AI-102 Official Course Study Guide
AI-102 Official Course Study Guide
AI-102
Official
Course Study
Guide
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.
Scoring
All technical exam scores are reported on a scale of 1 to 1,000. A passing score is 700 or greater. As
this is a scaled score, it may not equal 70% of the points. A passing score is based on the knowledge
and skills needed to demonstrate competence as well as the difficulty of the questions.
When answering most multi-part questions, you’ll receive one point for each correctly answered
component. You can earn all, some, or none of the points possible for that question. If a question is
worth more than one point, it will be noted in the question. Usually, you’ll receive one point for each
correctly answered component.
There’s no penalty for guessing. If you choose an incorrect answer, you simply won’t earn the point
for that question or part. No points are deducted for incorrect answers.
Some questions on the exam may not be included in your score. These questions are used to gather
data to update and improve the quality of each exam. However, as soon as we have the necessary
data to evaluate their quality, questions that meet our psychometric standards will be scored. You
won’t know which questions are unscored, so you should answer every question as if it will be
included in your score.
Microsoft continues to introduce new and innovative question types that may require different
approaches to scoring. Alternate approaches to scoring will be noted in the question text.
Renewing
The AI-102 exam will need to be renewed every year. Microsoft will from time to time retire
certifications, however, and you may also find exam numbers evolve (this is what happened with the
Page | 1
previous exam AI-100) when Microsoft changes the curriculum substantially for the certification. You
can take the renewal assessment any time during your six-month eligibility window, via Microsoft
Learn. Once you pass, your certification will be extended one year from the expiration date.
There’s no cost to renew your certification, just make sure you pass the online assessment before
your certification expires. Fundamentals certifications do not expire.
Assessments focus on recent technological and industry updates, so they’re shorter than the original
exam(s) and are open book. You can take the assessment as many times as you need as long as you
pass before your certification expires.
Additional info
• The exam will have around 40-60 questions for which you have 130 min to answer.
• As of this moment of writing, there’re no labs.
Page | 2
Book/e-book:
Page | 3
Video training:
Microsoft Learn:
Those tutorials/paths have been combined by Microsoft and published for free. They contain a
collection of text, videos, and exercises for the exam.
Page | 4
Provision and manage Azure Cognitive Services
Azure Cognitive Services are building blocks of
AI functionality that you can integrate into your
applications. In this learning path, you'll learn
how to provision, secure, monitor, and deploy
cognitive services resources and use them to
build intelligent solutions.
Page | 5
Build custom text analytics solutions
Build solutions with newer text analytics
services such as custom text classification and
custom name entity recognition. These services
allow for customizing the built-in features
available in the Language service for exactly
what your application needs.
Page | 6
Develop Generative AI solutions with Azure
OpenAI Service
Azure OpenAI Service provides access to
OpenAI's powerful large language models such
as ChatGPT, GPT, Codex, and Embeddings
models. These models enable various natural
language processing (NLP) solutions to
understand, converse, and generate content.
Users can access the service through REST APIs,
SDKs, and Azure OpenAI Studio.
Page | 7
Practice exams
Those are practice exams and not dumps. I do not encourage dumps as they ruin the certification
value for everyone.
What’s inside:
This guide is divided up into the following sections and is also part of the exam:
Feel free to join our Facebook Azure Study Group, or check out the other Azure courses on Udemy.
Errors and suggestions can also be reported in the Azure Group on Facebook.
