Preparation Guide for Microsoft AI-100 Designing and Implementing an Azure AI Solution – Azure AI Engineer Associate Certification
I just get my AI-100 Microsoft Azure AI Engineer Associate Certification and it is time now to share my preparation notes for those who are interested to pass the “AI-100 Designing and Implementing an Azure AI Solution” exam and get certified too.
This article is just one another preparation guide to Microsoft exam AI-100 (but probably the most complete). I hope it will be useful 🙂

Even you don’t plan to take the exam, all this content is really interesting to read and understand if you want to discover and improve your knowledge on Artificial Intelligence on Azure. You will find below more than 300 slides, good articles, nice courses and excellent tutorials.
Audience Profile : Candidates for this exam analyze the requirements for AI solutions,recommends appropriate tools and technologies, and implements solutions that meet scalability and performance requirements.
Before starting studying, you must know very well what this certification is about and what are the prerequisites.
The topics included in this exam are the following :
- Analyze solution requirements(25-30%)
- Design AI solutions(40-45%)
- Implement and monitor AI solutions(25-30%)
More details : https://www.microsoft.com/en-us/learning/exam-ai-100.aspx
Update (june 2019) Official list of subjects in the AI-100 exam (you must read it !!)
https://query.prod.cms.rt.microsoft.com/cms/api/am/binary/RE36ywa
Module 0 – AI Basics
Different job in AI and Data Science
https://medium.com/hackernoon/top-10-roles-for-your-data-science-team-e7f05d90d961
Module 1 – Analyze solution requirement
Part 1 – Recommend Cognitive Services APIs to meet business requirements
Choosing a Microsoft cognitive services technology
https://docs.microsoft.com/en-us/azure/architecture/data-guide/technology-choices/cognitive-services
Microsoft Azure Cognitive Services: The Big Picture
https://app.pluralsight.com/library/courses/microsoft-azure-cognitive-services-big-picture
Microsoft Azure Cognitive Services: Custom Vision API (Excellent course by
Andy Butland)
https://app.pluralsight.com/player?course=microsoft-azure-cognitive-services-custom-vision-api
Precision versus Recall
https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-understand-automated-ml#precision-recall-chart
Performance measures in Azure ML: Accuracy, Precision, Recall and F1 Score
https://blogs.msdn.microsoft.com/andreasderuiter/2015/02/09/performance-measures-in-azure-ml-accuracy-precision-recall-and-f1-score/
Part 2 – Map security requirements to tools, technologies, and processes
Bot Service Compliance
https://docs.microsoft.com/en-us/azure/bot-service/bot-service-compliance?view=azure-bot-service-4.0
Part 3 – Select the software, services, and storage required to support a solution
Machine learning at scale
https://docs.microsoft.com/en-us/azure/architecture/data-guide/big-data/machine-learning-at-scale
Designing an Intelligent Edge in Microsoft Azure (By Jared Rhodes)
https://app.pluralsight.com/library/courses/microsoft-azure-intelligent-edge-designing
Azure IoT reference architecture
https://docs.microsoft.com/en-us/azure/architecture/reference-architectures/iot/index
Azure IoT reference architecture (Detailed PDF)
https://aka.ms/iotrefarchitecture
Choosing a real-time message ingestion technology in Azure
https://docs.microsoft.com/en-us/azure/architecture/data-guide/technology-choices/real-time-ingestion
What are your options for real-time message ingestion?
