Manuals / AI Agents & Workflows / Chapter 3
Steady · beginner · ~30 min · Chapter 3 of 3
Evaluate the loop
Score task success, cost, and scary failures — not vibes.
Tiny eval set
10 real tasks with expected outcomes. Run weekly when you change prompts/tools.
Tiny eval setDrag stickies · tap for tips
Do this now
Write 5 eval tasks for your agent idea.
Was this step clear?
Chapter learning outcomes
Clear these before you leave