Nice primer for thinking about model-harness-context structures and protocols for agents.

He argues that traces and evals are the common foundation of all three loops, which is why LangChain built SmithDB and the new LangSmith AI Search for trace data, then covers what makes evals hard (realistic inputs, defining what good looks like, simulation environments) and how red teaming in LangSmith Engine looks for agent mistakes proactively. He closes with what he calls a North Star vision: an agent that notices its own mistakes, creates its own eval data points, and suggests its own fixes.

How to Build Agents That Improve Over Time: Model, Harness, Context | Interrupt London ↗