New Guide: Incorporating human judgment in the agent improvement loop Building agents is hard. Everyone talks about the code. What gets less…

New Guide: Incorporating human judgment in the agent improvement loop Building agents is hard. Everyone talks about the code. What gets less attention is how to capture domain expert knowledge and actually get it into your agent. The most successful teams follow an agent improvement loop. They deploy early, get experts to review what's going wrong, and turn that feedback into automated evals. Then they repeat. Rahul Verma, deployed engineer, wrote about how to do this in practice -- using a trader copilot as a running example: https://blog.langchain.com/human-judgment-in-the-agent-improvement-loop/ Media

Related

• Human judgment in the agent improvement loop
• What does it actually take to make agents better over time? A system that starts with a trace. You capture traces of agent behavior, enrich …
• tldr > evals are the new training data. instead of updating weights, you're updating the agent harness > problem is agents are famous cheate…
• here's how we're improving our base harness, you can apply these same lessons to hill-climbing for your application-specific harness!
• This 10-min read from @Vtrivedy10 changes how you build AI agents. Most people are stuck in the same loop; switching models when agents brea…

Source: Harrison Chase (X) | 2026-04-10