Storybooks and UI tests that can be applied directly to practice
How to Use Storybooks A to Z. We show you everything about storybooks.
578 learners
Level Basic
Course period Unlimited
[Course Launch] How to Prove AI Agent Performance: Advanced Evaluation Practice
Hello! As I previewed when announcing the publication of my first book, the 'AI Agent Evaluation' advanced course has finally opened!๐
As mentioned in my previous message, if the book established the 'theoretical foundation and core principles' of evaluation, this lecture is a complete hands-on and application guide on how to automate and build this into a system in a practical work environment.
As you can see in the attached table of contents, this course is packed with essential content for managing agents through objective metrics that go beyond subjective testing.
๐ Key Lecture Content
Everything about building a Golden Dataset: Efficient evaluation dataset generation techniques using the RAGAS library, LangSmith, custom agents, and Claude Code Agent Skills
Multi-faceted Evaluation Practice: From e2e evaluation checking the accuracy of the final answer, to Component Evaluation verifying whether documents were retrieved correctly and whether tools were used in the proper sequence (Trajectory).
Applying Advanced Evaluation Metrics and Frameworks: Anthropic's recommended agent evaluation metrics, and methods for measuring AI potential (
pass@k) and consistency (pass^k)How to build a sustainable evaluation system
This will be the most reliable guide for those who want to go beyond simply 'implementing' an agent and instead 'prove' and optimize whether their AI "always works correctly" at a production level using data. If you have built a solid foundation through the book, now experience the 'completion of evaluation' firsthand through this follow-up practical course!
We are currently offering a 30% early bird discount to celebrate the launch, so experience the 'completion of evaluation' right now based on the solid theory you built through the book!