- Azure Event Hub : https://docs.microsoft.com/en-us/azure/event-hubs/
- Kafka : https://docs.microsoft.com/en-us/azure/hdinsight/kafka/apache-kafka-introduction
- IoT Hub : https://docs.microsoft.com/en-us/azure/iot-hub/
Connecting IoT Devices to Azure: IoT Hub and Event Hubs
https://docs.microsoft.com/en-us/azure/iot-hub/iot-hub-compare-event-hubs
Azure Databricks
https://docs.microsoft.com/en-us/azure/azure-databricks/what-is-azure-databricks
Tutorial: Sentiment analysis on streaming data using Azure Databricks
https://docs.microsoft.com/en-us/azure/azure-databricks/databricks-sentiment-analysis-cognitive-services
Build a real-time recommendation API on Azure
https://docs.microsoft.com/en-us/azure/architecture/reference-architectures/ai/real-time-recommendation
Identify storage required to store logging, bot state data, and Cognitive Services output
https://docs.microsoft.com/en-us/azure/architecture/reference-architectures/ai/conversational-bot
Choose the right data store
https://docs.microsoft.com/en-us/azure/architecture/guide/technology-choices/data-store-overview
Data Warehouse
https://azure.microsoft.com/services/sql-data-warehouse/
Azure Data Lake Analytics
https://docs.microsoft.com/en-us/azure/data-lake-analytics/data-lake-analytics-overview
Azure Data Lake Store
https://docs.microsoft.com/en-us/azure/storage/blobs/data-lake-storage-introduction
Cosmos DB Global Distribution:
https://docs.microsoft.com/en-us/azure/cosmos-db/distribute-data-globally
==> Microsoft recommend CosmosDB for warm path storage (Warm path storage holds data that must be available immediately from device for reporting and visualization)
Enable edge intelligence with Azure IoT Edge (excellent introduction video to Azure IoT Edge)
https://channel9.msdn.com/events/Connect/2017/T253
Install the Azure IoT Edge runtime on Debian-based Linux system
https://docs.microsoft.com/en-us/azure/iot-edge/how-to-install-iot-edge-linux
Deploy Azure IoT Edge modules from the Azure portal
https://docs.microsoft.com/en-us/azure/iot-edge/how-to-deploy-modules-portal
Creating an image recognition solution with Azure IoT Edge and Azure Cognitive Services
https://dev.to/azure/creating-an-image-recognition-solution-with-azure-iot-edge-and-azure-cognitive-services-4n5i
Microsoft IoT edge built-in modules
https://azuremarketplace.microsoft.com/en-us/marketplace/apps/category/internet-of-things?search=iot&page=1&filters=microsoft
Azure Stream Analytics
https://azure.microsoft.com/en-us/services/stream-analytics/
Another option for stream analytics is Apache Spark in Azure Databrick or HDInsigt, or Apache Storm in HDInsight
Apache Storm
https://intellipaat.com/blog/what-is-apache-storm/
https://docs.microsoft.com/en-us/azure/hdinsight/storm/apache-storm-overview
https://docs.microsoft.com/en-us/azure/hdinsight/spark/apache-spark-overview
https://docs.microsoft.com/bs-latn-ba/azure/hdinsight/interactive-query/apache-interactive-query-get-started
Anomaly detection using machine learning in Azure Stream Analytics
https://www.youtube.com/watch?v=Ra8HhBLdzHE
Built-in ML based Anomaly Detection
-> Un-supervised learning models : Learn from the data it sees
Anomaly detection in Azure Stream Analytics
https://docs.microsoft.com/en-us/azure/stream-analytics/stream-analytics-machine-learning-anomaly-detection
Real-Time ML based Anomaly Detection in Azure Stream Analytics (same as above but demo with Raspberry Pi)
https://www.youtube.com/watch?v=qWxdL5gngaA
Anomaly Generator (Git)
https://aka.ms/ASAanomalyGenerator
Performing sentiment analysis by using Azure Stream Analytics and Azure Machine Learning Studio
https://docs.microsoft.com/en-us/azure/stream-analytics/stream-analytics-machine-learning-integration-tutorial
Real-time analytics on IoT Edge with Azure Stream Analytics
https://sec.ch9.ms/ch9/6959/5b904422-823a-49d7-8639-d5fbc80e6959/CONN17T157_high.mp4
Azure Stream Analytics now available on IoT Edge
http://aka.ms/ASAEdge
Module 2 – Design AI Solutions (40-45%)
Part 1 – Design solutions that include one or more pipelines
What is Azure Machine Learning
https://docs.microsoft.com/en-us/azure/machine-learning/service/overview-what-is-azure-ml
Tutorial: Predict automobile price with the visual interface
https://docs.microsoft.com/en-us/azure/machine-learning/service/ui-tutorial-automobile-price-train-score
Create and manage Azure Machine Learning service workspaces
https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-workspace
AI Pipelines
https://docs.microsoft.com/en-us/azure/machine-learning/service/concept-ml-pipelines
https://docs.microsoft.com/en-us/azure/machine-learning/service/concept-azure-machine-learning-architecture#pipeline
1-Import and clean data
2-Train a machine learning model
3-Score and evaluate a model
4- Deploy the trained model
Azure Machine Learning Pipeline
https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/machine-learning-pipelines
AML Samples:
https://github.com/Azure/MachineLearningNotebooks
Get Started with Azure Machine Learning
https://www.youtube.com/watch?v=GBDSBInvz08
How to use Notebooks with Azure Machine Learning workspace
https://www.youtube.com/watch?v=lCkYUHV86Mk
Choose a Compute target
https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-deploy-and-where#choose-a-compute-target
Deploy a model to an Azure Kubernetes Service cluster
https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-deploy-azure-kubernetes-service
Deploy a model using a custom Docker image
https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-deploy-custom-docker-image
Azure Data Factory
https://docs.microsoft.com/en-in/azure/data-factory/introduction
Data Science Virtual Machine :
- Data Science Virtual Machine : https://docs.microsoft.com/en-us/azure/machine-learning/data-science-virtual-machine/overview
- Geo AI Data Science Virtual Machine : https://docs.microsoft.com/en-us/azure/machine-learning/data-science-virtual-machine/geo-ai-dsvm-overview
- Deep Learning Virtual Machine
Part 2 – Design solutions that uses Cognitive Services
Cognitives Services Directory
https://azure.microsoft.com/en-gb/services/cognitive-services/directory/
Process images with the Computer Vision service (course 32 minutes with sandbox test environment + 3 knowledge questions)
https://docs.microsoft.com/en-us/learn/modules/create-computer-vision-service-to-classify-images/index
Classify images with the Microsoft Custom Vision Service (course 40 minutes)
https://docs.microsoft.com/en-us/learn/modules/classify-images-with-custom-vision-service/index
Develop solutions by using intelligent algorithms related to speech, natural language processing, Bing Search, and recommendations and decision making
Speech Service Documentation
https://docs.microsoft.com/en-gb/azure/cognitive-services/speech-service/
https://docs.microsoft.com/en-gb/azure/cognitive-services/speech-service/overview
Bing Web Search API Documentation
https://docs.microsoft.com/en-us/azure/cognitive-services/bing-web-search/
https://docs.microsoft.com/en-us/azure/cognitive-services/bing-web-search/overview
What is Custom Decision Service?
