AI Engineering · 400-level

Evals & Quality Systems

AIE-4013 creditscorebadge: evaluatorprereqs: AIE-203, AIE-301
Start this course — free

Earn the evaluator credential

What's inside

Sections & lessons

01

Golden datasets & rubric design

  • Writing the 20 cases a system must passconcept45 min
02

Code graders vs. LLM-as-judge

  • Deterministic checks next to a judge model, run togetherconcept60 min
03

The disagreement heat-map

  • Where the code grader and the AI judge part waysconcept60 min
04

Grader-hacking

  • Crafting an output that fools the judge but still fails the code graderconcept60 min
05

Reward-model bias & judge drift

  • Teaching a simple reward model your own bias, then seeing itconcept60 min
06

Quiz: eval-design judgment

  • Checkpoint on rubric gaps and grader-hacking riskconcept30 min
07

Lab + eval-gate: golden set + grading suite

  • 20-case golden set, two graders, threshold pass (Evaluator badge)concept120 min
Learn it from the inside

This module's playgrounds

Vocabulary

Key concepts in this course

Compare related approaches

This module ends in a gate you can fail.

That's what makes passing it mean something. Take the DSAT, get placed, and start earning.