AI-102 Exam Study Guide (Designing And Implementing A Microsoft Azure AI Solution)
You can access AI-102 Exam Microsoft official page here
Preparing for AI-102 Designing and Implementing an Azure AI Solution Certificate exam? Don’t know where to start? This post is the AI-102 Certificate Study Guide (with links to each exam objective).
I have curated a list of articles from Microsoft documentation for each objective of the AI-102 exam. I hope this article will help you to prepare for the AI-102 Certification exam. Also, please share the post within your circles so it helps them to prepare for the exam.
Skills Measured
- Plan and Manage an Azure Cognitive Services Solution (15-20%)
- Implement Computer Vision Solutions (20-25%)
- Implement Natural Language Processing Solutions (20-25%)
- Implement Knowledge Mining Solutions (15-20%)
- Implement Conversational AI Solutions (15-20%)
AI-102 Exam Free Study Guide
For each test objective, I’ve compiled a thorough collection of articles from Microsoft documentation. Please feel free to forward this page to your friends and coworkers in order to assist them in preparing for the test .
Plan and Manage an Azure Cognitive Services Solution (15-20%)
Select the Appropriate Cognitive Services Resource
- Select the appropriate cognitive service for a vision solution
- Choosing a Microsoft cognitive services technology
- Azure Cognitive Services Vision APIs
- Computer Vision
- Custom Vision
- Azure Face service
- Form Recognizer
- Azure Media Services Video Indexer
- Select the appropriate cognitive service for a language analysis solution
- Azure Cognitive Services Language APIs
- Language Understanding (LUIS)
- QnA maker service
- Text mining and analysis with the Text Analytics API
- Microsoft Translator service
- Immersive Reader
- Select the appropriate cognitive Service for a decision support solution
- Azure Cognitive Services Decision APIs
- Anomaly Detector API
- Azure Content Moderator
- Metrics Advisor service
- Personalizer
- Select the appropriate cognitive service for a speech solution
- Azure Cognitive Services Speech APIs
- Speech service
- Speech-to-text
- Text-to-speech
- Speech translation
- Intent recognition
- Speaker Recognition
Plan and Configure Security for a Cognitive Services Solution
- Manage Cognitive Services account keys
- Get the keys for your resource
- CLI command to manage Azure Cognitive Services accounts
- What’s new? A single key for Cognitive Services
- Manage authentication for a resource
- Authenticate requests to Azure Cognitive Services
- Secure Cognitive Services by using Azure Virtual Network
- Configure Azure Cognitive Services virtual networks
- Plan for a solution that meets responsible AI principles
- Responsible AI principles from Microsoft
- Build powerful & responsible AI solutions with Azure
Create a Cognitive Services Resource
- Create a Cognitive Services resource
- Create a Cognitive Services resource using the Azure portal
- Create a Cognitive Services resource using the Azure CLI
- Configure diagnostic logging for a Cognitive Services resource
- Enable diagnostic logging for Azure Cognitive Services
- Manage Cognitive Services costs
- Plan and manage costs for Azure Cognitive Services
- Monitor a cognitive service
- Monitor operations and activity of Azure Cognitive Search
- Implement a privacy policy in Cognitive Services
- Data & privacy for Spatial Analysis
Plan and Implement Cognitive Services Containers
- Identify when to deploy to a container
- Azure Cognitive Services containers
- Azure Cognitive Services containers (FAQ)
- Containerize Cognitive Services (including Computer Vision API, Face API, Text Analytics, Speech, Form Recognizer)
- Install Read OCR Docker containers
- Face containers (Install & run)
- Install & run Text Analytics containers
- Run and install Docker containers for the Speech service APIs
- Install and run Form Recognizer containers
- Containerize other Cognitive Services
- Install and run Docker containers for LUIS
- Docker containers for the Anomaly Detector API
Implement Computer Vision Solutions (20-25%)
Analyze Images by Using the Computer Vision API
- Retrieve image descriptions and tags by using the Computer Vision API
- Describe images with a human-readable language
- Applying content tags to images
- Identify landmarks and celebrities by using the Computer Vision API
- Detect domain-specific content
- Detect brands in images by using the Computer Vision API
- Detect popular brands in images
- Moderate content in images by using the Computer Vision API
