Stop guessing how to fix your agent

Learn More: bit.ly/4ikf9L0 Traditional software tests confirm that your code is working, but fall short when it comes to testing agents. Evals allow you to measure an agent’s decisions and actions when its failures may not be obvious. In our new course, Evaluating and Improving Agentic Applications, built in partnership with Arize AI, you’ll take an agent through the full evaluation process, from reading its traces to improving it. Taught by Laurie Voss, Head of Developer Relations at Arize and co-founder of npm. In this course, you’ll learn how to: Read your agent’s traces to find recurring failures and turn them into a test set you can rerun after every change. Automate evaluation with code and LLM judges you can rely on. Use your evals to check that every change makes your agent better. Enroll for free: bit.ly/4ikf9L0