AI-103 Study Guide | Developing AI Apps and Agents on Azure

AI-103 Preparation Details

Preparing for the AI-103 Developing AI Apps and Agents on Azure certification exam? Start here with a complete, objective-wise AI-103 study guide designed to help you pass faster.

This guide brings together official Microsoft documentation, key concepts, and curated resources for every AI-103 exam objective, making it ideal for both beginners and last-minute revision.

Looking for the best AI-103 preparation resources in one place? This page covers everything you need to get exam-ready with confidence.

If this helped you, share it with others preparing for the AI-103 certification exam.

Exam Voucher for AI-103 with 1 Retake

Get 40% OFF with the combo

AI-103 AI Leader Materials

Udemy CourseAzure AI App & Agent Developer Associate Exam Prep
Udemy Practice TestAzure AI App & Agent Developer Practice Exams

Plan and manage an Azure AI solution (25–30%)

Choose the appropriate Foundry services for generative AI and agents

Choose an appropriate model for each task, including LLMs, small language models, multimodal models, and Foundry Tools

Microsoft Foundry Models overview

Foundry Models sold directly by Azure

Foundry Models from partners and community

Choose the appropriate Foundry services for generative tasks, grounding, vector search, agent workflows, or multimodal processing

What is Microsoft Foundry?

What is Microsoft Foundry Agent Service?

Vector Search Overview – Azure AI Search

Choose an appropriate method for retrieval and indexing

Retrieval augmented generation (RAG) and indexes in Microsoft Foundry

RAG and generative AI – Azure AI Search

Agentic Retrieval Overview – Azure AI Search

Choose appropriate memory, tool, and knowledge integration services for agent solutions

Agent tools overview for Microsoft Foundry Agent Service

What is Memory? – Microsoft Foundry

Connect Agents to Foundry IQ Knowledge Bases

Set up AI solutions in Foundry

Design Azure infrastructure for AI apps and agent-based solutions

Microsoft Foundry architecture

Baseline Microsoft Foundry Chat Reference Architecture

High availability and resiliency for Microsoft Foundry projects and Agent Services

Choose appropriate deployment options

Deployment overview for Azure AI Foundry Models

Understanding deployment types in Microsoft Foundry Models

Configure model and agent deployments

Deploy Microsoft Foundry Models in the Foundry portal

What is Microsoft Foundry Agent Service?

Integrate Foundry projects with CI/CD pipelines

Baseline Microsoft Foundry Chat Reference Architecture

High availability and resiliency for Microsoft Foundry projects and Agent Services

Manage, monitor, and secure AI systems

Manage quotas, scaling, rate limits, and cost footprints for model and agent workloads

Manage and increase quotas for resources – Microsoft Foundry

Microsoft Foundry Models quotas and limits

Quotas and limits for Microsoft Foundry Agent Service

Monitor model performance, drift, safety events, and grounding quality

Observability in Generative AI – Microsoft Foundry

Monitor Model Deployments in Microsoft Foundry Models

Monitor agents with the Agent Monitoring Dashboard

Monitor data ingestion quality, search index health, and relevance performance

RAG and generative AI – Azure AI Search

What is Microsoft Foundry Control Plane?

Observability in Generative AI – Microsoft Foundry

Configure security, including managed identity, private networking, keyless credentials, and role policies

Role-based access control for Microsoft Foundry

Azure security baseline for Microsoft Foundry

Govern Azure platform services (PaaS) for AI

Implement responsible AI across generative AI and agentic systems

Configure safety filters, guardrails, risk detection, and content moderation

Guardrails and controls overview in Microsoft Foundry

Content filtering for Microsoft Foundry Models

How to use Risks & Safety monitoring in Microsoft Foundry

Apply responsible AI instrumentation, including evaluators, safety evaluations, and explanation tooling

Risk and Safety Evaluators for Generative AI – Microsoft Foundry

Microsoft Foundry risk and safety evaluations Transparency Note

Responsible AI in Azure Workloads – Azure Well-Architected Framework

Implement auditing through trace logging, provenance metadata, and approval workflows

