Building Effective AI Agents
Engineering at Anthropic Building effective agents Over the past year, we've worked with dozens of teams building large language model LLM agents across industries. …
Search
Demystifying evals for AI agents
… LLMs have progressed from 40% to 80% on this eval in just one year. …
Eval awareness in Claude Opus 4.6’s BrowseComp performance
… New contamination sources appear continuously, driven by the research community’s practice of using benchmark questions as worked examples in papers. …
Anthropic Economic Index report: Economic primitives
… In our productivity work , Claude’s time estimates correlate with actual time spent on software engineering tasks. …