Study guide
3.1 Agentic Solutions: Foundry Agent Service and the Microsoft Agent Framework
Azure AI Engineer Associate AI-102
Track your progress as you read
Finished sections get a check mark.
1 Introduction
About the Azure AI Engineer Associate (AI-102) Exam Study Strategies and Exam Tips for the AI-102
2 Domain 1: Plan and Manage an Azure AI Solution (20-25%)
1.1 Azure AI Services Overview and Selection 1.2 Resource Provisioning and Configuration 1.3 Security and Access Management 1.4 Responsible AI Principles and Implementation 1.5 Azure AI Solution Architecture Patterns
3 Content Safety and Moderation (within Plan and Manage, Domain 1)
2.1 Azure AI Content Safety Overview 2.2 Prompt Shields and Adversarial Attack Detection 2.3 Text and Image Moderation Implementation 2.4 Content Filtering in Azure OpenAI Service
4 Domain 4: Implement Computer Vision Solutions (10-15%)
3.1 Azure AI Vision — Image Analysis 4.0 3.2 Azure AI Face Service 3.3 Azure AI Custom Vision 3.4 Optical Character Recognition (OCR) 3.5 Video Analysis and the Retired Spatial Analysis
5 Domain 5: Implement Natural Language Processing Solutions (15-20%)
4.1 Azure AI Language — Text Analytics Features 4.2 Conversational Language Understanding (CLU) 4.3 Custom Text Classification and Custom NER 4.4 Azure AI Speech Services 4.5 Azure AI Translator Service 4.6 Question Answering and Conversational AI
6 Domain 6: Implement Knowledge Mining and Information Extraction Solutions (15-20%)
5.1 Azure AI Search — Fundamentals and Architecture 5.2 AI Enrichment with Skillsets 5.3 Azure AI Document Intelligence
7 Domain 2: Implement Generative AI Solutions (15-20%)
6.1 Azure OpenAI Service — Models and Deployment 6.2 Chat Completions API and Prompt Engineering 6.3 Embeddings and Vector Search for RAG 6.4 Fine-Tuning and Model Customization 6.5 Image Generation (gpt-image; DALL-E 3 Retired) 6.6 RAG After On Your Data, and AI Agents
8 Domain 3: Implement an Agentic Solution (5-10%)
3.1 Agentic Solutions: Foundry Agent Service and the Microsoft Agent Framework
9 Exam Review: Cross-Domain Topics and Advanced Practice
7.1 Service Comparison and Selection Guide 7.2 SDK and REST API Patterns 7.3 Responsible AI Across All Domains 7.4 End-to-End Solution Architectures 7.5 Exam Day Quick Reference
3.1 Agentic Solutions: Foundry Agent Service and the Microsoft Agent Framework
Key Takeaways Explain This Topic AI
Domain 3 (Implement an agentic solution) is an explicit 5-10% AI-102 domain added in the April 30, 2025 outline; it kept its name and 5-10% weight in the final December 23, 2025 outline, which renamed its agent tooling. Older notes omit it.
Foundry Agent Service is the MANAGED, hosted single-agent runtime; the Microsoft Agent Framework is the open-source SDK (AutoGen + Semantic Kernel converged) for code-first multi-agent orchestration.
Every agent = model + instructions + tools (function, code_interpreter, file_search, bing_grounding, OpenAPI) + stateful conversations (threads in the classic API).
Multi-agent orchestration patterns to know: sequential, concurrent, group chat, handoff, and Magentic (dynamic manager-led planning).
A function_call output item (requires_action in the classic thread/run API, retiring March 31, 2027) means the agent is waiting for your code to run a tool and return its output - it is not an error or completion; secure every tool with managed identity and least privilege.
Last updated: October 2026
Quick Answer: Domain 3 ( Implement an agentic solution , 5-10%) tests building autonomous, tool-using agents. The two pillars are the Microsoft Foundry Agent Service (the managed, hosted runtime for single agents) and the Microsoft Agent Framework (the open-source SDK — the convergence of AutoGen and Semantic Kernel — for code-first single- and multi-agent orchestration). Know the agent anatomy (model + instructions + tools + conversations), the function-call tool loop ( requires_action in the classic API), and the multi-agent orchestration patterns (sequential, concurrent, group chat, handoff, and Magentic).
