AI-103 Certification Practice Question #37

Question

You need to recommend a plan to create a customer support agent by using the Microsoft Foundry Agent Service. The agent must meet the following requirements:
Retain user preferences across multiple conversations.
Enable users to provide contextual grounding by directly uploading documents during a chat.
Which Foundry capability should you recommend for each requirement? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.

Accepted Answer

Retaining user preferences across multiple conversations is precisely Foundry's long-term Memory feature: MS Learn describes memory stores as persistent storage that retain user preferences (user profile memory) across sessions. Conversation history and orchestration-managed session context only carry context within or across turns of a session and don't persist distilled preferences long-term, so they're eliminated. For letting users provide contextual grounding by uploading documents during a chat, MS Learn's memory guidance explicitly points to the file search tool "to search user-provided documents during an interaction"; the Azure AI Search tool grounds on a pre-built index (not ad-hoc user uploads) and the code interpreter runs Python rather than grounding on documents. Confidence is high-but-not-maximal because the file has no Suggested Answer or community vote to corroborate; both selections are grounded directly in MS Learn.

More AI-103 practice questions