How to Write AI Agent Evals That Prove You Wrong
Write AI agent evals that catch what you missed: source cases from production traces, spot tests that pass for the wrong reason, and know when to overrule an LLM judge.
Evals• 18 min read
Prompting
Posts tagged Prompting.
The Art of Agent Prompting: Anthropic’s Playbook for Reliable AI Agents
Learn Anthropic’s production-tested playbook for prompting AI agents like Claude Code. We distill their principles, heuristics, and eval strategies into a practical guide you can use to build reliable, tool-using agents for the real world.
AI Agents• 12 min read