What we’ve learned building cloud agents · Cursor
After a year of shipping cloud agents, we’ve learned that environment quality, durable execution, and the right harness boundaries drive autonomous performance.
Blog / research When we first launched cloud agents a year ago, they seemed like a straightforward extension of local agents. Since then, cloud agent capabilities have expanded considerably. Cloud agents now run on their own dedicated virtual machines, with their own environments, dependencies, and network access. They can work in parallel, run unattended, and take on longer tasks than a local agent sitting on your laptop. These capabilities introduce challenges around environment setup, reliability, and orchestration that are less pronounced when an agent is running on your laptop. In this po
saved by
related reading
- Arjun Virkarjunvirk.com
- Best practices for coding with agents · Cursorcursor.com
- The third era of AI software developmentcursor.com
- Continually improving our agent harness · Cursorcursor.com
- Agent Observability and Tracingarize.com
- Why We Built Our Own Background Agentbuilders.ramp.com
- Effective harnesses for long-running agents \ Anthropicanthropic.com
- AddyOsmani.com - Long-running Agentsaddyosmani.com
- Building Effective AI Agents \ Anthropicanthropic.com
- Building Effective AI Agents \ Anthropicanthropic.com
- The Age of Async Agents — Cognition's Walden Yan & OpenInspect's Cole Murraylatent.space
- Demystifying evals for AI agents \ Anthropicanthropic.com