← Cursor changelog

Cloud Agents and Cursor Harness Improvements

This release significantly advances agent autonomy, enabling cloud agents to operate as a system without constant intervention. New event subscriptions allow agents to monitor PRs and Slack threads, automatically picking up work and driving tasks to completion, including CI fixes and addressing bot comments. Users benefit from custom modes for focused agent work, isolated virtual environments for subagents to test changes or fix bugs independently, and the introduction of long-lived goals for agents to pursue complex objectives. Additionally, follow-up messages can now steer agents mid-task without interruption, streamlining collaboration.

Changed

  • We're continuing to improve cloud agents and the Cursor harness so always-on agents can operate as a system, building and shipping software on their own without the need for intervention at each loop.
  • With this release, cloud agents can automatically pick up work in response to events, hold a goal until it's met, and stay on course through long-running sessions.
  • Cursor can now monitor your PRs, watch a Slack thread, or run scheduled tasks. Cursor Agent subscribes to an event source (a thread or conversation) and wakes when something happens. Subscriptions are available for cloud agents only, for now.
  • <figure><video src="https://ptht05hbb1ssoooe.public.blob.vercel-storage.com/assets/changelog/2026-08-13-changelog-subscriptions-ObbzEOzAUiaMhh70DUYG6fJZwv2SQ8.mov" controls preload="metadata" loop></video></figure>
  • Use any skill as a Custom Mode: a skill that stays pinned in the chat. Custom modes keep agents focused on a skill - you can think about it like "always on" skills.
  • From `/`, pick a skill and press ⌥⏎ (Mac) or Alt+Enter (Windows), or choose **Use as Mode**.
  • <figure><video src="https://ptht05hbb1ssoooe.public.blob.vercel-storage.com/assets/changelog/2026-08-13-changelog-sticky-skills-GyjHI2f0MGVFngQBebLBnlQjEkkxQm.mp4" controls preload="metadata" loop></video></figure>
  • Subagents can now run on their own virtual machines. Each gets an isolated copy of the project with clean context in its own cloud environment.
  • <figure><video src="https://ptht05hbb1ssoooe.public.blob.vercel-storage.com/assets/changelog/2026-08-13-changelog-subagents-YD3SIKspySs8zoib2kY7RAPA9Injca.mp4" controls preload="metadata" loop></video></figure>
  • Use `/goal` to give the agent a long-lived objective to work towards until it's fully complete.
  • <figure><video src="https://ptht05hbb1ssoooe.public.blob.vercel-storage.com/assets/changelog/2026-08-13-changelog-goal-CPDEcewlxhbdqRa131C8yZjhDdOGzb.mp4" controls preload="metadata" loop></video></figure>
  • You can now send a message to steer the agent while it's working without interruption. Follow-ups wait for the next tool call instead of cutting the agent off mid-action.
  • Type a follow-up and hit Send now, or press ⏎ twice.

Fixed

  • Cloud agents automatically subscribe to PRs they create and drive them to completion, fixing CI and addressing bot comments. In Slack, ask `@cursor check back in an hour and keep going until that feedback is in`.
  • Have subagents test the parent agent's changes in fresh environments or swarm independent fixes without collisions. Try `run a swarm of subagents to test my app for bugs, each in its own environment`.
  • Try `/goal fix all flaky tests and make CI green` in a new chat. Pair it with a custom mode to follow a playbook, or `/loop` for recurring check-ins.