Skip to course content
Free CrewAI course

CrewAI for Multi-Agent Automation

Module 04 Knowledge Check

5 questions. Pass mark 4 out of 5. Answer every question before checking the answer key below, then retry after reading the feedback.

1. Tools should be assigned…

2. Giving an agent too many tools tends to…

3. Knowledge sources attached to a crew should be treated as…

4. Shared memory across agents raises the risk of…

5. Memory containing user or client data requires…

---

Answer Key and Explanations

Check these only after attempting every question.

1. B - Only to the agent whose role requires them

Least privilege limits both accidental misuse and the impact of prompt injection.

2. B - Degrade tool-selection accuracy and widen the risk surface

Choice quality falls as the option set grows, and every extra tool is extra exposure.

3. B - Retrieved context whose relevance and freshness still need checking

Attaching a knowledge source does not make the output grounded or current.

4. B - One agent's unverified assumption propagating as established fact

Memory spreads errors as efficiently as it spreads useful context.

5. B - Scoping, retention limits, and a deletion path

Agent memory is a data store and must be governed as one.

Practical Check

Apply this module to your own work: complete the module activity for *Tools, Knowledge, and Memory*, then write one sentence naming what your result shows and one naming what it does not.

Strong Answer Pattern

A strong answer names the task, the evidence used, the check performed, and the remaining limitation. It avoids "proved", "guaranteed", or "always" unless the evidence genuinely supports it.