Cloud agents start 3x faster with builds

Summary

Cursor introduces builds for Cloud Agents, continuously prepared copies of development environments that replace just-in-time machine boot, repository cloning, dependency installation, and install-script execution. Builds run by default every hour; successful builds become the starting point for future agents, which fork warm live machines rather than restoring environments from disk. The post reports 10x faster internal environment boot times and 3x faster time to first token, while customers cite quick starts and uninterrupted automated runs when builds fail. If a dependency bump or Docker build breaks installation, the failed build stays inactive and sessions continue from the last successful version while debugging proceeds. The Cloud Agents dashboard exposes build status, logs, captured commit SHAs, and run-to-build links, while a git-state threshold and Cursor Cloud MCP support oversight; setup requires moving preparable work into install and reserving fresh services for start.

Takeaways

1. 1

   Successful builds provide ready environments with cloned repositories, installed dependencies, and completed install scripts, allowing agents to fork warm machines instead of setting up from scratch.

2. 2

   A failed dependency update or Docker build does not replace the active environment: new and existing sessions keep using the last successful build while the problem is debugged.

3. 3

   Builds expose logs, versioning, commit SHAs, and agent-run associations; user secrets are added when an agent starts, while team or environment secrets can support build-time installation.