Exams / AIF-C01 / Agentic AI / Question 4
AIF-C01 practice question: Agentic AI (4 of 4)
Fundamentals of Generative AI A free question from our original AIF-C01 practice exam. Try it, then open the answer to see why each option is right or wrong.
A logistics company is moving its AI agents to production on Amazon Bedrock AgentCore. Match each requirement to the AgentCore service that meets it.
Match each item to one answer. An answer can be used more than once, and some may not be used.
Items
- Host agents in a secure, serverless runtime that scales with demand
- Keep context about each user so agents can recall it in later sessions
- Turn existing APIs and Lambda functions into MCP-compatible tools
- Let agents access third-party services on behalf of users with managed credentials
- Trace, debug and monitor agent behaviour in production
Answers
- AA. AgentCore Browser
- BB. AgentCore Gateway
- CC. AgentCore Identity
- DD. AgentCore Memory
- EE. AgentCore Observability
- FF. AgentCore Runtime
Show the answer and explanation
Correct matches
- Host agents in a secure, serverless runtime that scales with demand: F. AgentCore Runtime
- Keep context about each user so agents can recall it in later sessions: D. AgentCore Memory
- Turn existing APIs and Lambda functions into MCP-compatible tools: B. AgentCore Gateway
- Let agents access third-party services on behalf of users with managed credentials: C. AgentCore Identity
- Trace, debug and monitor agent behaviour in production: E. AgentCore Observability
About each answer
- A. Distractor: a cloud browser that lets agents navigate websites and fill in forms. None of the requirements asks for web browsing.
- B. Converts APIs, Lambda functions and existing services into MCP-compatible tools. It matches the third requirement.
- C. Manages agent identity, authentication and credentials so agents can act for users. It matches the fourth requirement.
- D. Gives agents short-term and long-term memory. It matches the second requirement.
- E. Gives a unified view to trace, debug and monitor agents. It matches the fifth requirement.
- F. A secure, serverless runtime for deploying and scaling agents and tools. It matches the first requirement.
Explanation
Amazon Bedrock AgentCore is a set of services for running agents in production, and it works with any framework and model. Runtime hosts agents, Memory stores context, Gateway exposes tools through MCP, Identity handles authentication and credentials, Observability traces behaviour, and Browser and Code Interpreter give agents built-in tools.
Study
Keep practising
Answer questions with a score at the end, or practise just this topic with the explanation after each one. No sign-up needed.