Skip to content
Cheat sheets
Associate · AI-103Prep available

Microsoft Certified: Azure AI Apps and Agents Developer Associate (AI-103) practice exam and study path

A free, timed 60-question AI-103 practice exam in 120 minutes, scored by domain, with every option explained after you submit. Also 130 practice questions you can check one at a time, a page for every task in the exam guide, and a study path. No sign-up.

Start the free practice examGet the exam packPractise question by question →
Azure AI Apps and Agents Developer Associate exam pack:

$7for 12 months

For Azure AI engineers who build generative AI apps and agents in Python on Microsoft Foundry: choosing models and services, securing and operating them, responsible AI, and vision, text, speech and retrieval solutions.

The exam

Exam code
AI-103
Questions
Not yet published
Time
120 minutes
Passing score
700 of 1,000 (scaled)
Exam fee
$165 (USD)
Question types
multiple choice, multiple response

Exam AI-103 runs 120 minutes, is delivered through Pearson VUE in ten languages and may include interactive components; 700 passes. The fee is set by the country or region (USD 165 in the United States), and the certification renews every year with a free online assessment.

From Microsoft's certification page and exam guide, checked Oct 18, 2026.

Domains and weights

  • Domain 1: Plan and manage an Azure AI solution

    28%

  • Domain 2: Implement generative AI and agentic solutions

    33%

  • Domain 3: Implement computer vision solutions

    13%

  • Domain 4: Implement text analysis solutions

    13%

  • Domain 5: Implement information extraction solutions

    13%

Practice

130 original practice questions, every option explained with the Microsoft documentation page that proves it. Free, no sign-up; progress stays on this device.

Your results on this device →

More practice exams

The lessons, the sample questions on every task page and the first full practice exam are free and stay free. A pack adds the further timed AI-103 practice exams.

Azure AI Apps and Agents Developer Associate exam pack

$7for 12 months

  • Every paid AI-103 practice exam, timed, with every option explained
  • The next version of this exam included when it changes within your 12 months
  • 12 months of access. One payment, nothing renews by itself.
  • 14-day refund, no conditions
  • 14-day refund, no conditions: ask within 14 days of buying and you get the whole payment back.
  • No pass guarantee. These are practice exams written by us from the exam guide and the Microsoft documentation; a score here does not predict your result on the real exam.

Study path

One module per exam domain. Lessons that already exist on BytePatterns are linked; the rest are being written.

  1. Module 1: Plan and manage an Azure AI solution

    1. 1Choosing a model: large, small, reasoning and multimodal models, and when a Foundry Tool fits betterTask 1.1

      Partly covered by: What Is an LLM, Model Routing and Fallbacks

    2. 2Grounding choices: Foundry IQ, file search, web search and Azure AI SearchTask 1.1

      Partly covered by: Retrieval-Augmented Generation, Vector Databases

    3. 3Agent building blocks: toolboxes, memory, knowledge and workflowsTask 1.1

      Partly covered by: Agents and Tools

    4. 4Foundry resources and projects, and the Azure infrastructure around themTask 1.2

      Lesson coming

    5. 5Deployment types: Global, Data Zone and regional; standard, provisioned and batchTask 1.2

      Lesson coming

    6. 6Configuring model and agent deployments, and CI/CD for Foundry projectsTask 1.2

      Partly covered by: From Pilot to Production

    7. 7Quotas, rate limits, provisioned throughput and costTask 1.3

      Partly covered by: Rate Limiting

    8. 8Monitoring models, agents, safety events and search indexesTask 1.3

      Partly covered by: Observability Basics

    9. 9Security: managed identity, keyless credentials, private networking and rolesTask 1.3

      Lesson coming

    10. 10Guardrails, content filters and risk detectionTask 1.4

      Partly covered by: Guardrails

    11. 11Evaluators, safety evaluations and AI red teamingTask 1.4

      Partly covered by: Evaluating LLMs, LLM as a Judge

    12. 12Auditing with traces, provenance and approvals; governing tool accessTask 1.4

      Partly covered by: Tracing a Request, Guardrails

  2. Module 2: Implement generative AI and agentic solutions

    1. 13Deploying and calling models with the Responses API and the Foundry SDKsTask 2.1

      Lesson coming

    2. 14Retrieval-augmented generation in an applicationTask 2.1

      Partly covered by: Retrieval-Augmented Generation, Chunking and Reranking

    3. 15Tool-augmented and multistep flowsTask 2.1

      Partly covered by: The Tool-Use Loop

    4. 16Evaluating models and apps: groundedness, relevance, quality and safetyTask 2.1

      Partly covered by: Evaluating LLMs

    5. 17Prompt agents and hosted agents: instructions, conversations and tool schemasTask 2.2

