EnglishDeutschFrançaisEspañolPortuguês

Microsoft · AI-103 · Associate

Developing AI Apps and Agents on Azure (AI-103) — Practice Questions and Mock Exam

Exam AI-103, Developing AI Apps and Agents on Azure, leads to the Microsoft Certified: Azure AI Apps and Agents Developer Associate certification.

Practice for freeTry a practice question first
Try a practice question firstPractice for free
Start practicing AI-103 freeBuy AI-103 access for $29.99
50Questions per Pass-IT mock exam
120minPass-IT mock exam time limit

Official AI-103 exam: 700 out of 1000 points to pass.

Checked against Microsoft · August 2026 · Current exam version

Try Pass-IT

See what learning with Pass-IT is like.

Answer a AI-103 sample question and read the explanation with its source. Right here, with no sign-up.

Plan and manage an Azure AI solution1 / 5

Your security policy requires that approval is obtained before any change, but a developer asks to set a deployment's content filter to 'No filters' (turn filtering off) for an Azure OpenAI model. What is required before this configuration can take effect?

AlexFull explanation from Alex

Foundry content filters are configurable: any customer can set the severity threshold (low, medium, or high) separately for prompts and completions. However, the 'No filters' and 'Annotate only' options, which disable blocking, require special approval. For Azure OpenAI models, only customers approved through the Azure OpenAI Limited Access Review for modified content filters can fully turn off filtering. This is a governance guardrail to keep responsible-AI protections in place by default. Exam tip: changing thresholds = no approval needed; disabling filtering entirely or annotate-only = requires the modified-content-filter approval.

Sourcelearn.microsoft.com

Implement computer vision solutions2 / 5

A solution must extract custom structured fields directly from product-shelf photos (for example, shelf-share percentages and detected brands) using a schema you define, including classifying images into categories and generating fields with a generative model. Which Azure capability is purpose-built for this image field extraction?

AlexFull explanation from Alex

Azure AI Content Understanding extends field extraction across all modalities, including images. Its image field extraction capability lets you extract custom structured fields from images based on a schema you define; fields can be extracted directly, classified from a set of categories, or generated using a generative model. This is well suited to retail shelf analysis, manufacturing quality control, and chart-based BI where you need structured outputs rather than free-form captions. Unlike Image Analysis Caption (a fixed sentence) or generic VQA, image field extraction is schema-driven and returns machine-readable fields. Exam tip: 'custom schema-driven structured fields from images, with classification and generative options' = Content Understanding image field extraction.

Sourcelearn.microsoft.com

Implement information extraction solutions3 / 5

You must ingest mixed PDFs that contain both narrative text and embedded charts/diagrams into an Azure AI Search index for multimodal RAG. You want a single skill that analyzes layout, produces Markdown that preserves section structure, and extracts images with location metadata so chunks stay near their related figures. Which built-in skill should you use?

AlexFull explanation from Alex

The Document Layout skill in Azure AI Search calls the Azure Document Intelligence layout model to detect document structure and emit a syntactical representation in Markdown or text. Its markdownHeaderDepth setting controls section nesting, and when configured for text output with image extraction it returns normalized_images plus locationMetadata that preserves each image's position in the document. Keeping images near their related content is valuable for RAG and multimodal search. Exam tip: 'structure-aware Markdown plus image location metadata for multimodal RAG' points to the Document Layout skill, not plain OCR.

Sourcelearn.microsoft.com

Implement text analysis solutions4 / 5

A contact centre stores multi-turn chat transcripts and must redact personal data before analysts are allowed to read them. Whether a phrase counts as sensitive depends on turn boundaries and on what the other speaker said. The redaction job runs nightly over stored transcripts rather than at request time. Which Azure Language PII feature fits?

AlexFull explanation from Alex

Azure Language splits PII detection by the shape of the input rather than by the entity types involved, and that split determines both the API pattern and the quality of the result. Plain strings are handled synchronously, which suits request-time redaction of a message or a log line. Native files are handled asynchronously and the output preserves document structure, which matters when the redacted artefact has to remain readable as a document. Conversations are their own shape because context crosses turns: a name mentioned once can make a later pronoun identifying, and masking has to respect who said what. Choosing the wrong feature type usually still returns entities, which is why the mistake survives review; it just returns worse ones. Matching feature type to data shape first, and tuning entity categories second, is the reliable order.

