AI & ML Engineering · Unit 16 · AI Engineering
AI Evaluation
Testing AI systems the way software is tested, so changes do not break quality.
- 16.1
Building an Evaluation Dataset
Collecting real cases, edge cases and expected answers.
- 16.2
Automated Metrics
Exact match, similarity scores and task-specific checks.
- 16.3
LLM-as-a-Judge
Using a model to grade outputs, and checking the judge.
- 16.4
Human Evaluation
Rubrics, annotation and agreement between reviewers.
- 16.5
Regression Testing
Running evaluations on every change.
- 16.6
Tracing and Observability
Recording every step so failures can be explained.
Unit project
An evaluation suite for one of your earlier projects that runs automatically and catches a regression you introduce on purpose.
Paid learners get the full brief, submit it from their dashboard and have it reviewed. It goes in your portfolio.
Open every unit
Enrol once to open every unit, its videos and a reviewed project for your portfolio.