AI-103 Azure AI Apps and Agents Developer Associate Study Guide

By Macdara Ó Murchú · Founder, AzurePrep·Last reviewed ·11 min read·2,310 words

AI-103 validates your ability to build, manage and deploy AI apps and agents on Azure using Microsoft Foundry. This AI-103 study guide covers the exam domains, format and a preparation plan, so you can focus your study time on what the exam actually measures.

What the AI-103 Exam Tests

AI-103 targets an Azure AI engineer who builds, manages and deploys agents and AI solutions using Microsoft Foundry. You should have experience developing apps in Python, and be familiar with general AI, generative AI and Azure services.

Your responsibilities in this role include:

In this role you collaborate with business stakeholders, solution architects, data scientists, DevOps engineers and cloud security engineers to design, implement and maintain AI solutions. AI-102 split generative AI (15-20%) and agentic solutions (5-10%) into two domains. AI-103 combines them into one domain at 30-35%, the largest weighting on the exam.

Target Audience and Prerequisites

The certification is pitched at an intermediate level for two overlapping roles: AI Engineer and Developer. Expect to bring:

If you are new to Azure AI entirely, working through the Microsoft Foundry documentation and the associated training modules before you start timed practice will save you time later, since several exam objectives assume you already know your way around a Foundry project.

Exam Format and Scoring

AI-103 follows Microsoft's standard proctored certification format:

Most questions cover features that are generally available, though the exam may include questions on preview features already in common use. Many of the skills measured start with "choose", so practise picking the right Foundry service, model or configuration for a described business requirement.

Domain Weightings and Blueprint

The current AI-103 blueprint, published as the "skills measured as of April 16, 2026" version, is organised into five domains:

Domain Weight
Plan and manage an Azure AI solution 25-30%
Implement generative AI and agentic solutions 30-35%
Implement computer vision solutions 10-15%
Implement text analysis solutions 10-15%
Implement information extraction solutions 10-15%

Plan and Manage an Azure AI Solution

This domain covers choosing and operating Foundry services rather than writing application code.

Choosing Foundry services: know how to choose an appropriate model for a task, including large language models, small language models, multimodal models and Foundry Tools. You also need to choose the right service for generative tasks, grounding, vector search, agent workflows or multimodal processing, and pick an appropriate retrieval and indexing method.

Setting up AI solutions: design Azure infrastructure for AI apps and agent-based solutions, choose deployment options, configure model and agent deployments, and integrate Foundry projects with CI/CD pipelines.

Managing, monitoring and securing: manage quotas, scaling, rate limits and cost footprints for model and agent workloads. Monitor model performance, drift, safety events and grounding quality, along with data ingestion quality, search index health and relevance. Configure security using managed identity, private networking, keyless credentials and role policies.

Responsible AI: configure safety filters, guardrails, risk detection and content moderation. Apply responsible AI instrumentation such as evaluators and safety evaluations, implement auditing through trace logging and provenance metadata, and govern agent behaviour with oversight modes, constraints and tool-access controls.

Implement Generative AI and Agentic Solutions

This is the largest domain on the exam and the one most changed from AI-102.

Building generative applications: deploy and consume large language models, small models, code models and multimodal models. Implement retrieval-augmented generation in an application, and design workflows, tool-augmented flows and multistep reasoning pipelines. Evaluate models and apps for fabrications, relevance, quality and safety, and integrate generative workflows using Foundry SDKs and connectors.

Building agents: define agent roles, goals, conversation-tracking approach and tool schemas. Build agents that integrate retrieval, function-calling and conversation memory, and integrate agent tools such as APIs, knowledge stores, search, content understanding and custom functions. Implement orchestrated multi-agent solutions, build autonomous or semiautonomous workflows with safeguards and approval controls, and integrate monitoring so you can evaluate agent behaviour and perform error analysis.

Optimising and operationalising: tune generation behaviour through prompt engineering and model parameters, implement model reflection and self-critique loops, set up observability through tracing, token analytics, safety signals and latency breakdowns, and orchestrate multiple models or hybrid LLM and rules-based flows.

Example AI-103 Scenario

Here is the kind of scenario to expect. It tests a skill from the generative AI and agentic solutions domain, the heaviest on the exam.

A retail company is building a customer support agent in Foundry. The agent needs to look up order status from an internal API, answer product questions grounded in a document repository, and remember earlier turns in the same conversation. Which combination of capabilities should the agent use?

B is correct. The scenario needs three capabilities AI-103 tests separately: function-calling for the live order lookup, retrieval-augmented generation for grounded product answers, and conversation memory to track earlier turns. Option A does not scale past a small repository, since it resends the same content every turn. Option C cannot answer questions about documents added or changed after the fine-tuning run. Option D drops context between tasks, which fails the conversation-tracking requirement Foundry agents are built around.

Implement Computer Vision Solutions

Vision on AI-103 spans generation as well as understanding.

Image and video generation: implement solutions that generate images and videos from text prompts and reference media, configure image-editing workflows including inpainting, mask-based edits and prompt-driven modifications, and edit generated videos using the platform's generation and editing controls.

Multimodal understanding: build solutions that analyse visual context using multimodal models, configure concise or detailed captions for single or multiple images, and implement question-answering grounded in visual evidence. Configure alt-text and extended image descriptions aligned to accessibility guidelines, implement visual understanding through Azure Content Understanding in Foundry Tools, and process video segments using single-task and pro-mode Content Understanding pipelines.

