Skip to course content
Free agentic AI fundamentals course

Introduction to Agentic AI and Workflow 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. The two questions for every state field are…

2. An agent's own unverified conclusion, left in the state…

3. Carrying a growing transcript makes a long run cost…

4. A handoff should be…

5. To verify that resume works, you must…

---

Answer Key and Explanations

Check these only after attempting every question.

1. B - can it be written down and read back, and would resuming be wrong without it?

The first rules things out - connections, file handles. The second rules things in - guard flags, counters.

2. B - becomes a premise for every later step, indistinguishable from what was read

Track how each fact was established, not only that it was, and carry forward only what a source supports.

3. B - quadratically more

It grows every turn AND is re-sent every turn. Short test runs cannot show it.

4. B - an explicit allowlist of fields

Passing everything carries credentials, carries text a later step may repeat, and inflates every downstream call.

5. B - resume in a genuinely separate process

An in-process test passes even when a step depends on a module-level variable that would not survive a restart.

Practical Check

Apply this module to your own work: complete the module activity for *State, Memory, Context and Handoff*, 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.