mediumMultiple Select
AIF-C01 Practice Question: Using Bedrock Agents to automate multi-step…
A company is using Bedrock Agents to automate multi-step workflows that interact with external APIs and databases. They need to ensure the agent can perform actions like querying a database and calling an API. Which TWO components must be defined to enable these capabilities? (Choose TWO)
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
✓
Lambda functions that implement the business logic for each action
In Amazon Bedrock Agents, action groups (option C) are the required construct that defines the set of actions the agent can invoke, including the OpenAPI schema describing the external APIs and the parameters/operations for database interactions, so the agent knows what actions exist and how to call them. Lambda functions (option B) provide the actual business logic execution behind those action groups, receiving the agent's invocation and performing the concrete work such as running SQL queries against a database or calling an external API. Together, the action group defines the interface and the Lambda function implements it, which is exactly what is needed for querying a database and calling an API. Option A is incorrect because prompt flows are for orchestrating prompt sequences in Amazon Bedrock Flows, not for defining agent action capabilities. Option D is incorrect because Guardrails filter and constrain content and safety, not enable action execution. Option E is incorrect because a Knowledge Base stores and retrieves static documents via RAG for informational responses, not for performing actions against APIs or databases.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
A prompt flow to manage multiple prompts
Why it's wrong here
Prompt flows orchestrate prompt chaining in Amazon Bedrock, not agent action invocation, so they define no API schema or Lambda function the agent can call. It is tempting because prompt flows manage multi-step logic, and would be the right choice for sequencing prompts in a generative application rather than enabling tool use.
- ✓
Lambda functions that implement the business logic for each action
Why this is correct
Bedrock Agents invoke Lambda functions to execute each action's business logic, so the function performs the actual database query or API call the workflow requires. Without a Lambda backing, the action group has no executable code, so defining these functions satisfies the requirement to perform actions.
- ✓
Action groups that describe the APIs and databases
Why this is correct
Action groups define the OpenAPI schema describing each API and database operation, giving the agent the parameters and endpoints it must invoke. This schema is the interface the agent reasons over, so it satisfies the requirement to describe the APIs and databases the workflow calls.
- ✗
Bedrock Guardrails to filter inappropriate actions
Why it's wrong here
Guardrails filter and block harmful input or output content; they grant no capability to query a database or call an API. It is tempting because Guardrails are a core Bedrock safety control, and would be correct when the requirement is content moderation or PII redaction rather than action execution.
- ✗
A Bedrock Knowledge Base to store static documents
Why it's wrong here
A Knowledge Base supplies retrieval-augmented context from documents; it defines no action group, so the agent cannot invoke APIs or databases. It is tempting because Knowledge Bases are the standard Bedrock component for grounding answers in proprietary content, and would be correct if the requirement were document Q&A rather than transactional actions.
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 by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
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.