Effective harnesses for long-running agents \ Anthropic

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

As AI agents become more capable, developers are increasingly asking them to take on complex tasks requiring work that spans hours, or even days. However, getting agents to make consistent progress across multiple context windows remains an open problem. The core challenge of long-running agents is that they must work in discrete sessions, and each new session begins with no memory of what came before. Imagine a software project staffed by engineers working in shifts, where each new engineer arrives with no memory of what happened on the previous shift. Because context windows are limited, and

saved by

• Proby Shandilya
• Jayaditya Sethi
• Timothy Kostolansky
• Proby Shandilya
• Keshav Raj Singhal

related reading

• Harness design for long-running application developmentanthropic.com
• Effective context engineering for AI agents \ Anthropicanthropic.com
• Scaling Managed Agents: Decoupling the brain from the hands \ Anthropicanthropic.com
• Building Effective AI Agents \ Anthropicanthropic.com
• Towards self-driving codebases · Cursorcursor.com
• When AI builds itself \ Anthropicanthropic.com
• Building Effective AI Agents \ Anthropicanthropic.com
• Claude’s Constitution \ Anthropicanthropic.com
• Best practices for Claude Code - Claude Code Docsanthropic.com
• AddyOsmani.com - Long-running Agentsaddyosmani.com
• Demystifying evals for AI agents \ Anthropicanthropic.com
• Why We Built Our Own Background Agentbuilders.ramp.com