Skip to course content
Free generative AI app course

Generative AI Application Development with Python

Module 12 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. A typical log line's prompt field contains…

2. Redaction should happen…

3. Pattern-based redaction does not catch…

4. Retention should be set…

5. Whether your content is used for model training depends on…

---

Answer Key and Explanations

Check these only after attempting every question.

1. B - the user's input and whatever you retrieved

That makes the log store a second copy of both, usually with broader access than the primary one.

2. B - in a nightly cleanup job

A log capturing raw content with a plan to clean it later is personal data with a plan attached.

3. B - a customer writing their own name and address in free text

Which is why retention limits and access control are not optional alongside it.

4. B - per field

One policy forces you to over-retain the sensitive part in order to keep aggregate metrics.

5. B - your provider's terms

Read them before writing the notice, and check again when you change provider.

Practical Check

Apply this module to your own work: complete the module activity for *Privacy, Logging and Safe Deployment Boundaries*, 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.