- Detect adult content
- Generate thumbnails by using the Computer Vision API
- Generate smart-cropped thumbnails with Computer Vision
Extract Text from Images
- Extract text from images by using the OCR API
- OCR API
- Optical Character Recognition (OCR)
- Extract text from images or PDFs by using the Read API
- Read API
- Convert handwritten text by using Ink Recognizer
- Recognize digital ink with the Ink Recognizer REST API
- Extract information from forms or receipts by using the pre-built receipt model in Form Recognizer
- Form Recognizer prebuilt receipt model
- Build and optimize a custom model for Form Recognizer
- Build a training data set for a custom model
- Train a custom model
- Manage custom models
Extract Facial Information from Images
- Detect faces in an image by using the Face API
- Get face detection data
- Recognize faces in an image by using the Face API
- Quickstart: Use the Face client library
- Configure persons and person groups
- Person Group – Create
- Create a new person in a person group
- Add faces to a PersonGroup
- Analyze facial attributes by using the Face API
- Facial attributes
- Get started with Face analysis on Azure
- Analyze faces with the Face service
- Match similar faces by using the Face API
- Face – Find Similar
Implement Image Classification by Using the Custom Vision Service
- Label images by using the Computer Vision Portal
- Label images faster with Smart Labeler
- Train a custom image classification model in the Custom Vision Portal
- Build a classifier with the Custom Vision website
- Train a custom image classification model by using the SDK
- Create an image classification project with the Custom Vision client library
- Manage model iterations
- Manage training iterations
- Use your model with the prediction API
- Evaluate classification model metrics
- Evaluate the classifier
- Publish a trained iteration of a model
- Publish your trained iteration
- Export a model in an appropriate format for a specific target
- Export your model for use with mobile devices
- Consume a classification model from a client application
- Consume an AML model deployed as a web service
- Deploy image classification custom models to containers
- Perform image classification with Custom Vision Service
Implement an Object Detection Solution by Using the Custom Vision Service
- Label images with bounding boxes by using the Computer Vision Portal
- Tag images & specify bounding boxes for object detection
- Train a custom object detection model by using the Custom Vision Portal
- Build an object detector with the Custom Vision website
- Train a custom object detection model by using the SDK
- Create an object detection project with the Custom Vision library
- Manage model iterations
- Manage training iterations
- Evaluate object detection model metrics
- Evaluate the detector
- Publish a trained iteration of a model
- Publish the current iteration
- Consume an object detection model from a client application
- Use the object detection model in Power Automate
- Deploy custom object detection models to containers
- Azure Cognitive Services containers
Analyze Video by Using Video Indexer
- Process a video
- Upload and index your videos
- Extract insights from a video
- Video Indexer – Unlock insights from your video
- Moderate content in a video
- Video moderation with Content Moderator
- Customize the Brands model used by Video Indexer
- Customize a Brands model with the Video Indexer website
- Customize the Language model used by Video Indexer by using the Custom Speech Service
- Customize a Language model with the Video Indexer website
- Customize the Person model used by Video Indexer
- Customize a Person model with the Video Indexer website
- Extract insights from a live stream of video data
- Live stream analysis with Video Indexer
- Use Video Indexer to process a live stream & display data
Implement Natural Language Processing Solutions (20-25%)
Analyze Text by Using the Text Analytics Service
- Retrieve and process key phrases
- How to extract key phrases using Text Analytics?
- Retrieve and process entity information (people, places, URLs, etc.)
- Supported entity categories Text Analytics
- How to use Named Entity Recognition in Text Analytics?
- Retrieve and process sentiment
- Sentiment analysis on streaming data using Databricks
- Analyze sentiment & synthesize speech
- Detect the language used in text
- Detect language with Text Analytics
Manage Speech by Using the Speech Service
- Implement text-to-speech
- What is text-to-speech?