Thank you,
Page | 8
Contents
Introduction............................................................................................................................................. 1
About the exam ....................................................................................................................................... 1
Plan and Manage an Azure AI Solution (25-30%).................................................................................. 13
Select the appropriate Azure AI service ............................................................................................ 13
Select the appropriate service for a vision solution ...................................................................... 13
Select the appropriate service for a language analysis solution ................................................... 13
Select the appropriate Service for a decision support solution .................................................... 13
Select the appropriate service for a speech solution .................................................................... 13
Select the appropriate Applied AI services ................................................................................... 13
Plan and configure security for Azure AI services ............................................................................. 14
Manage account keys .................................................................................................................... 14
Manage authentication for a resource.......................................................................................... 14
Secure Cognitive Services by using Azure Virtual Network ........................................................... 14
Plan for a solution that meets responsible AI principles ............................................................... 14
Create and manage an Azure AI service ............................................................................................ 14
Create an Azure AI resource .......................................................................................................... 14
Configure diagnostic logging ......................................................................................................... 14
Manage costs for Azure AI services ............................................................................................... 14
Monitor an Azure AI resource ....................................................................................................... 14
Deploy Azure AI services ................................................................................................................... 14
Determine a default endpoint for a service .................................................................................. 14
Create a resource by using the Azure portal ................................................................................. 15
Integrate Azure AI services into a continuous integration/continuous deployment (CI/CD)
pipeline .......................................................................................................................................... 15
Plan a container deployment ........................................................................................................ 15
Implement prebuilt containers in a connected environment ....................................................... 15
Create solutions to detect anomalies and improve content............................................................. 15
Create a solution that uses Anomaly Detector, part of Cognitive Services .................................. 15
Create a solution that uses Azure Content Moderator, part of Cognitive Services ...................... 15
Create a solution that uses Personalizer, part of Cognitive Services ............................................ 15
Create a solution that uses Azure Metrics Advisor, part of Azure Applied AI Services................. 15
Create a solution that uses Azure Immersive Reader, part of Azure Applied AI Services ............ 15
Implement image and video processing solutions (15–20%)................................................................ 15
Analyze images .................................................................................................................................. 15
Select appropriate visual features to meet image processing requirements ............................... 15
Page | 9
Create an image processing request to include appropriate image analysis features ................. 15
Interpret image processing responses .......................................................................................... 15
Extract text from images ................................................................................................................... 16
Build and optimize a custom model for Azure Form Recognizer .................................................. 16
Implement image classification and object detection by using the Custom Vision service, part of
Azure Cognitive Services ............................................................................................................... 16
Choose between image classification and object detection models ............................................ 16
Specify model configuration options, including category, version, and compact ........................ 16
Label images .................................................................................................................................. 16
Train custom image models, including classifiers and detectors .................................................. 16
Manage training iterations ............................................................................................................ 16
Evaluate model metrics ................................................................................................................. 17
Publish a trained iteration of a model........................................................................................... 17
Export a model to run on a specific target .................................................................................... 17
Implement a Custom Vision model as a Docker container ........................................................... 17
Interpret model responses ............................................................................................................ 17
Analyze video by using Azure Video Analyzer for Media (formerly Video ........................................ 17
Indexer) ............................................................................................................................................. 17
Process a video by using Azure Video Indexer .............................................................................. 17
Extract insights from a video or live stream by using Azure Video Indexer .................................. 17
Implement content moderation by using Azure Video Indexer .................................................... 17
Integrate a custom language model into Azure Video Indexer..................................................... 18
Implement Natural Language Processing Solutions (20-30%) .............................................................. 18
Analyze text ....................................................................................................................................... 18
