Section checkpoint

Your First AI App

9 questions drawn from the 3 chapters in this section. If most land on the first try, you are ready for the next section. If not, the explanation after each answer says which idea to revisit.

Checkpoint

9 questions · first-try answers earn the most XP

1. The chat completion API is described as stateless. What follows for multi-turn conversations?

2. Which three things should you add before this code runs in production?

3. Why does the chapter set a low temperature on a first LLM API call?

4. Why does the guidance say to change either temperature or top-p, but not both at once?

5. What is a stop sequence used for in a completion request?

6. A team sets temperature 0.8 for every feature including data extraction. What is the likely consequence?

7. Why validate structured output with a schema library such as Pydantic or Zod instead of checking the keys by hand?

8. Which prompt change most improves the odds of getting output that parses first time?

9. Where should a validation error from a schema check be surfaced so the failure is visible?

What this checkpoint covers

Next section: Prompt Engineering