- Get started with text-to-speech
- Customize text-to-speech
- Get started with Custom Voice
- Create a Custom Voice
- Implement speech-to-text
- What is speech-to-text?
- Get started with speech-to-text
- Improve speech-to-text accuracy
- Improve accuracy with tenant models
Translate Language
- Translate text by using the Translator service
- Create a translation app with WPF
- Translate speech-to-speech by using the Speech service
- Get started with speech translation
- Translate speech-to-text by using the Speech service
- Get started with speech-to-text
Build an Initial Language Model by Using Language Understanding Service (LUIS)
- Create intents and entities based on a schema, and then add utterances
- Intents in your LUIS app
- Add intents to determine user intention of utterances
- Extract data with entities
- Add entities to extract data
- Understand what good utterances are for your LUIS app
- Create complex hierarchical entities
- Using Hierarchical Entities in Microsoft’s LUIS for NLP
- Hierarchical Entities in LUIS
- Use this instead of roles
- Add contributors to your app
- Train and deploy a model
- Train your active version of the LUIS app
- Deploy an app in the LUIS portal
Iterate on and Optimize a Language Model by Using LUIS
- Implement phrase lists
- Create a phrase list for a concept
- Add phrase list as a feature
- Using Phrase Lists in Microsoft’s LUIS for NLP
- Implement a model as a feature (i.e. prebuilt entities)
- Model as a feature
- A model as a feature helps another model
- Effective prebuilt entities
- Add a prebuilt entity
- Prebuilt entities
- Manage punctuation and diacritics
- Punctuation normalization
- What are Diacritics?
- Diacritics normalization
- Implement active learning
- Concepts for enabling active learning
- Log user queries to enable active learning
- Monitor and correct data imbalances
- Review data imbalance
- Evaluate the performance of your LUIS app
- Implement patterns
- Patterns improve prediction accuracy
- Add patterns to improve predictions
Manage a LUIS Model
- Manage collaborators
- Collaborate with others – LUIS
- How do I give collaborators access to LUIS?
- Manage versioning
- Manage versions
- Application and version settings
- Publish a model through the portal or in a container
- Publish your app to a staging or production endpoint
- Install and run Docker containers for LUIS
- Export a LUIS package
- Export packaged app from LUIS
- Export your customer data in (LUIS) in Cognitive Services
- Export a version
- Deploy a LUIS package to a container
- Deploy LUIS on Azure Container instances
- Deploy LUIS service as a Docker image
- Integrate Bot Framework (LUDown) to run outside of the LUIS portal
- LUDown
- Creating a LUIS Service with LUDown and the CLI
Implement Knowledge Mining Solutions (15-20%)
Implement a Cognitive Search Solution
- Create data sources
- Create Data Source (Cognitive Search REST API)
- Define an index
- Create a basic search index in Azure Cognitive Search
- Create and run an indexer
- Create a search indexer
- Run the indexer
- Query an index
- Querying in Azure Cognitive Search
- Configure an index to support autocomplete and autosuggest
- Add autocomplete to client apps using Azure Cognitive Search
- Create a suggester to enable autocomplete
- Boost results based on relevance
- Boost search rank using scoring profiles
- Implement synonyms
- Synonyms in Azure Cognitive Search
Implement an Enrichment Pipeline
- Attach a Cognitive Services account to a skillset
- Attach a Cognitive Services resource to a skillset
- Select and include built-in skills for documents
- Built-in cognitive skills for text & image processing
- Document Extraction cognitive skill
- Implement custom skills and include them in a skillset
- Add a custom skill to an Azure Cognitive Search enrichment pipeline
Implement a Knowledge Store
- Define file projections
- Projecting to file
- Define object projections
- Projecting to objects
- Define table projections
- Projecting to tables
- Query projections
- Knowledge store “projections” in Azure Cognitive Search
Manage a Cognitive Search Solution
- Provision Cognitive Search
- Create an Azure Cognitive Search service
- Configure security for Cognitive Search
- Security in Azure Cognitive Search
- Configure keys for data encryption in Azure Cognitive Search
- Configure IP firewall for Azure Cognitive Search
- Configure scalability for Cognitive Search
- Scale for performance on Azure Cognitive Search
Manage Indexing
- Manage re-indexing
- Update index
- Rebuild indexes
- Rebuild an index in Azure Cognitive Search
- Schedule indexing
- Schedule indexers in Azure Cognitive Search
- Monitor indexing
- Monitor Azure Cognitive Search indexer status
- Implement incremental indexing
- Incremental enrichment and caching
- Manage concurrency
- Manage concurrency in Azure Cognitive Search
- Push data to an index
- Pushing data to an index
- Troubleshoot indexing for a pipeline
- Troubleshooting common indexer issues
Implement Conversational AI Solutions (15-20%)
Create a Knowledge Base by Using QnA Maker
- Create a QnA Maker service
- Create a new QnA Maker service
- Create a knowledge base
- Create your QnA Maker knowledge base
- Import a knowledge base
- Migrate a knowledge base from QnA Maker (Step 6)
- Train and test a knowledge base
- Train the knowledge base
- How to test a knowledge base?
