Microsoft Azure AI Engineer Associate (AI-102)
The AI-102 exam is designed for professionals who implement and configure Copilot & AI. It validates your ability to plan and manage an Azure AI solution, implement generative AI solutions, implement an agentic solution, implement computer vision solutions, implement natural language processing solutions, and implement knowledge mining and information extraction.
This certification has retired. New candidates should take AI-103. The Azure expert path after that is AI-500.
Exam details
- Certification
- Microsoft Azure AI Engineer Associate
- Application
- Copilot & AI
- Exam code
- AI-102
- Level
- Associate
- Duration
- Approximately 100 minutes
- Questions
- Typically 40–60 questions
- Passing score
- 700 out of 1000
- Cost
- USD $165 — typical price; the exact fee varies by country/region and currency, and local taxes may apply.
- Prerequisites
- None required
- Languages
- English (also available in Japanese, German, French, Spanish and several other languages)
- Delivered by
- Pearson VUE
- Renewal
- Free online assessment, every 12 months
Skills measured
Plan and manage an Azure AI solution (20–25%)
- Select, create, and deploy the right Microsoft Foundry services, models, SDKs, and containers.
- Manage, monitor, and secure AI resources, including keys, authentication, and cost.
- Implement responsible AI, content safety, filters, and governance.
Implement generative AI solutions (15–20%)
- Build generative solutions in Microsoft Foundry, including RAG, prompt flows, and evaluation.
- Use Azure OpenAI in Foundry Models to generate text, code, images, and multimodal output.
- Optimise generation with prompt engineering, monitoring, orchestration, and fine-tuning.
Implement an agentic solution (5–10%)
- Configure resources and create agents with Microsoft Foundry Agent Service.
- Implement multi-agent workflows, orchestration, and autonomous capabilities.
- Test, optimise, and deploy custom agents.
Implement computer vision solutions (10–15%)
- Analyse images, detect objects, generate tags, and extract printed or handwritten text.
- Train, evaluate, and consume custom vision models.
- Analyse video with Azure AI Video Indexer and spatial analysis.
Implement natural language processing solutions (15–20%)
- Analyse and translate text, including entities, sentiment, language detection, and PII.
- Process speech with speech-to-text, text-to-speech, custom speech, and translation.
- Implement custom language understanding and question answering models.
Implement knowledge mining and information extraction (15–20%)
- Implement Azure AI Search indexes, skillsets, indexers, and semantic or vector search.
- Extract data with Document Intelligence prebuilt and custom models.
- Use Content Understanding to extract text, tables, entities, and attributes from documents and media.
Study Resources
Disclosure: some links below are affiliate links. If you buy through them we may earn a commission, at no extra cost to you. Read our affiliate disclosure.
Frequently asked questions
Who should take AI-102?
AI-102 is for Azure AI engineers, machine learning engineers, and software engineers. Most work at software firms and consultancies, or in enterprise data and AI teams in financial services, healthcare, and technology. This exam has retired; new candidates should look at AI-103 instead.
What is the average salary for an Azure AI Engineer?
As of 2026, Azure AI and applied AI engineer roles in the United States commonly earn about $130,000 to $170,000. In the United Kingdom, Azure AI jobs have a median advertised salary around £71,250. In western Europe, AI and ML engineer pay is typically lower than the US; German professional bands for comparable technical roles are often about €70,000 to €100,000. This exam retired in June 2026, so new hires may be asked for newer AI credentials.
Where do I find exam questions to practice?
You will find websites selling exam dumps or brain dumps that claim to be real AI-102 questions. Those materials are not official. Microsoft treats using brain dumps as cheating. It can invalidate your score, revoke certifications you already hold, and ban you from future exams. MeasureUp also sells the official practice test linked in the study resources on this page. You can try the Microsoft exam sandbox to see the question types and timer, but it does not use real exam questions. Practise the skills measured in a real product environment rather than memorising leaked items.
Does the exam include official labs I can use to practice?
Microsoft does not publish a stable list of which certification exams include labs, and a lab can be dropped for a candidate if the live environment is unavailable. Role-based Azure and security exams such as AI-102 may include performance-based labs in a live cloud environment. You only find out at the start of your sitting. For practice, Microsoft Learn modules for this exam often include a free Azure sandbox, and official instructor-led AI-102T00 training delivered by a Microsoft Learning Partner includes labs. Those labs are for the course, not a copy of the exam. Applied Skills assessment labs are a separate Microsoft credential, not AI-102 exam labs. The Microsoft exam sandbox shows traditional question types only. It does not give you the lab virtual machine.