Responsible AI for multimodal content: implement filters to classify unsafe or disallowed visual content, detect and mitigate indirect prompt injection embedded as text in images, and enforce visual policy rules such as watermarks and brand usage requirements.

Implement Text Analysis Solutions

Language model text analysis: implement solutions to extract entities, topics, summaries and structured JSON output using generative prompting and Foundry Tools, configure detection of sentiment, tone, safety issues and sensitive content, and build translation solutions using Azure Translator in Foundry Tools or LLM-powered translation flows.

Speech solutions: implement speech-to-text and text-to-speech workflows for agentic interactions, integrate speech as an agent modality including custom speech models, enable multimodal reasoning from audio inputs, and translate speech into other languages using language models and Foundry Tools.

Implement Information Extraction Solutions

Retrieval and grounding pipelines: ingest and index documents, images, audio and video. Configure semantic search, hybrid search and vector search for grounding, implement enrichment using custom or built-in skills for text, images and layout, configure RAG ingestion flow including OCR, and connect retrieval pipelines directly to workflows and agent tools.

Extracting content from documents: extract information using multimodal pipelines that combine OCR, layout analysis and field extraction, produce clean, grounded representations for agents and RAG using Content Understanding, and implement analyzers that generate structured or markdown output for downstream reasoning.

Study Timeline and Preparation Strategy

A realistic AI-103 timeline runs 8 to 10 weeks with consistent effort, longer if you are new to Microsoft Foundry.

Weeks 1-2: Foundation. Work through the Foundry documentation and training modules for each domain. Provision a Foundry project and deploy a model so you have a working environment to practise in.

Weeks 3-5: Generative AI and agents. This is where the exam weighting is heaviest, so give it proportionally more time. Build a retrieval-augmented generation application end to end, then build an agent with function-calling, tool integration and conversation memory. Practise orchestrating more than one agent in a single workflow.

Weeks 6-7: Vision, text and extraction. Implement an image or video generation workflow, a document extraction pipeline using Content Understanding, and a text analysis solution that produces structured output. Configure responsible AI controls, such as content filters, on at least one of these.

Weeks 8-10: Practice tests and review. Take full-length practice tests to find weak domains, then revisit the Foundry documentation for anything you scored poorly on. Review scenario questions that ask you to choose between similar services, since that pattern recurs across every domain.

Common Exam Traps and How to Avoid Them

Service selection under Foundry. Several questions describe a scenario and ask which Foundry service or model fits. The trap is usually two services with overlapping capability, such as a general multimodal model versus a purpose-built Content Understanding pipeline. Read for clues about whether the scenario needs structured, grounded output or open-ended generation.

Treating agents as a single-step feature. The exam separates agent definition, tool integration, orchestration and monitoring into distinct skills. A solution that only calls one function once is a different skill from an orchestrated, monitored multi-agent workflow, and the skills list names each one separately.

Skipping responsible AI until the end. Responsible AI controls appear inside the planning domain and again inside the computer vision domain. Build guardrails, content filters and prompt-injection mitigation into your practice projects from the start. Treating them as an afterthought is the mistake that costs the most marks here.

Under-preparing for extraction pipelines. Document and multimodal extraction can look like a smaller, easier domain because of its weighting, but scenario questions here combine OCR, layout analysis and Content Understanding in ways that reading alone will not prepare you for; build at least one pipeline yourself.

Essential Study Resources

The AI-103 study guide on Microsoft Learn is the primary reference for the domains, weightings and update history covered above.

Training paths and modules cover Foundry, generative AI, agents, computer vision, text analysis and information extraction, each with interactive exercises and knowledge checks.

The exam sandbox lets you experience the question types and interface before exam day.

AI Skills Navigator hosts the official practice assessment for this certification; you need to be signed in to launch it.

Microsoft Foundry documentation is where you will spend most of your hands-on time, since almost every domain routes through a Foundry project, deployment or tool.

azureprep.com offers practice questions across current Azure certifications, useful for building exam-style question familiarity alongside the official study resources.

Taking the Exam

Schedule AI-103 through Pearson VUE from the certification page. Microsoft recommends registering with a personal MSA account. A work or school account puts your exam records at risk: they are lost if you leave that organisation.

The exam is proctored and may include interactive components, so review Microsoft's exam duration and experience guidance before your session. Read each scenario fully before looking at the answer options, identify the requirement the question is actually testing, and manage your time across the 120 minutes so you can return to any questions you flag for review.

If you do not pass, you can retake the exam 24 hours after your first attempt. For further retakes the wait varies; check Microsoft's current retake policy when you schedule.

Maintaining Your Certification

Microsoft associate certifications expire annually. You keep the Azure AI Apps and Agents Developer Associate certification current by passing a free online renewal assessment on Microsoft Learn before the expiry date. There is no need to resit the full exam.

Moving Forward After AI-103

The Azure AI Apps and Agents Developer Associate certification demonstrates that you can build and operate AI apps and agents on Azure using Microsoft Foundry. From here, broader Azure architecture knowledge through AZ-305 is a natural next step if your role extends beyond AI-specific implementation into wider solution design. For how AI-103 fits into the wider Azure AI Engineer role, see our Azure AI Engineer career path guide.

Keep practising against real Foundry projects after you pass. The domains on this exam, particularly agent orchestration and responsible AI controls, describe day-to-day engineering work, so the skills stay relevant well past certification day.

Ready to test yourself against exam-style questions? Practise for AI-103 and work through scenario questions across all five domains before you sit the real exam.