AIF-C01 Applications of Foundation Models Practice Question
A media company runs a daily news digest built on Amazon Bedrock with Anthropic Claude. Editors complain that summaries of long policy documents sometimes omit the final recommendations, even though the source text clearly contains them near the end. The requests currently pass only the document body and set a maximum output length of 300 tokens. Which change best addresses the truncation of the source content before the model reasons over it?
⚠ Common exam trap
The trap here is assuming that a larger output token limit also expands how much source text the model can read.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Chunk the document and apply retrieval or summarization so all sections reach the model.
The symptom points to input truncation: content beyond the context window is discarded before the model sees it, so the closing recommendations vanish. Increasing output length or changing sampling cannot recover text that never entered the prompt. Chunking the document, then summarizing or retrieving relevant chunks, ensures the full source is represented and the recommendations reach the model.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Chunk the document and apply retrieval or summarization so all sections reach the model.
Why this is correct
When the source exceeds the model's context window, the trailing content is silently truncated, so recommendations at the end never reach inference. Splitting the document into chunks and either summarizing hierarchically or retrieving the most relevant passages ensures every section is represented, restoring the omitted recommendations without exceeding context limits.
- ✗
Raise the temperature setting so the model explores more of the document.
Why it's wrong here
Temperature controls randomness in token sampling during generation, making output more or less varied. It has no effect on how many input tokens are accepted or whether the end of a long document is included. Changing it here would only make summaries less deterministic, not recover missing recommendations.
- ✗
Increase the maxTokens parameter so the digest can be longer.
Why it's wrong here
Raising maxTokens only extends how many tokens the model may generate in its reply. It does nothing about how much of the input document fits into the model's context window, so the tail of the policy document would still be dropped before inference begins. This parameter governs output length, not input handling.
- ✗
Switch the model invocation to streaming responses.
Why it's wrong here
Streaming changes how generated tokens are delivered back to the caller, returning them incrementally rather than in one payload. It does not enlarge the context window or change input truncation behaviour. The missing recommendations come from input loss, so streaming would only deliver the same incomplete summary faster.
Go deeper
Related to this question
About these practice questions
One of 862 original AIF-C01 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Amazon Web Services exam blueprint
This AIF-C01 practice question is part of Courseiva's free Amazon Web Services certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AIF-C01 exam.