https://docs.microsoft.com/en-us/azure/cognitive-services/custom-decision-service/custom-decision-service-overview
Sample showing how to deploy a AI model from the Custom Vision service to a Raspberry Pi 3 device using Azure IoT Edge
https://github.com/Azure-Samples/Custom-vision-service-iot-edge-raspberry-pi
Part 3 – Design solutions that implement the Bot Framework
Building a bot
https://docs.microsoft.com/en-us/azure/bot-service/bot-service-overview-introduction?view=azure-bot-service-4.0
Bot Framework Emulator
https://github.com/microsoft/BotFramework-Emulator
Data sources for QnA Maker content
https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/concepts/data-sources-supported
Best practices of a QnA Maker knowledge base
https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/concepts/best-practices
LUIS (Language Understanding Intelligent Services)
https://www.luis.ai/
Entity types and their purposes in LUIS
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-concept-entity-types
Composite entity
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/reference-entity-composite
List entity
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/reference-entity-list
Enterprise-grade conversational bot
https://docs.microsoft.com/en-us/azure/architecture/reference-architectures/ai/conversational-bot
Part 4 – Design the compute infrastructure to support a solution.
What are field-programmable gate arrays (FPGA)
https://docs.microsoft.com/en-us/azure/machine-learning/service/concept-accelerate-with-fpgas
Inside the Microsoft FPGA-based configurable cloud
https://channel9.msdn.com/Events/Build/2017/B8063
Hyperscale hardware: ML at scale on top of Azure + FPGA
https://channel9.msdn.com/events/Build/2018/BRK3202
GPUs vs CPUs for deployment of deep learning models by Fidan Boylu Uz
https://azure.microsoft.com/en-us/blog/gpus-vs-cpus-for-deployment-of-deep-learning-models/
Reference architecture: Machine Learning model training with AKS
https://azure.microsoft.com/en-us/solutions/architecture/machine-learning-with-aks/
Deploy Deep Learning CNN on Kubernetes Cluster with GPUs – AML version
https://github.com/Microsoft/AKSDeploymentTutorialAML
Deploying Deep Learning Models on Kubernetes with GPUs
https://blogs.technet.microsoft.com/machinelearning/2018/04/19/deploying-deep-learning-models-on-kubernetes-with-gpus/
Part 5 – Design Data for Governance, compliance, integrity & security
Managing GDPR compliance on Azure BRK2091
https://www.youtube.com/watch?v=oF6d8fNqT3I
Module 3 – Implement and monitor AI solutions (25-30%)
Part 1 – Implement and AI Workflow
IoT Hub
AML Services
AML Sample
https://github.com/Azure/MachineLearningNotebooks
VS Code extension for Azure Machine Learning
https://marketplace.visualstudio.com/items?itemName=ms-toolsai.vscode-ai
Part 2 – Integrate AI services with solution components
Azure IoT reference architecture
https://docs.microsoft.com/en-us/azure/architecture/reference-architectures/iot/index
Add authentication to your bot via Azure Bot Service
https://docs.microsoft.com/en-us/azure/bot-service/bot-builder-authentication?view=azure-bot-service-4.0&tabs=aadv1%2Ccsharp%2Cbot-oauth
Part 3 – Monitor and Evaluate the AI environment
Overview of alerts in Microsoft Azure
https://docs.microsoft.com/en-us/azure/azure-monitor/platform/alerts-overview
Monitor your Azure Machine Learning models with Application Insights
https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-enable-app-insights
ML Processing Pipeline : Ingest -> Storage -> Analyze -> Interact
Add telemetry to your bot
https://docs.microsoft.com/en-us/azure/bot-service/bot-builder-telemetry?view=azure-bot-service-4.0
Bot analytics
https://docs.microsoft.com/en-us/azure/bot-service/bot-service-manage-analytics?view=azure-bot-service-4.0
Real-Time Analytics (architecture)
Image Classification (architecture)
Interactive Bot (architecture)
Azure AutoML
Hyperdrive ==> automates the tuning of hyperparameters by defining how to tweak each parameter and criteria and adding stopping conditions
Understand automated machine learning results
https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-understand-automated-ml
Other useful materials
Developing AI Models in Microsoft Azure (Excellent course by Sahil Malik)
https://app.pluralsight.com/player?course=microsoft-azure-ai-models-developing
