AI-100 Exam Study Guide (Designing and Implementing an Azure AI Solution)

AI-100 Designing & Implementing Azure AI Solution Certificate Study Guide-01

Preparing for AI-100 Designing and Implementing an Azure AI Solution Certificate exam? Don’t know where to start? This post is the AI-100 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-100 exam. I hope this article will help you to prepare for the AI-100 Certification exam. Also, please share the post within your circles so it helps them to prepare for the exam.

AI-100 Design an Azure AI Solution Online Course

AI-100 Azure AI Solution Practice Test and Lab

AI-100 Microsoft Azure AI Related Study Materials

Looking for AI-100 Dumps? Read This!

Using ai-100 exam dumps can get you permanently banned from taking any future Microsoft certificate exam. Read the FAQ page for more information. However, I strongly suggest you validate your understanding with practice questions.

Not Sure Which Exam Is Right for You?

Confused between AI-100 and DP-100? You are not alone. Read this blog post and choose the one that’s right for you!

AI-100 Sample Practice Exam Questions

To view other Azure Certificate Study Guides, click here

Full Disclosure: Some of the links in this post are affiliate links. I receive a commission when you purchase through them.

Analyze Solution Requirements (25-30%)

Recommend Cognitive Services APIs to Meet Business Requirements

Select the processing architecture for a solution

Compare the machine learning products & technologies from Microsoft

Select the appropriate data processing technologies

Understand data store models

Select the appropriate AI models and services

What are Azure Cognitive Services?

Cognitive services & Machine learning

Identify components and technologies required to connect service endpoints

Azure REST API Reference

Create a Cognitive services resource using the Azure portal

Identify automation requirements

An introduction to Azure Automation

Map Security Requirements to Tools, Technologies, and Processes

Select the Software, Services, and Storage Required to Support a Solution

Identify appropriate services and tools for a solution

What is Azure Machine Learning?

Compare the machine learning products & technologies from Microsoft

Choosing a Microsoft cognitive services technology

Identify integration points with other Microsoft services

What is Azure Event Grid?

Azure Event Hubs

Overview – What is Azure Logic Apps?

Identify storage required to store logging, bot state data, and Cognitive Services output

Understand data store models

Use the best data store for the job

ai-100

Amazon link (affiliate)

Design AI Solutions (40-45%)

Design Solutions That Include One or More Pipelines

Define an AI application workflow process

What are the Azure Machine Learning pipelines?

What is an Azure Machine Learning designer?

Design a strategy for ingest and egress data

Azure Data ingestion made easier with Azure Data Factory’s Copy Data Tool

Design the integration point between multiple workflows and pipelines

Integrating Data in Microsoft Azure

Design pipelines that use AI apps

Microsoft Azure Machine Learning Web Services portal

Design pipelines that call Azure Machine Learning models

Create endpoints for deployed Azure Machine Learning Studio web services

Select an AI solution that meets cost constraints

Azure Bot Service pricing

Azure Cognitive Services pricing

Design Solutions that use Cognitive Services

Design Solutions that Implement the Bot Framework

Integrate bots and AI solutions

Building with Conversational AI

Design bot services that use Language Understanding (LUIS)

Use a Web App Bot enabled with Language Understanding in C#

Design bots that integrate with channels

Connect a bot to channels

Integrate bots with Azure app services and Azure Application Insights

Exercise – Create an Azure web app bot

Add telemetry to your bot

Design the Compute Infrastructure to Support a Solution

Identify whether to create a GPU, FPGA, or CPU-based solution

Deploy ML models to FPGAs with Azure Machine Learning

Identify whether to use a cloud-based, on-premises, or hybrid compute infrastructure

What are public, private & hybrid clouds?

Select a compute solution that meets cost constraints

Choose an Azure compute service for your application

https://docs.microsoft.com/en-us/azure/architecture/guide/technology-choices/compute-decision-tree

Design for Data Governance, Compliance, Integrity, and Security

Define how users and applications will authenticate to AI services

Authenticate requests to Azure Cognitive Services

Design a content moderation strategy for data usage within an AI solution

What is Azure Content Moderator?

Try Content Moderator on the web

Ensure that data adhere to compliance requirements defined by your organization

Get compliance data of Azure resources

Microsoft compliance manager

Ensure appropriate governance for data

Azure governance documentation

Design strategies to ensure that the solution meets data privacy regulations and industry standards

Azure Cognitive Services

Data collection, retention & storage in Application Insights

Implement and Monitor AI Solutions (25-30%)

Implement an AI Workflow

Integrate AI Services with Solution Components

Configure prerequisite components and input datasets to allow the consumption of Cognitive Services APIs

Build a training data set for a custom model

Configure integration with Cognitive Services

Configure an application to expose a web API

Configure prerequisite components to allow connectivity to the Bot Framework

Create a bot with Azure Bot Service

Debug with the emulator

Implement Azure Cognitive Search in a solution

Search the web using the Bing Web Search REST API & C#

Monitor and Evaluate the AI Environment

Identify the differences between KPIs, reported metrics, and root causes of the differences

Create custom KPI dashboards using Azure Application Insights

Azure monitor data platform

Identify the differences between expected and actual workflow throughput

Scalability and Performance

Monitor & collect data from ML web service endpoints

Maintain an AI solution for continuous improvement

Create CI/CD pipelines for AI apps using Azure Pipelines, Docker & Kubernetes

Monitor AI components for availability

Send to Log Analytics workspace

Application Insights telemetry data model

Recommend changes to an AI solution based on performance data

Getting AI/ML and DevOps working better together

This brings us to the end of AI-100 Study Guide

What do you think? Let me know in the comments section if I have missed out on anything. Also, I love to hear from you about how your preparation is going on!

In case you are looking for other Azure certification exams check out this page

Follow/Like ravikirans.com to Receive Updates

Sign up for Newsletter

Want to be notified as soon as I post? Subscribe to RSS feed / leave your email address in the subscribe section. Share the article to your social networks with the below links so it can benefit others.

Share the Article in Your Social Media Networks

  • 3
  • 2
  •  
  •  
  •  
    5
    Shares

You may also like

Leave a Reply

Your email address will not be published. Required fields are marked *