Agent tracing in Microsoft Foundry

Set Up Tracing for AI Agents in Microsoft Foundry

Configure tracing for AI agent frameworks – Microsoft Foundry

Govern agent behavior with oversight modes, constraints, and tool-access controls

Transparency Note for Azure Agent Service – Microsoft Foundry

Governing Agent Identities – Microsoft Entra ID Governance

Governance and security for AI agents across the organization

Implement generative AI and agentic solutions (30–35%)

Build generative applications by using Foundry

Deploy and consume LLMs, small models, code models, and multimodal models

Microsoft Foundry Models overview

How to deploy and inference a managed compute deployment

Foundry Models sold directly by Azure

Implement retrieval-augmented generation (RAG) in an application

Retrieval augmented generation (RAG) and indexes in Microsoft Foundry

Build a custom knowledge retrieval (RAG) app with the Microsoft Foundry SDK

Build a RAG solution using Azure Content Understanding in Foundry Tools

Design workflows, tool-augmented flows, and multistep reasoning pipelines

Build a workflow in Microsoft Foundry

Prompt flow in Microsoft Foundry portal

Microsoft Agent Framework overview

Evaluate models and apps, including detecting fabrications, relevance, quality, and safety

Retrieval-Augmented Generation (RAG) Evaluators for Generative AI

Risk and Safety Evaluators for Generative AI – Microsoft Foundry

Observability in Generative AI – Microsoft Foundry

Integrate generative workflows into applications by using Foundry SDKs and connectors

Get started with Microsoft Foundry SDKs and Endpoints

Integrate Microsoft Foundry with your applications

Azure AI Foundry SDK client libraries

Configure an application to connect to a Foundry project

Create a project – Microsoft Foundry

Integrate Microsoft Foundry with your applications

Build agents by using Foundry

Define agent roles, goals, conversation-tracking approach, and tool schemas

What is Microsoft Foundry Agent Service?

Understand agent runtime components in Foundry Agent Service

Agent tools overview for Microsoft Foundry Agent Service

Build agents that integrate retrieval, function-calling, and conversation memory

Build with agents, conversations, and responses in Foundry Agent Service

What is Memory? – Microsoft Foundry

Microsoft Agent Framework multi-turn conversations

Integrate agent tools, including APIs, knowledge stores, search, content understanding, and custom functions

Agent tools overview for Microsoft Foundry Agent Service

Connect Agents to Foundry IQ Knowledge Bases

Add tools to custom agents – Microsoft Copilot Studio

Implement orchestrated multi-agent solutions

Build a workflow in Microsoft Foundry

Microsoft Agent Framework agent types

Baseline Microsoft Foundry Chat Reference Architecture

Build autonomous or semiautonomous workflows with safeguards and approval flow controls

Transparency Note for Azure Agent Service – Microsoft Foundry

How to Use Task Adherence for Your Agentic Workflows

Process to build agents across your organization with Microsoft Foundry and Copilot Studio

Integrate monitoring into deployed agents, evaluate agent behavior, and perform error analysis

Agent Evaluators for Generative AI – Microsoft Foundry

Monitor agents with the Agent Monitoring Dashboard

Agent Evaluation with the Microsoft Foundry SDK

Optimize and operationalize generative AI systems

Tune generation behavior, such as prompt engineering and adjusting model parameters

Prompt engineering techniques – Microsoft Foundry

Getting started with customizing a large language model (LLM)

Prompt flow in Microsoft Foundry portal

Implement model reflection, chain-of-thought evaluations, and self-critique loops

How to use reasoning models with Microsoft Foundry Models

Retrieval-Augmented Generation (RAG) Evaluators for Generative AI

Agent Evaluators for Generative AI – Microsoft Foundry

Set up observability by implementing tracing, token analytics, safety signals, and latency breakdowns

