Measure agents with numbers you can defend, then use those numbers to improve prompts, tools and models.
Path 2 of 4, taken after LLM and Agent Foundations. First you learn to evaluate agents rigorously: error analysis, code graders, calibrated LLM judges and honest statistics. Then you put the eval suite to work optimising prompts, examples, tool descriptions and skills, by hand and automatically with DSPy and GEPA, and migrating safely between models.
2 courses13 lessons~33 hours
In this path
2
Courses
13
Lessons
~33
Hours
Each course builds on the one before it. Overviews are open to everyone; sign in to start the lessons.
Turn "it seems better" into numbers you can defend: error analysis, code graders, calibrated LLM judges and honest statistics.
2 modules · 6 lessons ~16h 6 quizzes Capstone
Modules
Capstone: A full eval suite for your drafting agent
Treat prompts, examples, tool descriptions and skills as versioned, measured artefacts, and improve them by hand, by optimiser and in production without breaking what already works.
2 modules · 7 lessons ~17h 7 quizzes Capstone
Modules
Capstone: Optimise and ship the questions drafter