Production AI Systems: sections and modules
T4.2
Evaluation and release gates
Write an eval plan with golden sets, judges and gates.
About 3 h 57 min: 42 min reading + 3 h 15 min practice · 6 lessons
- Scope
- Offline and online evaluation
- Prerequisites
Lessons
Start module- 1The Evaluation Pyramid
6 min · Credited source
- 2Component and Trajectory Metrics
6 min · Credited source
- 3Golden Sets and Sample Size
7 min · Credited source
- 4Validating LLM Judges
6 min · Credited source
- 5Release Gates: Safety, Quality, and Cost
9 min · Credited source
- 6Practise Evaluation and Release-Gate Interview Questions
8 min · Credited source
Also used in this module
Lessons taught in another module that this one builds on.
- Evaluation and Release Gating
1 h · Opens the practice page
Practise and Check
- Deliverable
- Eval plan for P2
- Assessment
- Checkpoint
- Interview probe
- How do you know it works?
- Common mistakes
- Vibes-based evaluation
- Unvalidated LLM judges
Your Progress
Saved in this browser when you leave the box.