Learn AI Evaluation.
A structured path from absolute beginner to advanced AI evaluation. Understand how AI systems work, how quality is measured, how evaluation systems are built, and how modern teams test models in production.
Build evaluation knowledge in the right order.
Start with the fundamentals before moving into evaluation methods, scoring, test design, RAG, safety, multimodal systems, agents, production monitoring, and advanced benchmark design.
Your progress is stored locally in this browser. Sign-in based progress can be connected later.
The learning path.
Every stage builds on the previous one. You do not need an AI, machine learning, or programming background to begin.
Learn the concept.
Each lesson starts from plain language and gradually introduces the technical idea behind the evaluation problem.
Evaluate real examples.
Work through prompts, model responses, datasets, edge cases, scoring decisions, and failure examples.
Think like an evaluator.
Progress from reviewing individual responses to designing evaluation systems, benchmarks, judges, and production monitoring.