Updated: May 2023 February 2024

There has been an AI specific exam around for a while know, but perhaps the interest in it has been quite limited, not anymore! The AI-102 is becoming very popular, here is what Microsoft have to say about it:

Microsoft Azure AI engineers build, manage, and deploy AI solutions that make the most of Azure Cognitive Services and Azure services. Their responsibilities include participating in all phases of AI solutions development—from requirements definition and design to development, deployment, integration, maintenance, performance tuning, and monitoring.

These professionals work with solution architects to translate their vision and with data scientists, data engineers, IoT specialists, infrastructure administrators, and other software developers to build complete end-to-end AI solutions.

Azure AI engineers have experience developing solutions that use languages such as Python or C# and should be able to use REST-based APIs and software development kits (SDKs) to build secure image processing, video processing, natural language processing (NLP), knowledge mining, and conversational AI solutions on Azure. They should be familiar with all methods of implementing AI solutions. Plus, they understand the components that make up the Azure AI portfolio and the available data storage options. Azure AI engineers also need to understand and be able to apply responsible AI principles.

If you pass the exam, you will earn an associate certification – Microsoft Certified: Azure AI Engineer Associate.

As always, a great place to start is Microsoft Learn. Microsoft now offer their version of a study guide too, this is important to keep an eye on upcoming changes to content, and with AI, I expect this to change more frequently than some other exams. As always, these are free and you can work through them at your own pace. I find this a great way to study and gain greater understanding of the services by actually using them and you will need to be very familiar with Azure networking to pass this exam.

Below I’ve put together a collection of links relevant to the sections Microsoft have highlighted as being part of the skills measured for this exam. These are only guide links, sometimes you need to explore a topic much more deeply if you are not familiar with it. Hopefully these study materials will help guide you to successfully passing AI-102!

Plan and manage an Azure AI solution (15-20%)

Select the appropriate Azure AI service

• Select the appropriate service for a computer vision solution
• Select the appropriate service for a natural language processing solution
• Select the appropriate service for a decision support solution
• Select the appropriate service for a speech solution
• Select the appropriate service for a generative AI solution
• Select the appropriate service for a document intelligence solution
• Select the appropriate service for a knowledge mining solution
• https://learn.microsoft.com/en-us/azure/architecture/data-guide/technology-choices/cognitive-services – Cycle through each, familiarise yourself with terms and capabilities of each.

Plan, create and deploy an Azure AI service

• Plan for a solution that meets Responsible AI principles – https://learn.microsoft.com/en-us/azure/cloud-adoption-framework/innovate/best-practices/trusted-ai
• Create an Azure AI resource – https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/create-resource?pivots=web-portal
• Determine a default endpoint for a service – As above
• Integrate Azure AI services into a continuous integration and continuous delivery (CI/CD) pipeline – https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-speech-continuous-integration-continuous-deployment (logic is relatively similar for other services, may need more research depending on your familiarity)
• Plan and implement a container deployment – https://learn.microsoft.com/en-us/azure/ai-services/cognitive-services-container-support

Manage, monitor and secure an Azure AI service

• Configure diagnostic logging – https://learn.microsoft.com/en-us/azure/ai-services/diagnostic-logging
• Monitor an Azure AI resource – https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/monitoring
• Manage costs for Azure AI services – https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/manage-costs
• Manage account keys – https://learn.microsoft.com/en-us/azure/ai-services/rotate-keys
• Protect account keys by using Azure Key Vault – https://learn.microsoft.com/en-us/azure/ai-services/use-key-vault?tabs=azure-cli&pivots=programming-language-python
• Manage authentication for an Azure AI Service resource – https://learn.microsoft.com/en-us/azure/ai-services/authentication
• Manage private communications – https://learn.microsoft.com/en-us/azure/ai-services/cognitive-services-virtual-networks?tabs=portal

Implement decision support solutions (10–15%)

Create decision support solutions for data monitoring and content delivery

• Implement a data monitoring solution with Azure AI Metrics Advisor – https://learn.microsoft.com/en-us/azure/ai-services/metrics-advisor/overview
• Implement a text moderation solution with Azure AI Content Safety – https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/text-moderation-api
• Implement an image moderation solution with Azure AI Content Safety – https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/image-moderation-api (read more on what Content Moderator is as well for context)

