CursorAnnouncement
Cloud Agents Start 3x Faster with Builds
Summary
Cursor’s Cloud Agents now use Builds, ready-to-use copies of a development environment prepared in the background. These environments include cloned repositories, installed dependencies, and completed install commands, allowing agents to start without repeating setup each session. Cursor refreshes environments regularly, keeps warm copies, and activates only successful builds; internally, environments boot 10x faster and time to first token is 3x faster. If a commit or dependency update breaks a build, the last successful build remains active, while users receive a notification and can debug in the background. Builds can be inspected in the Cloud Agents dashboard, where logs, commit SHAs, statuses, and agent run associations are available, with tools for agents to inspect or manage them.
Context
The release targets Cloud Agents startup time and resilience by preparing development environments before an agent session begins. It also provides visibility into build history and preserves a working environment when a newer build fails.
Approach / What changed
Builds run regularly in the background and become the starting environment only after succeeding. Warm copies are retained for faster launches; install commands prepare reusable dependencies and setup, while start commands handle services that must be fresh. Existing environments can enable Builds from the dashboard, test migration with a setup agent, trigger builds manually, debug failures with an agent, and configure a staleness threshold.
Takeaways
Builds prepare cloned repositories, dependencies, and install-script work ahead of an agent session, while the start command remains for session-fresh services.
A failed build does not replace the active environment: agents continue using the last successful build, and the failure is reported for background debugging.
The Builds tab shows status, logs, commit SHAs, and the build used by each agent run; agents can also inspect and manage builds with built-in tools.
FAQ
What belongs in the install command versus the start command?
Use the install command for anything that can be prepared ahead of time, such as repository setup and dependencies. The start command runs when an agent is first prompted and should focus on services that need to be fresh during that session.
What happens when a new build breaks after a commit or dependency update?
The broken build never becomes active. Agents keep using the last successful build, and the issue is reported so it can be debugged in the background.
How can an existing environment enable Builds?
Open the environment in the Cloud Agents dashboard, select the Builds tab, and click Enable Builds. A setup agent can first test the migration and show proposed configuration changes.
Source and freshness
- Source
- cursor.com
- Published
- Added to Yomu
Summaries are generated from the original by a language model. Check the original before relying on it.
Keep reading
Related reading
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
The best engineering reads, once a week
One useful email. Unsubscribe anytime.