Managing Microsoft Azure AI Solutions (Another excellent course by Sahil Malik)
https://app.pluralsight.com/library/courses/microsoft-azure-ai-solutions-managing
Microsoft Azure Developer: Creating and Integrating AI with Azure Services (Again an excellent course by Sahil Malik)
https://app.pluralsight.com/player?course=microsoft-azure-developer-creating-integrating-ai-services-update
AI-100: Designing and Implementing an Azure AI Solution — Study Guide
https://medium.com/@marioamendieta/ai-100-designing-and-implementing-an-azure-ai-solution-study-guide-f0065db01c83
MLOps Workshop
https://github.com/microsoft/MCW-ML-Ops
Microsoft Cloud Workshop library
https://microsoftcloudworkshop.com/
Creating an image recognition solution with Azure IoT Edge and Azure Cognitive Services
https://dev.to/azure/creating-an-image-recognition-solution-with-azure-iot-edge-and-azure-cognitive-services-4n5i
Be prepared for questions on :
- Azure Cognitives Services (a lot of questions)
- Azure AI + AKS + ACI
- Azure IoT Edge + Azure Stack + Azure DataBox Edge
- IoT Hub + EventBus
- Azure Storage
- Azure Stream Analytics
- Azure Functions + Azure Logic App
- LUIS
- Monitoring Apps & AI applications
- Azure Bot Service + QnA Maker + Cognitives Services
- Security (Authentication, Azure Key Vault)
Hope this study guide will be useful for you. Don’t hesitate to share, or post a comment or send me a message on Twitter @squastana or on LinkedIn
https://www.linkedin.com/in/stanislasquastana/
Last but not least, don’t forget to spend time on http://microsoft.com/learn where you can find additional materials to prepare your certification.
Pierre
Hi Stanislas, thank you 1000 times for this very supportive material. Keep the good work.
themis
Hi Stanislas ! Thanks a lot for your feedback. One question : you passed the AI100 after or before the modifications (of June, 25th) ?
squastana
After the modification. In august 19
Sahana Hegde
Thanks a lot for this info. It helped me to clear the exam.
Ryan
Hi Stanislas, does the exam contain any lab questions?
squastana
Yes, there is a lab now
sdfdf
I heard that the lab questions have an issue with the opening the VM. exam participants are unhappy with this. Microsoft has not yet fixed the issue.
squastana
Hi, Microsoft is aware of Labs issues. Now Labs are supposed to be at the end of exam. If labs have issues, they will not be included in final exam scoring. So don’t be stressed about that 🙂
squastana
Sometimes there are issues with labs. That is why now labs are at the end of exam. In case of issues with labs, scoring of exam will not include labs
Gagan
Hi Stanislas,
Thank you for preparing the exhaustive list for AI 100 exam preparation. I just clear AZ 203 exam last week and was planning to take AI 100 next. This would a good starting point for me.
Harsh Chawla
What a comprehensive list of resources to prepare for this certification. PPTs are really good especially the screenshots you have put in. Thanks a lot!
squastana
Thanks. Happy that my prep guide is usefull !!
Faj
Could you please help with an estimation regarding what’s the proportion of questions from the exam, related to the official instructor led course? Asking because in that course there is nothing related to IoT,AKS,Stream Analytics, Kafka and such things, that seem to fall more into the Azure Data Engineer certifications
squastana
I didn’t read or use the official instructor led course so I don’t know
Julian Sharp
You are correct that the official course and the learn material does not cover a large part of the exam, which is about how you use cognitive services with other Azure services. Stanislas’s summary of what to be prepared for is helpful but I would add big data to that list.
xacidev
Hi. Can anyone tell me what all are the types of questions asked i.e the exam format? I have heard there are mcqs, labs and case studies. What else? And what is one supposed to do in each of them e.g: what do we have to do in lab type of questions or case study questions or any other type of questions? Do we have to also code during the exam? If so then do we have access to the documentation or are we supposed to memorize all the libraries and their functions?
Data science course training institutes in Marthahalli
Very interesting to read this article.
cloud computing
very well written your articles i enjoyed to read your blogs keep write !