🔒 Guided

Pre-launch preview. Authorised access only.

Incorrect code

Guided by A Guide to Cloud
Explore AB-900 AI-901
Guided AI-103 Domain 2
Domain 2 — Module 1 of 11 9%
9 of 27 overall

AI-103 Study Guide

Domain 1: Plan and Manage an Azure AI Solution

  • Choosing the Right AI Model Free
  • Foundry Services: Your AI Toolkit Free
  • Retrieval, Indexing & Agent Memory
  • Designing AI Infrastructure
  • Deploying Models & CI/CD
  • Quotas, Scaling & Cost
  • Monitoring & Security
  • Responsible AI: Filters, Auditing & Governance

Domain 2: Implement Generative AI and Agentic Solutions

  • Connecting Your App to Foundry Free
  • Building RAG Applications
  • Workflows & Reasoning Pipelines
  • Evaluating AI Models & Apps
  • Agent Fundamentals: Roles, Goals & Tools Free
  • Building Agents with Retrieval & Memory
  • Agent Tools & Knowledge Integration
  • Multi-Agent Orchestration & Safeguards
  • Agent Monitoring & Error Analysis
  • Prompt Engineering & Model Tuning
  • Observability & Production Operations

Domain 3: Implement Computer Vision Solutions

  • Image & Video Generation
  • Multimodal Visual Understanding
  • Responsible AI for Visual Content

Domain 4: Implement Text Analysis Solutions

  • Text Analysis with Language Models
  • Speech, Translation & Voice Agents

Domain 5: Implement Information Extraction Solutions

  • Ingestion, Indexing & Grounding Pipelines
  • Extracting Content with Content Understanding
  • Exam Prep: Putting It All Together

AI-103 Study Guide

Domain 1: Plan and Manage an Azure AI Solution

  • Choosing the Right AI Model Free
  • Foundry Services: Your AI Toolkit Free
  • Retrieval, Indexing & Agent Memory
  • Designing AI Infrastructure
  • Deploying Models & CI/CD
  • Quotas, Scaling & Cost
  • Monitoring & Security
  • Responsible AI: Filters, Auditing & Governance

Domain 2: Implement Generative AI and Agentic Solutions

  • Connecting Your App to Foundry Free
  • Building RAG Applications
  • Workflows & Reasoning Pipelines
  • Evaluating AI Models & Apps
  • Agent Fundamentals: Roles, Goals & Tools Free
  • Building Agents with Retrieval & Memory
  • Agent Tools & Knowledge Integration
  • Multi-Agent Orchestration & Safeguards
  • Agent Monitoring & Error Analysis
  • Prompt Engineering & Model Tuning
  • Observability & Production Operations

Domain 3: Implement Computer Vision Solutions

  • Image & Video Generation
  • Multimodal Visual Understanding
  • Responsible AI for Visual Content

Domain 4: Implement Text Analysis Solutions

  • Text Analysis with Language Models
  • Speech, Translation & Voice Agents

Domain 5: Implement Information Extraction Solutions

  • Ingestion, Indexing & Grounding Pipelines
  • Extracting Content with Content Understanding
  • Exam Prep: Putting It All Together
Domain 2: Implement Generative AI and Agentic Solutions Free ⏱ ~12 min read

Connecting Your App to Foundry

Every AI-powered application starts with a connection to Microsoft Foundry. Learn how to configure your app, deploy models, and use the Foundry SDKs and connectors to integrate generative AI into your code.

Your first connection to Foundry

☕ Simple explanation

Connecting your app to Foundry is like plugging in a power cable — until you do it, nothing works.

You need three things: (1) a Foundry Project (your workspace), (2) a deployed model (what you’re calling), and (3) the right SDK in your code (how you call it). Once connected, your Python app can send prompts and get AI-powered responses in a few lines of code.

Connecting an application to Microsoft Foundry involves:

  • Authentication — managed identity (recommended) or API key
  • Project connection — endpoint URL and project name
  • Model deployment reference — the deployment name you created
  • SDK integration — azure-ai-projects and/or OpenAI Python SDK

The Foundry SDKs support Python, C#, TypeScript, and Java. The exam focuses on Python patterns using azure-ai-projects (the unified Foundry SDK) and the OpenAI-compatible API.

The connection stack

New here? Throughout this course, you’ll follow four teams: 🏥 NeuralMed (health-tech startup), 🏦 Atlas Financial (enterprise bank), 🚀 MediaForge (content operations platform), and 👨‍💻 Kai (AI engineer at a logistics company). They’re introduced in Module 1.

