Agent Orchestration & Agent Memory — AI-103 Practice Question
A representative Microsoft Azure AI Apps and Agents Developer Associate (AI-103) exam question on Agent Orchestration & Agent Memory. Work through it below, then read why each option is right or wrong.
This question is part of the free Microsoft Azure AI Apps and Agents Developer Associate practice test.
Short answer
The correct answer is B. Implement tool definitions in the Foundry agent configuration, connect them to the CRM API and Azure Functions, and use the agent's built-in memory mechanism to persist user preferences across sessions.
Microsoft Foundry agents are designed to manage tool orchestration and memory natively. Agents can be configured with tool definitions that abstract away API details, and the agent's memory system persists context across sessions. This approach is scalable, maintainable, and aligns with Foundry's agent-centric architecture. Sequential Azure Function calls with manual database queries are possible but bypass Foundry's built-in orchestration and memory capabilities. Static configuration files do not support dynamic user preferences. Logic Apps and Key Vault are valid tools but introduce unnecessary indirection when Foundry provides native agent capabilities. The correct approach leverages Foundry's agent framework directly.
The Question
You are building an autonomous agent in Microsoft Foundry that must perform multi-step tasks: retrieve customer data from a CRM API, generate a personalized offer, and send a notification via Azure Functions. The agent must remember user preferences across multiple interactions. Which architectural pattern should you implement to enable the agent to access these tools and maintain memory?
Why B is correct
Microsoft Foundry agents are designed to manage tool orchestration and memory natively. Agents can be configured with tool definitions that abstract away API details, and the agent's memory system persists context across sessions. This approach is scalable, maintainable, and aligns with Foundry's agent-centric architecture. Sequential Azure Function calls with manual database queries are possible but bypass Foundry's built-in orchestration and memory capabilities. Static configuration files do not support dynamic user preferences. Logic Apps and Key Vault are valid tools but introduce unnecessary indirection when Foundry provides native agent capabilities. The correct approach leverages Foundry's agent framework directly.
Why the other options are wrong
Option A does not satisfy the requirement in the scenario. Review the explanation above: the correct choice (B) is the only one that fully meets every constraint stated in the question.
Option C does not satisfy the requirement in the scenario. Review the explanation above: the correct choice (B) is the only one that fully meets every constraint stated in the question.
Option D does not satisfy the requirement in the scenario. Review the explanation above: the correct choice (B) is the only one that fully meets every constraint stated in the question.
Key idea: Agent Orchestration & Agent Memory
Microsoft Foundry agents are designed to manage tool orchestration and memory natively. Agents can be configured with tool definitions that abstract away API details, and the agent's memory system persists context across sessions. This approach is scalable, maintainable, and aligns with Foundry's agent-centric architecture. Sequential Azure Function calls with manual database queries are possible but bypass Foundry's built-in orchestration and memory capabilities. Static configuration files do not support dynamic user preferences. Logic Apps and Key Vault are valid tools but introduce unnecessary indirection when Foundry provides native agent capabilities. The correct approach leverages Foundry's agent framework directly. On the AI-103 exam, questions in the "Implement generative AI and agentic solutions" domain test whether you can map a scenario's constraints to the right choice. Read the requirement carefully, eliminate options that violate any single constraint, and pick the one that satisfies all of them with the least operational overhead.
Ready to see how you'd score?
Take the free practice quiz and find out which Microsoft Azure AI Apps and Agents Developer Associate domains you need to focus on. No signup required.
Practice 5 similar questions
Same cert, same or adjacent domain. Use these after reviewing the explanation.
Related Microsoft Azure AI Apps and Agents Developer Associate Practice Questions
Official sources used
Verify program and exam details at the source before scheduling.