Get Your CertAIF-C01PlayCompete
‹ All AIF-C01 questions

AIF-C01 Practice Question 96: Knowledge Base Query Decomposition

AWS Certified AI Practitioner (AIF-C01) · Test 10 · question 6 of 10

Applications of Foundation Modelshard

A finance team uses an Amazon Bedrock knowledge base over annual reports. Users ask multi-part questions such as "Which grew revenue faster in 2023, the EMEA division or the APAC division?" Answers are poor because a single retrieval returns a mix of chunks about both divisions and neither figure is complete. The team wants to improve answers without re-chunking the documents or changing the model. What should they do?

Select one answer
Show answer and explanation

Answer:

  • D. Enable query decomposition so that the question is split into sub-queries.

Query decomposition breaks a complex query into smaller, more manageable sub-queries, and AWS notes it helps *"especially when the initial query is multifaceted or too broad."* For this question, the knowledge base can run one sub-query for EMEA revenue growth and another for APAC, retrieve the relevant chunks for each, and then generate a final comparison (option D). It is enabled in the orchestration configuration (QUERY_DECOMPOSITION), so no re-chunking or model change is needed.

- A is wrong because semantic-only search still runs one retrieval for the whole question, so the mixed-chunk problem remains. - B is wrong because keeping a single chunk makes it impossible to have evidence for both divisions in the same answer. - C is wrong because a contextual grounding check filters answers not supported by the retrieved text. It does not improve what is retrieved, so it would only block more answers.

Reference: Configure and customize queries and response generation

Practice Test 10 ›

Study guides for AIF-C01

AI engineer roadmap 2026: skills, certs and the orderAI engineer roadmap for 2026: skills to learn in order, AI engineer vs ML engineer, which certifications fit each stage, and what to skip.
How AI Is Changing Software Jobs: Where to PrepareHow AI is changing software jobs: what history shows, the evidence on junior developers, what Klarna learned, new AI roles and five domains to prepare for.
How AWS Certification Exams Work: Scoring and RenewalHow AWS certification exams work: levels, booking, question types, unscored questions, scaled scores, pass marks, validity and how recertification works.
What Is Amazon Bedrock? Models, Pricing and GuardrailsWhat is Amazon Bedrock? How a request reaches a model, what happens to your data, token pricing, Guardrails, Knowledge Bases, AgentCore and the exam traps.
Google Cloud Generative AI Leader vs AWS AI PractitionerGoogle Cloud Generative AI Leader vs AWS AI Practitioner: format, cost, topics, free preparation and which certification to take first.
AWS certification cost in 2026, and free ways to prepareWhat every AWS certification costs in 2026 in USD and INR, retake and reschedule rules, the 50% voucher, and the free official ways to prepare.
AWS Generative AI Developer Professional (AIP-C01) guideWhat the AWS Certified Generative AI Developer – Professional (AIP-C01) exam covers - format, cost, the five domains, the services, and how to prepare.
Best AI certifications 2026: AWS, Google, Microsoft, ClaudeThe best AI certifications in 2026 from AWS, Google, Microsoft, Claude and Databricks, by level, with price, status and which one to take first.
Which AWS certification should you get? 2026 roadmapWhich AWS certification to get first, by role and experience, with each exam's status in October 2026, what is changing, and prices in USD and INR.
What Is RAG? How Retrieval-Augmented Generation WorksWhat RAG is and how it works: chunking, embeddings, vector search, hybrid search, reranking, GraphRAG and agentic RAG on AWS, Google and Azure.
Prompt engineering vs RAG vs fine-tuningWhen to use prompt engineering, retrieval-augmented generation, fine-tuning or continued pre-training, compared on cost, freshness, hallucination and privacy.