      Partly covered by: Agents and Tools

    6. 18Retrieval, function calling, built-in tools and memory in agentsTask 2.2

      Partly covered by: The Tool-Use Loop

    7. 19Multi-agent workflows and human approval stepsTask 2.2

      Lesson coming

    8. 20Monitoring, evaluating and debugging deployed agentsTask 2.2

      Partly covered by: Evaluating LLMs

    9. 21Prompt engineering and model parametersTask 2.3

      Partly covered by: Temperature and Sampling, Context Windows

    10. 22Reflection, chain-of-thought evaluation and self-critique loopsTask 2.3

      Partly covered by: LLM as a Judge

    11. 23Tracing, token analytics, safety signals and latencyTask 2.3

      Partly covered by: Tracing a Request, Observability Basics

    12. 24Orchestrating several models, flows and rulesTask 2.3

      Partly covered by: Model Routing and Fallbacks

  3. Module 3: Implement computer vision solutions

    1. 25Image generation and editing: prompts, reference images and masksTask 3.1

      Lesson coming

    2. 26Video generation and editingTask 3.1

      Lesson coming

    3. 27Multimodal models for captions, alt text and visual question answeringTask 3.2

      Lesson coming

    4. 28Content Understanding for images and videoTask 3.2

      Lesson coming

    5. 29Safety for visual content: filters, injected text and visual policiesTask 3.3

      Partly covered by: Guardrails

  4. Module 4: Implement text analysis solutions

    1. 30Entities, topics, summaries and structured JSON with prompts and Azure LanguageTask 4.1

      Lesson coming

    2. 31Sentiment, safety and sensitive contentTask 4.1

      Partly covered by: Finding and Masking PII

    3. 32Translation with Azure Translator or a language modelTask 4.1

      Lesson coming

    4. 33Tailoring output to a domain: instructions, examples and fine-tuningTask 4.1

      Partly covered by: Fine-Tuning vs Prompting

    5. 34Speech to text, text to speech and custom speechTask 4.2

      Lesson coming

    6. 35Voice agents and real-time audioTask 4.2

      Partly covered by: WebSockets and Realtime

    7. 36Speech translationTask 4.2

      Lesson coming

  5. Module 5: Implement information extraction solutions

    1. 37Indexing content in Azure AI Search: indexers, chunking and vectorsTask 5.1

      Partly covered by: Vector Databases, Chunking and Reranking

    2. 38Keyword, semantic, hybrid and vector queriesTask 5.1

      Partly covered by: Embeddings, Approximate Neighbours, Cosine Similarity

    3. 39Enrichment skills and OCR in the ingestion flowTask 5.1

      Lesson coming

    4. 40Connecting retrieval to workflows and agentsTask 5.1

      Partly covered by: Retrieval-Augmented Generation

    5. 41OCR, layout and field extractionTask 5.2

      Lesson coming

    6. 42Content Understanding analyzers with structured and Markdown outputTask 5.2

      Lesson coming

Every task in the exam guide

The exam guide splits each domain into task statements. Each one has a page with a short summary, the lessons that teach it and open sample questions.

Domain 1: Plan and manage an Azure AI solution

Domain 2: Implement generative AI and agentic solutions

Domain 3: Implement computer vision solutions

Domain 4: Implement text analysis solutions

Domain 5: Implement information extraction solutions

How these questions are made

  • Written by us from the exam guide's task statements and the Microsoft documentation — never from real exam content.
  • Every option carries its own explanation and a link to the Microsoft page that proves it.
  • A question enters a timed exam only after an independent check; until then it is a practice question.
  • Results are a plain percentage, per domain too — not an imitation of Microsoft's scaled score.

Questions about the AI-103 practice exam

Is the AI-103 practice exam free?
Yes. The full practice exam (60 questions, 120 minutes) is free with no sign-up, and so are the 130 practice questions, the task pages and the study path. Your attempts are saved in this browser, on this device.
How many questions does it have, and is it timed?
60 questions in 120 minutes: the real AI-103 pace, scaled to this form. When the time runs out, the exam is submitted as it stands.
Are the answers explained?
After you submit, not during: like the real exam, the timed exam gives no feedback until the end. Then you get your score overall and per exam domain, and every question with each option explained and a link to the Microsoft documentation page behind it. In practice mode an answer is explained as soon as you check it.
What does the Azure AI Apps and Agents Developer Associate exam pack add?
3 more timed practice exams (Practice exam 1: 60 questions, 120 minutes; Practice exam 2: 60 questions, 120 minutes; Practice exam 3: 60 questions, 120 minutes), each scored and explained the same way, and the next version of this exam if it changes within your 12 months. 12 months of access. One payment, nothing renews by itself. Everything above stays free. See the pack.
Can I get a refund?
Yes, with no conditions: ask within 14 days of buying and you get the whole payment back. The details are in the terms.
Is this an official Microsoft practice exam?
No. BytePatterns is not affiliated with, endorsed or sponsored by Microsoft. Every question is written by us from the public exam guide and the Microsoft documentation, never from real exam content, and a score here does not predict your result on the real exam. Microsoft lists its own preparation resources on its certification page.