Sourcelearn.microsoft.com

Implement generative AI and agentic solutions5 / 5

A platform team wants to debug a multi-step agent by seeing the full execution flow, including each LLM call, tool invocation, and agent decision, with data flowing into Application Insights. Which observability capability in Microsoft Foundry provides this end-to-end execution visibility?

AlexFull explanation from Alex

Microsoft Foundry's observability rests on three pillars: evaluation (measuring quality and safety), monitoring (production dashboards and alerts), and tracing. Tracing provides distributed, end-to-end visibility into an AI application's execution: it records LLM calls, tool invocations, agent decisions, and inter-service dependencies. It is built on the OpenTelemetry standard and integrates with Azure Monitor Application Insights, which is exactly what you need to debug multi-step agent behavior, find bottlenecks, and understand reasoning chains. Tracing supports frameworks including the Microsoft Agent Framework and the OpenAI Agents SDK. Exam tip: when a question mentions 'execution flow', 'every decision', 'OpenTelemetry', or 'Application Insights for debugging agents', the answer is tracing.

Sourcelearn.microsoft.com

How to prepare for AI-103 with Pass-IT.

Currently 453 practice questions for AI-103, with new ones added regularly. Focus on what you still need to learn.

Get past difficult questions.

Understand why an answer is correct. Alex explains the concepts and answers your follow-up questions so you can apply what you learn to the next task.

Meet Alex →

Try the available questions in the preview above.

Make your study time count.

Practice at your level.
For new practice sessions, Pass-IT adjusts the difficulty based on your previous answers.

Learn from mistakes.
Incorrect answers automatically become flashcards. When you review them, you rate how confidently you remember; Pass-IT schedules the next review.

See how focused practice works →

Try the available questions in the preview above.

Practice for the moment that counts.

Take a full mock exam with a time limit and find out whether you can finish in time.

Your AI-103 mock exam

Questions
50
Minutes
120

Illustration of an exam session

  1. Start
  2. Answer questions
  3. Finish

Length and time limit of the Pass-IT mock exam.

Go into your exam with more confidence.

Your Readiness Score helps you assess whether you are ready for the exam. Results by exam domain show you where you should keep practicing.

Your money back if you fail despite 80% Readiness.
If your Readiness Score is at least 80% when you take the exam and you still fail, we refund the Pass-IT purchase price for this certification.

For active, paid access. Submit proof of failing within 14 days.

Further guarantee conditions

You need at least 80% Readiness and active, paid access to the certification when you take the exam. Take the exam within your access period and submit official proof of failing within 14 days after the exam.

For purchases through Apple or Google, refunds are handled by the respective store. See the full terms for further details.

Read the guarantee terms →

The Readiness Score describes your practice progress, not a probability of passing.

Guarantee requirement

80%

At least 80% Readiness
when you take the exam

Money back if you fail

Question counts and mock exam settings from the current Pass-IT catalog.

Exam domains

What you practice for AI-103.

Exam topics, relevant practice and sources you can check.

Planning and operating Foundry solutions25–30% of the exam122 QuestionsPass-IT questions

Choose AI services and configure the infrastructure, monitoring and controls they need.

  • Choose large, small or multimodal models and Foundry services for generation, retrieval, indexing, vector search, memory, knowledge and agent tools.
  • Design Azure infrastructure, choose deployment options, deploy models and agents and connect Foundry projects to continuous integration and deployment pipelines.
  • Manage quotas, scaling, rate limits and cost; monitor model drift, safety, grounding and index quality, and secure access with managed identities, private networks and role policies.
  • Apply safety filters, risk detection and responsible AI evaluations; record traces and provenance, require approvals and govern agent oversight, constraints and tool access.
Official Microsoft objectives
Generative applications and agents30–35% of the exam150 QuestionsPass-IT questions

Build applications and agents that use models, retrieved knowledge and tools.

  • Deploy and call language, code and multimodal models, add retrieval-augmented generation and multistep tool workflows, and connect applications to Foundry projects with SDKs and connectors.
  • Evaluate fabricated answers, relevance, quality and safety; monitor deployed agents, assess their behavior and investigate errors.
  • Define agent roles, goals, conversation tracking and tool schemas; integrate retrieval, function calls, memory, APIs, search, knowledge stores and content understanding.
  • Orchestrate multiple agents, models and flows, including hybrid language-model and rules systems; add safeguards and approvals to autonomous or partly autonomous workflows.
  • Tune prompts and model parameters, implement model-reflection and self-critique loops, evaluate reasoning steps, and trace token usage, safety signals and latency.
Official Microsoft objectives
Generating and understanding visual content10–15% of the exam58 QuestionsPass-IT questions

Create, edit and analyze images and video while applying visual-content safeguards.