Implement computer vision solutions (15–20%)

Analyze images

• Select visual features to meet image processing requirements – https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/overview
• Detect objects in images and generate image tags – https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-object-detection-40
• Include image analysis features in an image processing request Interpret image processing responses – https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/overview-image-analysis?tabs=4-0
• Extract text from images using Azure AI Vision – https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-ocr
• Convert handwritten text using Azure AI Vision – https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/quickstarts-sdk/client-library?tabs=windows%2Cvisual-studio&pivots=programming-language-csharp

Implement custom computer vision models by using Azure AI Vision

• Choose between image classification and object detection models – https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/overview#classification-and-object-detection
• Label images – https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/suggested-tags
• Train a custom image model, including image classification and object detection – https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/getting-started-improving-your-classifier
• Evaluate custom vision model metrics – https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/test-your-model
• Publish a custom vision model – https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/getting-started-build-a-classifier (easiest to understand via tutorial)
• Consume a custom vision model – https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/get-started-build-detector (again, as above but now objects so you get both elements)

Analyze videos

• Use Azure AI Video Indexer to extract insights from a video or live stream – https://learn.microsoft.com/en-us/azure/azure-video-indexer/concepts-overview
• Use Azure AI Vision Spatial Analysis to detect presence and movement of people in video – https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/intro-to-spatial-analysis-public-preview

Implement natural language processing solutions (30–35%)

Analyze text by using Azure AI Language

• Extract key phrases – https://learn.microsoft.com/en-us/azure/ai-services/language-service/key-phrase-extraction/overview
• Extract entities – https://learn.microsoft.com/en-us/azure/ai-services/language-service/entity-linking/overview
• Determine sentiment of text – https://learn.microsoft.com/en-us/azure/ai-services/language-service/sentiment-opinion-mining/overview
• Detect the language used in text – https://learn.microsoft.com/en-us/azure/ai-services/language-service/language-detection/overview
• Detect personally identifiable information (PII) in text – https://learn.microsoft.com/en-us/azure/ai-services/language-service/personally-identifiable-information/overview

Process speech by using Azure AI Speech

• Implement text-to-speech – https://learn.microsoft.com/en-us/azure/ai-services/speech-service/get-started-text-to-speech?tabs=windows%2Cterminal&pivots=programming-language-csharp
• Implement speech-to-text – https://learn.microsoft.com/en-us/azure/ai-services/speech-service/get-started-speech-to-text?tabs=windows%2Cterminal&pivots=programming-language-csharp
• Improve text-to-speech by using Speech Synthesis Markup Language (SSML) – https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup
• Implement custom speech solutions – https://learn.microsoft.com/en-us/azure/ai-services/speech-service/custom-speech-overview
• Implement intent recognition – https://learn.microsoft.com/en-us/azure/ai-services/speech-service/intent-recognition
• Implement keyword recognition – https://learn.microsoft.com/en-us/azure/ai-services/speech-service/keyword-recognition-overview

Translate language

• Translate text and documents by using the Azure AI Translator service – https://learn.microsoft.com/en-us/azure/ai-services/translator/text-translation-overview
• Implement custom translation, including training, improving, and publishing a custom model – https://learn.microsoft.com/en-us/azure/ai-services/translator/custom-translator/overview
• Translate speech-to-speech by using the Azure AI Speech service – https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-translate-speech?tabs=terminal&pivots=programming-language-csharp
• Translate speech-to-text by using the Azure AI Speech service – https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-translation
• Translate to multiple languages simultaneously – https://learn.microsoft.com/en-us/azure/ai-services/translator/custom-translator/overview

Implement and manage a language understanding model by using Azure AI Language

• Create intents and add utterances – https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/overview
• Create entities – https://learn.microsoft.com/en-us/azure/ai-services/language-service/entity-linking/overview
• Train, evaluate, deploy, and test a language understanding model – https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/how-to/train-model?tabs=language-studio
• Optimize a language understanding model – https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/overview
• Consume a language model from a client application – https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/how-to/call-api?tabs=language-studio
• Backup and recover language understanding models – https://learn.microsoft.com/en-us/azure/ai-services/language-service/conversational-language-understanding/how-to/fail-over

