Harness design for long-running application development \ Anthropic

Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

Written by Prithvi Rajasekaran, a member of our Labs team. Over the past several months I’ve been working on two interconnected problems: getting Claude to produce high-quality frontend designs, and getting it to build complete applications without human intervention. This work originated with earlier efforts on our frontend design skill and long-running coding agent harness, where my colleagues and I were able to improve Claude’s performance well above baseline through prompt engineering and harness design—but both eventually hit ceilings. To break through, I sought out novel AI…

saved by

• Cheikh Fiteni
• Akira Yoshiyama
• Lucas Xie
• Keshav Raj Singhal

related reading

• Effective harnesses for long-running agents \ Anthropicanthropic.com
• Continually improving our agent harnesscursor.com
• Demystifying evals for AI agents \ Anthropicanthropic.com
• How we built our multi-agent research system \ Anthropicanthropic.com
• Building Effective AI Agents \ Anthropicanthropic.com
• How to Harness Coding Agents with the Right Infrastructure | Blogalexlavaee.me
• Quantifying infrastructure noise in agentic coding evals \ Anthropicanthropic.com
• When AI builds itself \ Anthropicanthropic.com
• Towards self-driving codebases · Cursorcursor.com
• Scaling Managed Agents: Decoupling the brain from the hands \ Anthropicanthropic.com
• Building Effective AI Agents \ Anthropicanthropic.com
• Welcome to Learn Harness Engineeringwalkinglabs.github.io