  • Generate images and videos from text or reference media, edit images with masks or prompts and edit generated video using platform controls.
  • Analyze visual context, caption one or more images, answer questions from visual evidence and generate accessible alternative text and extended descriptions.
  • Configure Content Understanding for visual features, video segments and object or region detection, using single-task or pro-mode pipelines.
  • Filter unsafe visual content, detect prompt injection hidden in image text and enforce policies for watermarks, prohibited symbols and brand use.
Official Microsoft objectives
Text analysis and speech10–15% of the exam59 QuestionsPass-IT questions

Extract meaning from text and add speech and translation to agents.

  • Extract entities, topics, summaries and structured JSON, detect sentiment, tone and sensitive or unsafe content, and tailor outputs to a business domain.
  • Translate text and speech with Azure Translator, language models and Foundry Tools.
  • Implement speech-to-text and text-to-speech, integrate custom speech models into agents and support multimodal reasoning from audio.
Official Microsoft objectives
Retrieval and document extraction10–15% of the exam64 QuestionsPass-IT questions

Prepare searchable content and structured information for agents and grounded answers.

  • Ingest and index documents, images, audio and video, and configure semantic, hybrid and vector search for grounding.
  • Enrich text, images and layouts with built-in or custom skills, configure document ingestion with optical character recognition and connect retrieval to workflows and agent tools.
  • Combine character recognition, layout analysis and field extraction with Content Understanding to produce grounded structured or Markdown output for agents and retrieval-augmented generation.
Official Microsoft objectives
Question formats you can practice
Multiple Choice
Select one answer.
Multiple Response
Select multiple applicable answers.
Drag & Drop
Match items to the appropriate targets.

These are Pass-IT practice formats. Check the Microsoft certification page for the official exam information.

The ranges describe the weighting of exam topics. See Official Microsoft objectives for the current exam objectives.

Frequently asked questions

Your preparation

How much study time should I plan for AI-103?

For planning, Pass-IT estimates roughly 25–70 hours. Relevant experience may put you toward the lower end; starting from scratch may put you toward the higher end. Your needs may fall outside this range. This is not a time requirement from Microsoft or a promise that you will be exam-ready within that time.

What do you need to know before AI-103?

Microsoft expects experience developing applications in Python and familiarity with AI, generative AI and the Azure AI services, without enforcing a certification prerequisite. The catalog budget is around 45 hours. It is a developer exam, so SDK behaviour matters more than machine learning theory.

Using Pass-IT

What language are Pass-IT questions in?

Questions in the app are currently in English. Translations of the sample questions on this page apply only to this preview. Check with Microsoft for the languages available for the official exam.

How long does my AI-103 access last?

Access covers this certification for 12 months. You pay once, with no automatic renewal.

When does the money-back guarantee apply?

The guarantee refunds the Pass-IT purchase price for this certification. You need eligible paid access and a Readiness Score of at least 80% from your practice results when you take the exam. This score can only reach 80% after at least 50 answered questions and is not a validated probability of passing. Take the exam during your access period and submit official proof of failing within 14 days. Guarantee terms

About the AI-103 exam

Where can I take the AI-103 exam?

Pearson VUE (test center or online proctored).

How long is the Developing AI Apps and Agents on Azure exam?

The AI-103 exam has 50 questions and a 120-minute time limit.

How long does AI-103 stay valid?

One year. Microsoft renews it through a free online renewal assessment on Microsoft Learn that has to be passed before the expiry date. On a subject moving this quickly, the yearly assessment is a fair proxy for whether the knowledge is still current.

Your preparation for AI-103

$29.99one-time

12 months of access for AI-103 · No automatic renewal

Buy AI-103 access

Questions in the app are currently in English.

Try 20 questions for freeFree account required. No credit card.

Already have an account? Log in

Prefer a subscription? View subscriptions →

Money back if you fail with at least 80% Readiness, for eligible purchases under the guarantee terms.

Guarantee terms

The guarantee refunds the Pass-IT purchase price for this certification. You need eligible paid access and a Readiness Score of at least 80% from your practice results when you take the exam. This score can only reach 80% after at least 50 answered questions and is not a validated probability of passing. Take the exam during your access period and submit official proof of failing within 14 days.

Full guarantee terms →

Related certifications

Administering Information Security in Microsoft 365Administering Microsoft Azure SQL SolutionsAdministering Windows ServerCollaboration Communications Systems EngineerAll Microsoft certifications →