0<\/p>\n Ramp data<\/a> shows Cursor\u2019s market share holding steady since May, with roughly 25% of generative AI clients customers subscribing to Cursor in some capacity.<\/p>\n Still, the overall growth of the agentic coding space has kept the company\u2019s revenue increasing at a stunning pace. Earlier this week<\/a>, Bloomberg reported that Cursor\u2019s annual revenue had grown to more than $2 billion, doubling over the past three months.<\/p>\n<\/div>\n
\n\t\t\t\t\t\t\t\t\t\t\t\t\t|<\/span>
\n\t\t\t\t\t\t\t\t\t\t\t\t\tOctober 13-15, 2026<\/span>\n\t\t\t\t\t\t\t<\/p>\n<\/p><\/div>\n<\/p><\/div>\n<\/div>\n