AIF-C01 domain - 24% of the exam

Generative AI fundamentals

Generative AI fundamentals is 24% of the AWS Certified AI Practitioner (AIF-C01) exam. These are the objectives it covers, each with practice questions and worked explanations.

Objectives in this domain

Sample question from this domain

Free sampleGenerative AI fundamentalsmedium

A compliance team needs an LLM to return an identical answer every time it is given the same prompt, so generated audit summaries can be reproduced exactly. Which change best achieves deterministic output?

response = client.generate(
  prompt=audit_prompt,
  temperature=?,   # currently 0.7
  top_p=0.95
)
  • AIncrease the model context-window limit so the full document fits in one call.
  • BRaise the sampling temperature toward 1.0 for richer summaries.
  • CSet the sampling temperature to 0 so the model always picks the highest-probability token. Correct
  • DSwitch to a larger model with more parameters.
Temperature controls how randomly the model samples its next token. At temperature 0 the model is greedy: it always selects the single highest-probability token, so the same prompt produces the same output every run. That reproducibility is exactly what an audit trail requires.

Why C is correct: Correct. Temperature 0 forces greedy decoding, giving deterministic, reproducible output.

Examworthy is not affiliated with or endorsed by Amazon Web Services. Original, blueprint-aligned practice material only.