Where This Sits on AI-102
Agentic solutions are a small but explicit domain — 5-10% , the lowest-weighted of the six skill areas — on a 100-minute exam, passing at 700/1000 for about US$165 . It became a named domain in the April 30, 2025 outline and kept its name and 5-10% weight in the final December 23, 2025 revision, which renamed its agent tooling (Azure AI Agent Service, Semantic Kernel and AutoGen became Microsoft Foundry Agent Service and Microsoft Agent Framework), so older study notes omit it. Microsoft retired the AI-102 exam on June 30, 2026; AI-103 replaced it.
Agent Anatomy
An agent is an LLM wrapped with instructions, tools, and persistent memory so it can plan and act over multiple steps rather than answer once. Every agent is assembled from four parts:
- Part Role Example
- Model The reasoning engine (a deployment) gpt-4o , o3-mini
- Instructions System persona and rules "You are a refunds assistant; never exceed $500."
Tools Capabilities the agent may invoke function , code_interpreter , file_search , bing_grounding , OpenAPI tools
Conversations (threads in the classic API) Stateful conversation memory Recalls earlier user constraints across responses
Built-in tools matter on the exam: code_interpreter runs sandboxed Python (data analysis, charts); file_search is managed RAG over uploaded files with automatic chunking and citations; function tools call your own APIs; bing_grounding and OpenAPI tools reach external web and REST services. Prefer a built-in tool over hand-rolled code when one fits the requirement.
Foundry Agent Service vs. Microsoft Agent Framework
This comparison is the highest-value distinction in Domain 3:
- Dimension Foundry Agent Service Microsoft Agent Framework
- What it is Managed, hosted agent runtime in Microsoft Foundry Open-source SDK + runtime (Python and .NET)
Hosting Microsoft hosts agent versions, conversations, and state You host and deploy (local, container, anywhere)
Best for Single enterprise agents with governance, identity, and tracing built in Code-first, complex multi-agent orchestration and custom workflows
Lineage Successor to the retired Assistants API Converges AutoGen (multi-agent research) + Semantic Kernel (enterprise plugins/memory)
Orchestration Connected/sub-agents Sequential, concurrent, group-chat, handoff, Magentic patterns
On the Exam: "Managed, governed, single agent fast" → Foundry Agent Service . "Code-first, several specialized agents collaborating, custom control flow" → Microsoft Agent Framework . If a scenario names AutoGen or Semantic Kernel, the modern answer is to migrate to the Microsoft Agent Framework , which unifies both — do not pick the legacy SDKs as a new build target.
Multi-Agent Orchestration Patterns
A single agent struggles with broad, multi-skill tasks; multi-agent systems decompose work across specialists. Memorize the named patterns:
- Pattern Flow When to use
- Sequential Agent A's output feeds Agent B, then C Pipelines: research → draft → edit
- Concurrent Several agents run in parallel on the same input Gather independent perspectives, then merge
- Group chat Agents converse in a shared thread, a manager picks who speaks Brainstorming, debate, review boards
- Handoff One agent transfers control to a more specialized agent Triage routing (billing → technical)
- Magentic A manager agent plans, delegates, and re-plans dynamically Open-ended tasks with no fixed steps
- The Tool-Call Loop
In Foundry Agent Service the heartbeat is: create an agent version → create a conversation → create a response. When the agent decides to call one of your functions, the response returns a function_call item and waits : your code executes the tool and sends a function_call_output item with the same call_id , looping as many times as the task needs. The classic threads-and-runs API (deprecated, retiring March 31, 2027) showed this pause as a run in requires_action until you called submit_tool_outputs . while any(item.type == "function_call" for item in response.output):
- outputs = [{"type": "function_call_output", "call_id": item.call_id,
- "output": json.dumps(run_tool(item.name, json.loads(item.arguments)))}
- for item in response.output if item.type == "function_call"]
- response = openai.responses.create(conversation=conversation.id, input=outputs)
Common Trap: In the classic API, requires_action is not an error and not completion — it means "the agent is waiting for your tool output." A question showing a run stuck at requires_action is testing whether you know to submit tool outputs, not to retry or fail.
Securing and Testing Agents
Autonomy multiplies risk: every tool an agent can call is an attack surface. Authenticate agents and their downstream tools with managed identity (never embedded keys), scope each tool to least privilege, and wrap inputs/outputs with Content Safety (prompt shields for injection arriving through tool data, harm filters on responses). Use Foundry's tracing and evaluation to test runs: inspect each step's tool calls and intermediate reasoning, score task completion, and watch token cost — agents loop, so an unbounded tool loop or a runaway multi-agent group chat can be far more expensive than a single chat completion.
Always choose the simplest design that meets the requirement: a single function call beats an agent, and one agent beats a multi-agent system, unless the task genuinely needs dynamic multi-step tool use.