How to Write Evals for an AI Agent: A Practical Starter Guide
Build your first agent eval suite step by step: pick real tasks, grade outcomes instead of paths, measure consistency with pass^k and read the transcripts.
Practical notes on building AI agents that work
Hands-on guides to building AI agents: evals, tool design, memory, debugging and cost. Clear explanations, working code, cited sources.
Why Your Agent Calls the Wrong Tool (and How to Fix It)
A debugging checklist for tool-calling agents: overlapping tools, vague descriptions, ambiguous parameters, noisy responses and unhelpful errors, with a fix for each.
Prompt Caching for AI Agents: How to Cut Input Costs
How prompt caching works on Claude and OpenAI, how to order an agent's prompt so the cache actually hits, and how to measure your hit rate from the usage fields.