Exams / AIF-C01 / Agentic AI / Question 1
AIF-C01 practice question: Agentic AI (1 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 software company has built several AI agents. Each one needs access to the same ticketing system, code repository and internal wiki, and the team is tired of writing a custom integration for every agent and tool combination. Which open standard addresses this?
Choose one answer.
- AA. Model Context Protocol (MCP)
- BB. Retrieval Augmented Generation (RAG)
- CC. Reinforcement learning from human feedback (RLHF)
- DD. Open Neural Network Exchange (ONNX)
Show the answer and explanation
Answer: A
- A. Right: Correct. MCP is an open protocol that standardises how AI applications connect to external tools, data and prompts.
- B. Wrong: RAG retrieves documents to ground answers. It is a technique, not a standard for connecting agents to tools.
- C. Wrong: RLHF is a training method that uses human preferences. It does not connect agents to systems.
- D. Wrong: ONNX is a format for exchanging trained model files between frameworks. It does not connect agents to tools at run time.
Explanation
The Model Context Protocol is an open protocol for connecting LLM applications to external tools and data. An MCP server exposes tools (actions), resources (data) and prompts (templates) once, and any MCP-compatible agent can then use them. This replaces many custom, one-off integrations with one standard interface.
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.