AI 103 Assessment
Show that you can decide what an agent should remember, retrieve and be able to do
What is assessed
The assessment checks judgment, not vocabulary. It has four parts with the weights below.
| Part | Weight |
|---|---|
| Knowledge Checks (15 questions on context, memory, RAG, chunking, metadata and skills) | 20% |
| Decision Exercises (7 scenarios: Context, Memory, RAG, Tool; Remember, Retrieve, Ignore, Ask Again) | 20% |
| Hands-on Exercises (Agent Memory Policy, Knowledge Chunk & Metadata Design, Agent Skill Card) | 20% |
| Final Application (Agent Memory, Knowledge & Skills Canvas) | 40% |
Scoring and passing
Quiz scoring happens on the server. Correct answers and explanations never appear on public pages or in downloadable files. The passing threshold is 80%.
Info
Questions appear once you start the assessment.
Canvas rubric
| Criterion | Weight |
|---|---|
| Goal clarity | 10% |
| Memory design (what to keep, how long, who can see it) | 15% |
| Knowledge sources and retrieval | 15% |
| Chunking and metadata | 15% |
| Agent skills | 15% |
| Context optimization | 15% |
| Risks, boundaries and human review | 15% |
- 1Excellent
Every choice between memory, retrieval and skill has a reason. Chunk boundaries follow meaning, metadata is used as filters, skills define all seven parts, and risks, access control and human review are clear. - 2Competent
The main design is done, some reasons or skill parts are incomplete, and the boundaries are broadly sensible. - 3Needs improvement
Everything is remembered or pasted in, sources and versions are unclear, chunking follows a fixed length only, skills have no verification, or sensitive information is not addressed.
Reflection
Write 100 to 200 words in response to this question:
Info
Why should this information be remembered, retrieved, or provided as a skill?
Start
- Start the AI 103 assessment (post-test)
- My Learning: Progress and results