‹ All AI-103 questions

AI-103 Practice Question 17: Zero Retention Conversation State

Microsoft Azure AI Apps and Agents Developer Associate (AI-103) · Test 2 · question 7 of 10

Implement generative AI and agentic solutionsmedium

A bank is building a multi-turn assistant on Foundry Agent Service. Its regulator requires that no conversation content be persisted by the service: every message must live only in the bank's own encrypted store. The assistant still has to answer follow-up questions like "and what about the joint account?" with the earlier turns in context.

How should the application handle conversation state?

Select one answer
Show answer and explanation

Answer:

  • D. Set store to false and pass the previous turns' output items back in the input array of each request

By default the service stores response history server-side. Setting `store` to `false` stops that persistence, and the documentation is direct about the consequence: "You must carry forward the conversation context yourself by passing previous output items as input to the next request." Microsoft names this as the pattern for teams that want to minimize stored data or work in a zero-data-retention environment, which is precisely the regulator's requirement.

- A is wrong because conversations are *durable objects with unique identifiers* that persist items (messages, tool calls, tool outputs) server-side and can be reused across sessions. That is server-side persistence, which is what the regulator forbids. - B is wrong for the same reason: previous_response_id works only because the service retained the earlier response. Accepting the default keeps the history the bank may not keep. - C is self-defeating. previous_response_id points at a *stored* response; with store set to false there is nothing persisted for the ID to reference, so the context is simply lost.

Reference: Build with runtime components in Foundry Agent Service

Practice Test 2 ›

Study guides for AI-103

AI engineer roadmap 2026: skills, certs and the orderAI engineer roadmap for 2026: skills to learn in order, AI engineer vs ML engineer, which certifications fit each stage, and what to skip.
AI-200 exam guide: Azure AI Cloud Developer AssociateAI-200 replaced AZ-204: what the Azure AI Cloud Developer exam tests, how it differs from AI-103, price in USD and INR, format and how to prepare.
How AI Is Changing Software Jobs: Where to PrepareHow AI is changing software jobs: what history shows, the evidence on junior developers, what Klarna learned, new AI roles and five domains to prepare for.
AI-901 exam guide: Azure AI Fundamentals after AI-900AI-901 replaced AI-900: learn what changed, how much Python and Microsoft Foundry you need, exam costs in India, and how to prepare.
Best AI certifications 2026: AWS, Google, Microsoft, ClaudeThe best AI certifications in 2026 from AWS, Google, Microsoft, Claude and Databricks, by level, with price, status and which one to take first.
Microsoft AI certification path 2026: which exam firstMicrosoft AI certification path for 2026 - AI-901, AB-730, AI-103, AI-200, AI-300, AB-100, AI-500 and GH-300 by role, and which exam to take first.
AI-103 Certification Guide: What Changed From AI-102The AI-103 certification replaced AI-102 in 2026. Exam format, cost, the five skill domains, what changed and how to prepare, with free practice questions.
What Is RAG? How Retrieval-Augmented Generation WorksWhat RAG is and how it works: chunking, embeddings, vector search, hybrid search, reranking, GraphRAG and agentic RAG on AWS, Google and Azure.
Prompt engineering vs RAG vs fine-tuningWhen to use prompt engineering, retrieval-augmented generation, fine-tuning or continued pre-training, compared on cost, freshness, hallucination and privacy.