- Publish a knowledge base
- Publish the knowledge base
- Create a multi-turn conversation
- Use follow-up prompts to create multiple turns of a conversation
- Add alternate phrasing
- Add alternate questions
- Add additional alternatively-phrased questions
- Get suggested alternate questions
- Add chit-chat to a knowledge base
- Add Chit-chat to a knowledge base
- Export a knowledge base
- Migrate a knowledge base using export-import
- Add active learning to a knowledge base
- Use active learning to improve your knowledge base
- Manage collaborators
- Collaborate with other authors and editors
Design and Implement Conversation Flow
- Design conversation logic for a bot
- Design and control conversation flow
- How to design a conversation for a chatbot?
- Create and evaluate *.chat file conversations by using the Bot Framework Emulator
- Debug your bot using transcript files
- Add language generation for a response
- Language generation
- Use language generation templates in your bot
- Design and implement adaptive cards
- Adaptive Cards Designer SDK
- Designing Adaptive Cards for your Microsoft Teams app
Create a Bot by Using the Bot Framework SDK
- Implement dialogs
- Dialogs library
- Use dialogs within a skill
- Maintain state
- Managing state
- Implement logging for a bot conversation
- Add trace activities to your bot
- Implement a prompt for user input
- Create your own prompts to gather user input
- Add and review bot telemetry
- Add telemetry to your bot
- Analyze your bot’s telemetry data
- Implement a bot-to-human handoff
- Transition conversations from bot to human
- Bot to Human Handoff in Node.js
- Troubleshoot a conversational bot
- Troubleshoot general
- Add a custom middleware for processing user messages
- Middleware
- Manage identity and authentication
- Bot Framework authentication basics
- Add authentication to a bot
- Identity providers
- Implement channel-specific logic
- Implement channel-specific functionality
- Channel-specific functionality with the Bot Connector API
- Publish a bot
- Deploy a basic bot
Create a Bot by Using the Bot Framework Composer
- Implement dialogs
- Dialogs in Bot Framework Composer
- Maintain state
- Conversation flow and memory
- Implement logging for a bot conversation
- Conversation logging with the Composer
- Implement prompts for user input
- Ask for user input
- Troubleshoot a conversational bot
- Unable to publish my bot built with Bot Framework Composer
- Test a bot by using the Bot Framework Emulator
- Debug with the Emulator
- Publish a bot
- Publish your bot to Azure
Integrate Cognitive Services into a Bot
- Integrate a QnA Maker service
- Use QnA Maker to answer questions
- Add a QnA Maker knowledge base to your bot
- Integrate a LUIS service
- Add natural language understanding to your bot
- Integrate a Speech service
- Add speech to messages with the Bot Connector API
- Voice-enable your bot using the Speech SDK
- Integrate Dispatch for multiple language model
- Use multiple LUIS and QnA models
- Manage keys in app settings file
- Update the settings file
This brings us to the end of AI-102 Study Guide
Follow Me to Receive Updates on AI-102 Exam
Share the AI-102 Study Guide in Your Network
Share on facebook
Share on twitter
Share on linkedin