Create a question answering solution by using Azure AI Language

• Create a question answering project – https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/overview
• Add question-and-answer pairs manually – https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/create-test-deploy
• Import sources – https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/export-import-refresh
• Train and test a knowledge base – https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/quickstart/sdk?tabs=windows&pivots=studio
• Publish a knowledge base – https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/tutorials/bot-service
• Create a multi-turn conversation – https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/tutorials/guided-conversations
• Add alternate phrasing – https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/tutorials/adding-synonyms
• Add chit-chat to a knowledge base – https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/chit-chat
• Export a knowledge base – https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/how-to/export-import-refresh
• Create a multi-language question answering solution – https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/tutorials/multiple-languages

Implement knowledge mining and document intelligence solutions (10–15%)

Implement an Azure Cognitive Search solution

• Provision a Cognitive Search resource – https://learn.microsoft.com/en-us/azure/search/search-what-is-azure-search
• Create data sources – https://learn.microsoft.com/en-us/azure/search/search-get-started-vector
• Create an index – https://learn.microsoft.com/en-us/azure/search/search-get-started-vector
• Define a skillset – https://learn.microsoft.com/en-us/azure/search/cognitive-search-quickstart-blob
• Implement custom skills and include them in a skillset – https://learn.microsoft.com/en-us/azure/search/cognitive-search-defining-skillset
• Create and run an indexer – https://learn.microsoft.com/en-us/azure/search/search-indexer-overview
• Query an index, including syntax, sorting, filtering, and wildcards – https://learn.microsoft.com/en-us/azure/search/search-howto-run-reset-indexers?tabs=portal
• Manage Knowledge Store projections, including file, object, and table projections – https://learn.microsoft.com/en-us/azure/search/knowledge-store-concept-intro?tabs=portal

Implement an Azure AI Document Intelligence solution

• Provision a Document Intelligence resource – https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/overview?view=doc-intel-4.0.0
• Use prebuilt models to extract data from documents – https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/overview?view=doc-intel-4.0.0#prebuilt-models
• Implement a custom document intelligence model – https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/choose-model-feature?view=doc-intel-4.0.0
• Train, test, and publish a custom document intelligence model – https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/how-to-guides/build-a-custom-model?view=doc-intel-4.0.0 (should also look at classification model)
• Create a composed document intelligence model – https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/concept-composed-models?view=doc-intel-4.0.0
• Implement a document intelligence model as a custom Azure Cognitive Search skill – https://learn.microsoft.com/en-us/previous-versions/azure/search/cognitive-search-custom-skill-form?view=doc-intel-4.0.0

Implement generative AI solutions (10–15%)

Use Azure OpenAI Service to generate content

• Provision an Azure OpenAI Service resource – https://learn.microsoft.com/en-us/azure/ai-services/openai/overview
• Select and deploy an Azure OpenAI model – https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models
• Submit prompts to generate natural language – https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/chatgpt?tabs=python&pivots=programming-language-chat-completions
• Submit prompts to generate code – https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/work-with-code
• Use the DALL-E model to generate images – https://learn.microsoft.com/en-us/azure/ai-services/openai/dall-e-quickstart?tabs=dalle3%2Ccommand-line&pivots=programming-language-studio
• Use Azure OpenAI APIs to submit prompts and receive responses – https://learn.microsoft.com/en-us/azure/ai-services/openai/quickstart?tabs=command-line%2Cpython&pivots=programming-language-python

Optimize generative AI

• Configure parameters to control generative behavior – https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/content-filters
• Apply prompt engineering techniques to improve responses – https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/advanced-prompt-engineering?pivots=programming-language-chat-completions
• Use your own data with an Azure OpenAI model – https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/use-your-data?tabs=ai-search
• Fine-tune an Azure OpenAI model – https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/fine-tuning-considerations

And that’s it! Good luck with your exam!