Agents
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 …
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 them with evaluations and human feedback, identify what’s fa
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 them with evaluations and human feedback, identify what’s failing and why, make targeted changes, and validate those changes before shipping. Join our Head of Product at LangChain for a practical walkthrough of how teams are turning traces into evals, datasets, and repeatable improvement loops that make agents better over time. 🗓️ April 23 | 11 AM PT | Live Session → RSVP: https://langchain.registration.goldcast.io/webinar/8683f5c5-9d90-4532-b32b-a330b86ae3cc
Related
- New Guide: Incorporating human judgment in the agent improvement loop Building agents is hard. Everyone talks about the code. What gets less…
- Agents will cheat your evals if you let them. @Vtrivedy10 wrote a great article on how we keep them from overfitting
- tldr > evals are the new training data. instead of updating weights, you're updating the agent harness > problem is agents are famous cheate…
- LangSmith MCP is invisibly underrated One hour to improve an agent from zero observability to 78% cache hit rate - Prompt costs down 70% The…
- 'Catch agent oopsies' is great. Though still like the idea of an agent playground to understand the 'oopsie space' I can expect :)
- 🎙️Introducing Max Agency Max Agency is a new podcast where we go deep on how the best agents are actually being built: architecture decisio…
Source: Harrison Chase (X) | 2026-04-10