Observability in Generative AI – Microsoft Foundry

Set Up Tracing for AI Agents in Microsoft Foundry

Monitor Model Deployments in Microsoft Foundry Models

Orchestrate multiple models, flows, or hybrid LLM and rules engines

Build a workflow in Microsoft Foundry

Microsoft Agent Framework overview

Prompt flow in Microsoft Foundry portal

Implement computer vision solutions (10–15%)

Design and implement image- and video-generation solutions

Implement a solution that generates images from text prompts and reference media

How to Use Image Generation Models from OpenAI – Microsoft Foundry

Quickstart: Generate images with Azure OpenAI in Microsoft Foundry Models

Use the image generation tool in Foundry Agent Service

Implement a solution that generates videos from text prompts and reference media

Video generation with Sora 2 – Microsoft Foundry

Quickstart: Generate video with Sora – Azure OpenAI

Configure image-editing workflows, including inpainting, mask-based edits, and prompt-driven modifications

How to use image generation models – Azure OpenAI

How to Use Image Generation Models from OpenAI – Microsoft Foundry

Implement workflows to edit generated videos

Video generation with Sora 2 – Microsoft Foundry

Quickstart: Generate video with Sora – Azure OpenAI

Select and apply appropriate generation and editing controls provided by the platform

Microsoft Foundry Playgrounds

Generate images with AI – Training

Design and implement multimodal understanding workflows

Build a solution that analyzes visual context by using multimodal models

How to use vision-enabled chat models – Microsoft Foundry

What is Image Analysis? – Foundry Tools

Configure apps to produce concise or detailed captions for single or multiple images

Image captions – Image Analysis 4.0 – Foundry Tools

Multimodal Search Concepts and Guidance – Azure AI Search

Implement a solution that enables question-answering grounded in visual evidence

How to use vision-enabled chat models – Microsoft Foundry

Transparency Note and use cases for Image Analysis

Configure generation of alt-text and extended image descriptions aligned to accessibility guidelines

Overview: Generate alt text of images with Image Analysis

Image captions – Image Analysis 4.0 – Foundry Tools

Implement visual understanding by configuring Azure Content Understanding in Foundry Tools to extract visual characteristics

What is Azure Content Understanding in Foundry Tools?

Create an Azure AI Content Understanding single-file task in the Foundry portal

Implement video analysis workflows to process and interpret video segments

Azure Content Understanding in Foundry Tools video overview

What is Azure Content Understanding in Foundry Tools?

Configure single-task and pro-mode Content Understanding pipelines

Azure Content Understanding standard and pro modes

Create Content Understanding Standard and Pro tasks in the Foundry portal

Implement solutions that identify objects, components, or regions within images or video

Object detection using Image Analysis 4.0 – Foundry Tools

Azure Content Understanding in Foundry Tools video overview

Implement responsible AI for multimodal content

Implement filters to classify unsafe or disallowed visual content

What is Azure AI Content Safety?

Content filtering for Microsoft Foundry Models

Content Safety in Microsoft Foundry portal overview

Detect and mitigate indirect prompt injection by using embedded text in images

Content filtering in Azure AI Foundry portal

Guardrails and controls overview in Microsoft Foundry

Enforce visual policy rules, such as applying watermarks, flagging prohibited symbols, upholding brand usage requirements, and detecting potentially inappropriate content

What is Azure AI Content Safety?

Azure Content Understanding in Foundry Tools video overview

Risk and Safety Evaluators for Generative AI – Microsoft Foundry

Implement text analysis solutions (10–15%)

Apply language model text analysis

Implement solutions to extract entities, topics, summaries, and structured JSON outputs by using generative prompting and Foundry Tools

What is Azure Language in Foundry Tools

What is summarization? – Foundry Tools

How to use structured outputs with Azure OpenAI in Microsoft Foundry Models

Configure detection of sentiment, tone, safety issues, and sensitive content

What is Azure Language in Foundry Tools

What is Azure AI Content Safety?

Content filtering for Microsoft Foundry Models

Build solutions that translate text by using Azure Translator in Foundry Tools or LLM-powered translation flows

What is Azure Translator in Foundry Tools?

