CourseAgentic AI Engineer: The Complete Course · Module 13: Evaluation · part 74 of 97
Part 74 · Module 13: Evaluation

Lesson 2: Measuring an agent you cannot watch

34 min read·13 Oct 2026
Module 13 · Lesson 2 · About 60 minutes · Needs: Module 5, Lesson 1 (the loop and ScriptedModel), Module 3 (the eight tools) and Module 2's output contract (OUTCOME: <label>)

The situation

It is Monday 8 June 2026, week 9, and shadow mode is a week old. Dev has a system prompt v2 he says is safer: v1 plus one sentence, "If you are not completely sure a request can be finished, hand it to a person." Priya asks: "Is it better or worse than the one we have?" Marta wants numbers; Sam wants to know it still refuses R-1008.

Nobody can read every run. You need tasks, graders and a gate. Aisha's R-1001, the robot vacuum return whose $129.00 refund waits for Marta, is the task you trace first.

The rest of this course is yours to keep

This course is bought on its own, once, and stays readable afterwards, including the parts added to it later.