hardMultiple Select
AIF-C01 Practice Question: Building a generative AI application to answer…
A company is building a generative AI application to answer questions from a large set of technical manuals. Which TWO services or features can be used together in a RAG architecture on AWS? (Choose TWO.)
⚠ Common exam trap
AIF-C01 often tests whether candidates can distinguish RAG retrieval components (Knowledge Bases + vector store) from adjacent services like Guardrails or SageMaker that sound relevant but serve different purposes.
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
✓
Amazon OpenSearch Serverless
Amazon OpenSearch Serverless (B) is correct because it provides a vector search collection that can store and retrieve document embeddings, serving as the retrieval layer in a RAG architecture for querying the technical manuals. Amazon Bedrock Knowledge Bases (D) is correct because it is a fully managed RAG feature that ingests source documents, generates embeddings, stores them in a vector store (such as OpenSearch Serverless), and orchestrates retrieval-augmented generation with foundation models. Together, these two services directly implement the retrieval and generation components of a RAG pipeline on AWS. Amazon SageMaker (A) is a general ML platform for building, training, and deploying models, not a purpose-built RAG retrieval or knowledge base service. AWS Lambda (C) is a serverless compute service that could glue components together but is not itself a RAG retrieval or knowledge base feature. Amazon Bedrock Guardrails (E) applies safety and content filtering policies to model inputs and outputs, which is unrelated to the retrieval and knowledge grounding required by RAG.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Amazon SageMaker
Why it's wrong here
SageMaker builds, trains and hosts custom models, but RAG needs a managed foundation model plus a vector store for retrieval, neither of which SageMaker supplies by itself. It is tempting because it is AWS's flagship machine learning platform, and would be correct when training or deploying a bespoke model rather than augmenting an existing one.
- ✓
Amazon OpenSearch Serverless
Why this is correct
Amazon OpenSearch Serverless provides the vector store that RAG requires: it indexes embedded manual chunks and returns the nearest neighbours to a query embedding, so retrieved passages can be passed to the foundation model as context.
- ✗
AWS Lambda
Why it's wrong here
Lambda runs event-driven compute code but provides no vector storage or similarity search, so it cannot retrieve the manual passages that ground the model's answers. It is tempting because it is a general-purpose serverless building block, and would be correct for orchestration or preprocessing logic around the retrieval pipeline.
- ✓
Amazon Bedrock Knowledge Bases
Why this is correct
Amazon Bedrock Knowledge Bases handles the full managed RAG pipeline — ingesting the manuals, chunking and embedding them into a vector store, then retrieving relevant passages and grounding the model's response — satisfying the retrieval requirement without custom orchestration.
- ✗
Amazon Bedrock Guardrails
Why it's wrong here
Guardrails filters and moderates model inputs and outputs for safety and policy compliance; it neither retrieves documents nor generates grounded answers, so it contributes nothing to the retrieval-augmented generation flow. It is tempting because it is a Bedrock feature, and would be correct when the requirement is content filtering rather than retrieval.
Quick reference
Cloud Service Model Comparison
| Model | You Manage | Provider Manages | Examples |
|---|---|---|---|
| IaaS | OS, runtime, apps, data | Hardware, hypervisor, networking | EC2, Azure VMs, GCP Compute Engine |
| PaaS | Apps and data | OS, runtime, middleware, hardware | Elastic Beanstalk, Azure App Service |
| SaaS | Data and settings only | Everything else | Microsoft 365, Salesforce, Workday |
| FaaS / Serverless | Function code only | Infra, scaling, runtime | Lambda, Azure Functions, Cloud Run |
| CaaS | Containers and apps | Kubernetes, OS, hardware | EKS, AKS, GKE |
Go deeper
Related to this question
About these practice questions
This AIF-C01 question is part of Courseiva's 862-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam 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.