LayerWhat You ConfigureExample
AuthenticationHow your app proves its identityManaged identity or DefaultAzureCredential
EndpointYour Foundry project’s URLhttps://your-project.services.ai.azure.com
Deployment nameWhich model deployment to call”gpt4o-prod”
SDKClient library in your codeazure-ai-projects, openai

Two SDK options

Foundry SDK vs OpenAI SDK
Featureazure-ai-projects SDKOpenAI Python SDK
What it isMicrosoft's unified Foundry SDKOpenAI's official Python library (Azure-compatible)
Best forFull Foundry integration (agents, eval, tools, search)Simple chat/completion — OpenAI-compatible endpoints
Agent supportYes — full Agent Service management, Foundry IQ, evaluationSupports Responses API and function calling, but no Foundry-specific features (evaluation, Foundry IQ, Agent Service management)
EvaluationBuilt-in evaluator accessNot included
Installpip install azure-ai-projectspip install openai
💡 Exam tip: Which SDK to recommend

The exam may ask which SDK to use. Decision rule:

  • Building agents, using evaluation, or integrating Foundry Tools? → azure-ai-projects
  • Simple chat completion from a deployed model? → Either works, but OpenAI SDK is simpler
  • Migrating from OpenAI to Azure? → OpenAI SDK with Azure endpoint (minimal code changes)

Connecting with Python — the pattern

The typical connection pattern uses DefaultAzureCredential for keyless auth:

StepWhat Happens
1. Import SDKImport the Foundry client and credential classes
2. Create credentialDefaultAzureCredential() — tries managed identity first, then Azure CLI, then other methods
3. Create clientPass endpoint URL and credential to the SDK client
4. Call the modelSend messages using the deployment name
5. Process responseRead the model’s response from the returned object
ℹ️ Real-world example: Kai's first Foundry connection

Kai connects the logistics platform to Foundry:

  1. Creates a Foundry Project in East US 2 via the portal
  2. Deploys GPT-4o with deployment name “route-assistant”
  3. Enables managed identity on the Azure Container App hosting the code
  4. Grants “Azure AI User” role to the Container App’s identity
  5. Writes Python code using azure-ai-projects SDK with DefaultAzureCredential
  6. Tests locally using Azure CLI credentials (same DefaultAzureCredential falls back to CLI)

The same code works locally (uses CLI auth) and in production (uses managed identity) — no code changes needed.

Model consumption patterns

Once connected, you consume models in different patterns:

PatternUse CaseHow It Works
Chat completionConversational AI, Q&ASend message history, get response
Single completionOne-shot generation (summaries, translations)Send one prompt, get one response
StreamingReal-time chat UXReceive response token-by-token as generated
BatchBulk processing (10,000 emails)Submit batch job, retrieve results later
Function callingAgent toolsModel requests function execution, you return results

Key terms

Question

What is DefaultAzureCredential?

Click or press Enter to reveal answer

Answer

An Azure Identity SDK class that automatically tries multiple authentication methods in order: managed identity, Azure CLI, environment variables, and more. Write once, works everywhere — local dev and production.

Click to flip back

Question

What is the azure-ai-projects SDK?

Click or press Enter to reveal answer

Answer

Microsoft's unified Python SDK for Foundry. It provides access to model deployments, agents, evaluation, tools, and search integration — everything you need to build AI apps on Foundry.

Click to flip back

Question

What is streaming in model consumption?

Click or press Enter to reveal answer

Answer

Receiving the model's response token-by-token as it's generated, rather than waiting for the complete response. Used for real-time chat UX where users see text appearing progressively.

Click to flip back

Question

What is function calling?

Click or press Enter to reveal answer

Answer

A model capability where the model identifies that it needs to call an external function, generates the function arguments, and your code executes the function and returns the result. The foundation of agent tool use.

Click to flip back

Knowledge check

Knowledge Check

Kai's logistics app runs on Azure Container Apps and needs to call a GPT-4o deployment in Foundry. The security team requires no API keys in code. How should Kai authenticate?

Knowledge Check

MediaForge is building a content generation platform that needs agents with tools, evaluation tracking, and Foundry IQ integration. Which SDK should they use?

🎬 Video coming soon

← Previous

Responsible AI: Filters, Auditing & Governance

Next →

Building RAG Applications

Guided

I learn, I simplify, I share.

A Guide to Cloud YouTube Feedback

© 2026 Sutheesh. All rights reserved.

Guided is an independent study resource and is not affiliated with, endorsed by, or officially connected to Microsoft. Microsoft, Azure, and related trademarks are property of Microsoft Corporation. Always verify information against Microsoft Learn.