Labs: Evaluation + Quality Assurance¶
Practical Lab¶
Objectives¶
- Build a repeatable eval harness.
- Run baseline and regression comparisons.
- Configure fail conditions for gate behavior.
Rubric¶
| Task | Points | Criteria |
|---|---|---|
| Basics | 25 | Complete basic implementation |
| Intermediate | 50 | Add intermediate patterns |
| Advanced | 25 | Implement production considerations |
| Total | 100 | Pass all criteria |