Retrieve and process key phrases ................................................................................................. 18
Retrieve and process entities ........................................................................................................ 18
Retrieve and process sentiment .................................................................................................... 18
Detect the language used in text .................................................................................................. 18
Detect personally identifiable information (PII) ............................................................................ 18
Process speech .................................................................................................................................. 18
Implement and customize text-to-speech .................................................................................... 18
Implement and customize speech-to-text .................................................................................... 18
Improve text-to-speech by using SSML and Custom Neural Voice ............................................... 19
Improve speech-to-text by using phrase lists and Custom Speech............................................... 19
Implement intent recognition ....................................................................................................... 19
Implement keyword recognition ................................................................................................... 19
Page | 10
Translate language ............................................................................................................................ 19
Translate text and documents by using the Translator service .................................................... 19
Implement custom translation, including training, improving, and publishing a custom model . 19
Translate speech-to-speech by using the Speech service ............................................................. 19
Translate speech-to-text by using the Speech service .................................................................. 19
Translate to multiple languages simultaneously ........................................................................... 19
Build and manage a language understanding model ........................................................................ 20
Create intents and add utterances ................................................................................................ 20
Create entities ............................................................................................................................... 20
Train, evaluate, deploy, and test a language understanding model ............................................. 20
Optimize a Language Understanding (LUIS) model ....................................................................... 20
Integrate multiple language service models by using Orchestrator ............................................. 20
Import and export language understanding models..................................................................... 20
Create a Questions Answering solution ............................................................................................ 20
Create a question answering project ............................................................................................ 20
Add question-and-answer pairs manually..................................................................................... 20
Import sources............................................................................................................................... 20
Train and test a knowledge base ................................................................................................... 21
Publish a knowledge base ............................................................................................................. 21
Create a multi-turn conversation .................................................................................................. 21
Add alternate phrasing .................................................................................................................. 21
Add chit-chat to a knowledge base ............................................................................................... 21
Export a knowledge base .............................................................................................................. 21
Create a multi-language question answering solution.................................................................. 21
Create a multi-domain question answering solution .................................................................... 21
Use metadata for question-and-answer pairs .............................................................................. 21
Implement Knowledge Mining Solutions (5-10%) ................................................................................. 21
Implement a Cognitive Search solution ............................................................................................ 21
Create data sources ....................................................................................................................... 21
Define an index.............................................................................................................................. 21
Create and run an indexer ............................................................................................................. 21
Query an index, including syntax, sorting, filtering, and wildcards .............................................. 22
Apply AI enrichment skills to an indexer pipeline ............................................................................. 22
Attach a Cognitive Services account to a skillset .......................................................................... 22
Select and include built-in skills for documents ............................................................................ 22
Implement custom skills and include them in a skillset ................................................................ 22
Page | 11
Implement incremental enrichment ............................................................................................. 22
Implement Conversational AI Solutions (15-20%) ................................................................................ 22
Design and implement conversation flow......................................................................................... 22
Design conversation logic for a bot ............................................................................................... 22
Choose appropriate activity handlers, dialogs or topics, triggers, and state handling for a bot .. 22
Build a conversational bot ................................................................................................................. 22
Create a bot from a template ........................................................................................................ 22
Create a bot from scratch.............................................................................................................. 22
Implement channel-specific logic .................................................................................................. 23
Implement Adaptive Cards ............................................................................................................ 23
Implement multi-language support in a bot ................................................................................. 23