What is Azure Text translation in Foundry Tools?

Azure Translator in Foundry Tools 2025-10-01-preview reference

Customize language model outputs for domain tasks, such as compliance summarization and domain extraction

Create a custom analyzer with Azure Content Understanding in Foundry Tools using REST APIs

Azure Content Understanding in Foundry Tools prebuilt analyzers

Fine-tune models with Microsoft Foundry

Implement speech solutions

Implement workflows to convert speech to text and text to speech for agentic interactions

Speech to Text Overview – Speech Service – Foundry Tools

Text to speech overview – Speech service – Foundry Tools

Choose an Azure Speech Recognition and Generation Technology

Integrate speech as an agent modality, including custom speech models

Voice Live API Overview – Foundry Tools

Custom speech overview – Speech service – Foundry Tools

Train a custom speech model – Speech service – Foundry Tools

Enable multimodal reasoning from audio inputs

Use the LLM-speech API – Speech service – Foundry Tools

Choose an Azure Speech Recognition and Generation Technology

How to use vision-enabled chat models – Microsoft Foundry

Translate speech into other languages by using language models and Foundry Tools

Speech translation overview – Speech service – Foundry Tools

Use the LLM-speech API – Speech service – Foundry Tools

What is Azure Translator in Foundry Tools?

Implement information extraction solutions (10–15%)

Build retrieval and grounding pipelines

Ingest and index content, such as documents, images, audio, and video

AI Enrichment Overview – Azure AI Search

Multimodal Search Concepts and Guidance – Azure AI Search

Integrated vector embedding in Azure AI Search

Configure semantic search, hybrid search, and vector search for grounding

Vector Search Overview – Azure AI Search

Hybrid search using vectors and full text in Azure AI Search

Quickstart: Multimodal Search in the Azure portal – Azure AI Search

Implement enrichment by using custom or built-in skills for text, images, and layout

Skills Reference – Azure AI Search

Skillset Concepts – Azure AI Search

Custom Skill Interface – Azure AI Search

Configure RAG ingestion flow, including documents and using OCR

Tutorial: Skillsets – Azure AI Search

Document Layout Skill – Azure AI Search

Part 2: Build a custom knowledge retrieval (RAG) app with the Foundry SDK

Connect retrieval pipelines directly to workflows and agent tools

Agentic Retrieval Overview – Azure AI Search

Tutorial: Build an Agentic Retrieval Solution – Azure AI Search

Connect an Azure AI Search index to Foundry agents

Extract content from documents

Extract information by using multimodal pipelines that combine OCR, layout analysis, and field extraction

Azure Content Understanding Skill – Azure AI Search

Document Layout Skill – Azure AI Search

Use AI Enrichment With Image and Text Processing – Azure Architecture Center

Produce clean, grounded representations to use with agents and RAG by using Content Understanding

Build a RAG solution with Azure Content Understanding in Foundry Tools

Azure Content Understanding in Foundry Tools Document Overview

What is Foundry IQ? – Microsoft Foundry

Implement analyzers for generating structured or markdown outputs for downstream reasoning by using Content Understanding

Create a custom analyzer with Azure Content Understanding in Foundry Tools using REST APIs

Document Analysis: Extract Structured Content with Azure Content Understanding in Foundry Tools

Azure Content Understanding in Foundry Tools prebuilt analyzers

This brings us to the end of the AI-103 Developing AI Apps and Agents on Azure Study Guide.

What do you think? Let me know in the comments section if I have missed out on anything. Also, I love to hear from you about how your preparation is going on!

In case you are preparing for other Azure certification exams, check out the Azure certification study guides for those exams.

Follow Me to Receive Updates on the AI-103 Exam


Want to be notified as soon as I post? Subscribe to the RSS feed / leave your email address in the subscribe section. Share the article to your social networks with the links below so it can benefit others.

Share the AI-103 Study Guide in Your Network

You may also like

Leave a Reply

Your email address will not be published. Required fields are marked *