AIF-C01 Applications of Foundation Models Practice Question
A logistics company is building an internal assistant on Amazon Bedrock that must answer operational questions using its private runbooks and must return citations so staff can verify answers. The team also needs to control cost by limiting how much source text is sent with each request. Which TWO capabilities should they combine to meet these requirements? (Choose two.)
⚠ Common exam trap
The trap here is assuming that sending more source text or reserving capacity improves answer quality, when targeted retrieval is what controls both accuracy and cost.
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
✓
Knowledge Bases for Amazon Bedrock to ingest the runbooks and retrieve relevant passages.
Retrieval is the mechanism that both grounds answers in private runbooks and bounds prompt size, because only the most relevant chunks are injected. Knowledge Bases for Amazon Bedrock performs that ingestion and retrieval, and it can return citations linking generated text to source chunks, enabling verification. Capacity reservation, output-length increases, and profanity filtering do not supply grounding, traceability, or cost control.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Knowledge Bases for Amazon Bedrock to ingest the runbooks and retrieve relevant passages.
Why this is correct
Knowledge Bases for Amazon Bedrock ingests the runbooks from a supported data source, chunks and embeds them, and retrieves only the passages relevant to each question. That retrieval step both grounds answers in private content and keeps prompt size bounded, which directly serves the citation and cost-control requirements.
- ✗
Guardrails for Amazon Bedrock with a profanity filter enabled.
Why it's wrong here
A profanity filter blocks offensive language in prompts and responses but does not retrieve runbook content or produce citations. It addresses content safety, not grounding or prompt size. Enabling it would leave the assistant without access to the operational documents it needs to answer questions accurately.
- ✓
Citations returned from retrieved source chunks in the Knowledge Bases response.
Why this is correct
Knowledge Bases for Amazon Bedrock can return citations that map generated statements back to the specific source chunks used. This lets staff verify answers against the runbooks, satisfying the traceability requirement. The citations come from the same retrieval step that limits how much text is injected, so they pair naturally with the knowledge base.
- ✗
Provisioned Throughput to guarantee dedicated model capacity.
Why it's wrong here
Provisioned Throughput reserves model capacity for predictable latency and is billed hourly, which increases rather than controls cost for a low-volume internal assistant. It does not retrieve runbooks or generate citations, so it fails both stated requirements and adds expense unrelated to the scenario.
- ✗
A larger maxTokens value to include more of each runbook.
Why it's wrong here
Increasing maxTokens raises the ceiling on generated output tokens and consumes more budget per call. It does not select the right source passages or produce citations. Injecting more raw runbook text would work against the cost-control goal rather than supporting targeted retrieval.
Go deeper
Related to this question
About these practice questions
Courseiva writes every AIF-C01 question from scratch — 862 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. 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.