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
- Best practices for coding with agents · Cursorcursor.com
- Continually improving our agent harness · Cursorcursor.com
- The third era of AI software developmentcursor.com
- Towards self-driving codebases · Cursorcursor.com
- Arjun Virkarjunvirk.com
- How we built Linear Agentlinear.app
- Why We Built Our Own Background Agentbuilders.ramp.com
- Scaling long-running autonomous coding · Cursorcursor.com
- Context Engineering for AI Agents: Lessons from Building Manusmanus.im
- Building Effective AI Agents \ Anthropicanthropic.com
- Building Effective AI Agents \ Anthropicanthropic.com
- Demystifying evals for AI agents \ Anthropicanthropic.com