Implement multi-step conversations ............................................................................................ 23
Manage state for a bot .................................................................................................................. 23
Integrate Cognitive Services into a bot, including question answering, language understanding,
and Speech service ........................................................................................................................ 23
Page | 12
Plan and Manage an Azure AI Solution (25-30%)
Select the appropriate Azure AI service
Select the appropriate service for a vision solution
• Choosing a cognitive services technology - Azure Architecture Center | Microsoft Docs
• What are Azure Cognitive Services? - Azure Cognitive Services | Microsoft Docs
o What is Computer Vision? - Azure Cognitive Services | Microsoft Docs
o What is Custom Vision? - Azure Cognitive Services | Microsoft Docs
o What is the Azure Face service? - Azure Cognitive Services | Microsoft Docs
o What is Form Recognizer? - Azure Cognitive Services | Microsoft Docs
o What is Azure Video Indexer? - Azure Video Indexer | Microsoft Learn
Page | 13
Plan and configure security for Azure AI services
Manage account keys
• Create a Cognitive Services resource in the Azure portal - Azure Cognitive Services |
Microsoft Docs
• az cognitiveservices account keys | Microsoft Docs
• What’s New? A Single Key for Cognitive Services | AI Show | Channel 9 (msdn.com)
Page | 14
Create a resource by using the Azure portal
• Create a Cognitive Services resource in the Azure portal - Azure Cognitive Services |
Microsoft Learn
• How-to - Create a resource and deploy a model using Azure OpenAI Service - Azure OpenAI |
Microsoft Learn
• Create workspace resources - Azure Machine Learning | Microsoft Learn
Create a solution that uses Azure Content Moderator, part of Cognitive Services
• What is Anomaly Detector? - Azure Cognitive Services | Microsoft Learn
Create a solution that uses Azure Metrics Advisor, part of Azure Applied AI Services
• What is the Azure Metrics Advisor service? - Azure Applied AI Services | Microsoft Learn
Create a solution that uses Azure Immersive Reader, part of Azure Applied AI Services
• What is Azure Immersive Reader? - Azure Applied AI Services | Microsoft Learn
Page | 15
Extract text from images
Extract text from images or PDFs by using the Computer Vision service
• Cognitive Services APIs Reference (microsoft.com)
• What is Optical character recognition? - Azure Cognitive Services | Microsoft Docs
Implement image classification and object detection by using the Custom Vision
service, part of Azure Cognitive Services
Choose between image classification and object detection models
• Object Detection vs Image Classification: Simple Comparision - KiKaBeN
• Images Classification and Object Detection Metrics (analyticsvidhya.com)
Label images
• Label images faster with Smart Labeler - Azure Cognitive Services | Microsoft Docs
Analyze video by using Azure Video Analyzer for Media (formerly Video
Indexer)
Process a video by using Azure Video Indexer
• Sign up for Azure Video Indexer and upload your first video - Azure - Azure Video Indexer |
Microsoft Learn
• Upload and index videos with Azure Video Indexer using the Video Indexer website - Azure
Video Indexer | Microsoft Learn
Extract insights from a video or live stream by using Azure Video Indexer
• Azure Video Indexer insights overview - Azure Video Indexer | Microsoft Learn
• Video Indexer - Unlock Insights from your video | AI Show | Channel 9 (msdn.com)
• Live stream analysis using Video Indexer - Azure Media Services | Microsoft Docs
Page | 17
Integrate a custom language model into Azure Video Indexer
• Customize a Language model with Azure Video Indexer API - Azure Video Indexer | Microsoft
Learn
• azure-docs/articles/azure-video-indexer/customize-language-model-with-website.md at
main · MicrosoftDocs/azure-docs · GitHub
Process speech
Implement and customize text-to-speech
• Text-to-speech overview - Speech service - Azure Cognitive Services | Microsoft Docs
• Text-to-speech quickstart - Speech service - Azure Cognitive Services | Microsoft Docs
• Implement custom speech-to-text solutions that use AI - Azure Architecture Center |
Microsoft Learn
Page | 18
Improve text-to-speech by using SSML and Custom Neural Voice
• Custom Neural Voice overview - Speech service - Azure Cognitive Services | Microsoft Learn
• Speech Synthesis Markup Language (SSML) overview - Speech service - Azure Cognitive
Services | Microsoft Learn
• Voice and sound with Speech Synthesis Markup Language (SSML) - Speech service - Azure
Cognitive Services | Microsoft Learn
Translate language
Translate text and documents by using the Translator service
• Tutorial: Create a translation app with WPF, C# - Translator - Azure Cognitive Services |
Microsoft Docs
Page | 19
Build and manage a language understanding model
Create intents and add utterances
• Add intents - LUIS - Azure Cognitive Services | Microsoft Docs
• Intents and entities - LUIS - Azure Cognitive Services | Microsoft Docs
• Entity types - LUIS - Azure Cognitive Services | Microsoft Docs
• Add entities - LUIS - Azure Cognitive Services | Microsoft Docs
• Good example utterances - LUIS - Azure Cognitive Services | Microsoft Docs
Create entities
• How to use entities in LUIS - Azure Cognitive Services | Microsoft Learn
• Entities - Azure Cognitive Services | Microsoft Learn
Train, evaluate, deploy, and test a language understanding model
• How to train and evaluate models in Conversational Language Understanding - Azure
Cognitive Services | Microsoft Learn
• How to deploy a model for conversational language understanding - Azure Cognitive Services
| Microsoft Learn
• How to use train and test - Azure Cognitive Services | Microsoft Learn
Import sources
• Export/import/refresh - Azure Cognitive Services | Microsoft Learn
• Manage projects - question answering - Azure Cognitive Services | Microsoft Learn
Page | 20
Train and test a knowledge base
• Quickstart: Create, train, and publish knowledge base - QnA Maker - Azure Cognitive Services
| Microsoft Learn
Define an index
• Create an index - Azure Cognitive Search | Microsoft Docs
Page | 21
Query an index, including syntax, sorting, filtering, and wildcards
• Query types - Azure Cognitive Search | Microsoft Docs
Manage knowledge store projections, including file, object, and table projections
• Projection concepts - Azure Cognitive Search | Microsoft Learn
• Define projections - Azure Cognitive Search | Microsoft Learn
Apply AI enrichment skills to an indexer pipeline
Attach a Cognitive Services account to a skillset
• Attach Cognitive Services to a skillset - Azure Cognitive Search | Microsoft Docs
Choose appropriate activity handlers, dialogs or topics, triggers, and state handling for
a bot
• Create conversations with dialogs and Bot Framework Composer | Microsoft Learn
• Triggers in Bot Framework Composer | Microsoft Learn
• Bot activity handlers - Teams | Microsoft Learn
Page | 22
Implement activity handlers, dialogs or topics, and triggers
• Event-driven conversations and activity handlers - Bot Service | Microsoft Learn
• Events and triggers for adaptive dialogs - Bot Service | Microsoft Learn
Implement channel-specific logic
• Implement channel-specific functionality using REST API - Bot Service | Microsoft Learn
• Implement channel-specific functionality in Bot Framework SDK - Bot Service | Microsoft
Learn
Page | 23