How we built our multi-agent research system \ Anthropic

On the the engineering challenges and lessons learned from building Claude's Research system

Claude now has Research capabilities that allow it to search across the web, Google Workspace, and any integrations to accomplish complex tasks. The journey of this multi-agent system from prototype to production taught us critical lessons about system architecture, tool design, and prompt engineering. A multi-agent system consists of multiple agents (LLMs autonomously using tools in a loop) working together. Our Research feature involves an agent that plans a research process based on user queries, and then uses tools to create parallel agents that search for information simultaneously. Syste

saved by

• Katherine Driscoll
• surya
• Timothy Kostolansky
• Grace S
• yash raj
• Kevin Zhang

related reading

• How we built our multi-agent research system \ Anthropicanthropic.com
• The Pieces of The Loop - by Interesting Engineering ++interestingengineering.substack.com
• LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
• Building Effective AI Agents \ Anthropicanthropic.com
• Effective harnesses for long-running agents \ Anthropicanthropic.com
• karl.pdfdatabricks.com
• Towards self-driving codebases · Cursorcursor.com
• Building Effective AI Agents \ Anthropicanthropic.com
• Automated Weak-to-Strong Researcheralignment.anthropic.com
• Demystifying evals for AI agents \ Anthropicanthropic.com
• Effective context engineering for AI agents \ Anthropicanthropic.com
• Don’t Build Multi-Agents | Cognitioncognition.ai