✳flâneur — a map of the web's best reading

How we built our multi-agent research system \ Anthropic

anthropic.com · 3,758 words · saved by 6 readers

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

Explore this link on the map →

saved by

related reading