Teach on Udemy

Turn what you know into an opportunity and reach millions around the world.

Learn More

Your cart is empty.

Keep shopping

AI-100: Designing and Implementing an Azure AI Solutions

Name: AI-100: Designing and Implementing an Azure AI Solutions
Rating: 4.5 (926 reviews)

Clear and Concise

Role Play

Created byAnand Rao Nednur

Last updated 5/2025

English

What you'll learn

Ingest, transform, and prepare data for AI solutions
Design and implement end-to-end AI solutions on Microsoft Azure
Monitor and optimize AI solutions deployed on Microsoft Azure
Secure AI solutions on Microsoft Azure
You will be able to integrate and get best results for any computer vision or Natural Language processing tasks.
Ability to show and include Machine Learning applications in your app
Learn Microsoft Azure - Cloud platform cognitive services like Face, Vision, Text API

Course content

5 sections • 59 lectures • 5h 0m total length

Introduction2:17
Explore how to design and implement Azure AI solutions using cognitive services, including vision, language, and Azure Bot Service capabilities, and connect components with Azure Data Factory.

What Can you Expect in this Section0:51
Overview of Azure Services10:37
Using Azure Portal - I5:01
Using Azure Portal - II15:29
Using Azure CLI5:14
Service Categories10:58
Designing a Solution - An Overview7:15
Design a scalable Azure solution by integrating App Service, SQL Database, Cognitive Search, AD B2C, queues, Functions, Blob Storage, Redis Cache, CDN, Traffic Manager, and Application Insights.
How do you Manage these Services?7:13
Learn to monitor, backup, and secure Azure resources using Azure Monitor, Application Insights, and Security Center. Use Azure Advisor, Azure Policy, templates, and Azure Blueprints for governance and cost optimization.
Troubleshooting Azure Access & Service Visibility

Select the processing Architecture for a solution6:15
Select the appropriate data processing technologies3:23
Select the appropriate AI models and services6:52
Select the right Azure AI models and services across vision, speech, search, language, and decision APIs, with examples like computer vision, form recognizer, text analytics, QnA Maker, and content moderator.
Identify components and technologies required to connect service endpoints4:54
Identify automation requirements3:07
Introduction to Cognitive Services - Lab Activity4:46
Identify Processes and Regulations Needed to Conform with Data Privacy3:09
Identify which Users and Groups have Access to Information and Interfaces4:02
Learn how to apply role-based access control for Azure cognitive services using contributor, data reader, and cognitive service user roles, and secure keys with managed identities and Azure Key Vault.
Identify Appropriate Tools for a Solution3:42
Identify Auditing Requirements4:48
Identify appropriate services and tools for a solution4:59
Identify integration points with other Microsoft services5:41
Identify storage required to store logging, bot state data, and Azure Cognitive4:36
Face Recognition Lab Activity12:50
Group Picture -Detection- Lab Activity7:24
Train a group-based Azure Face Cognitive Service model to identify and group people in images, create a person group, train, and test with a sample image using keys and endpoints.
Module 1 : Analyze solution requirements (25-30%) - Quiz
Improving Visibility with the Right Auditing and Logging Strategy

Define an AI application workflow process3:40
Design a Strategy for Ingest and Egress Data5:56
Design the integration point between multiple workflows and pipelines3:05
Design Pipelines that use AI Apps2:31
Select an AI Solution that Meets Cost Restraints3:57
Design solutions that use vision, speech, language, knowledge, search etc6:11
Integrate Bots and AI Solutions6:51
Design Bot Services that use Language Understanding (LUIS)4:45
Design Bots that Integrate with Channels9:10
Integrate Bots with Azure App Services and Azure Application Insights2:25
Integrate bots with azure app services to host the bot service using serverless compute, and configure azure application insights for monitoring, logging, auditing, and troubleshooting.
Identify Whether to Create a GPU, FPGA, or CPU-Based Solution5:33
Identify Whether to Use a Cloud-Based, On-Premises, or Hybrid Compute Infra4:31
Select a Compute Solution that Meets Cost Constraints7:50
31 Define how users and applications autenticate to AI services4:33
32 Design a Content Moderation Strategy for Data Usage within an AI Solution4:48
33 Ensure that Data Adheres to Compliance Requirements Defined by an Organizatio1:32
34 Ensure Appropriate Governance for Data4:08
35 Design Strategies to Ensure the Solution Meets Data Privacy and Industry Stan3:47
Optical Character Recognition Using Python - Lab Activity6:21
Presenting a Secure and Cost-Effective AI Bot Solution to a Stakeholder
Module 2: Design Al solutions (40-45%)- Quiz

36 Develop AI Pipelines5:05
Explore five blocks of an Azure machine learning pipeline—workspace and data store, data reference, compute targets, submit and publish, and run and view results—showing how Azure services fit each stage.
37 Manage the Flow of Data Through Solution Components3:17
Implement Data Logging Processes2:37
Define and Construct interfaces for Custom AI Services8:16
Integrate AI Models with other Solutions Components3:10
Create Solution Endpoints2:00
Develop Streaming Solutions5:17
Configure Prerequisite Component and Input Datasets to Allow Consumption of data3:19
Configure Integration with Azure Services2:16
Implement Azure Search in a Solution3:40
Identify the Differences Between KPIs, Reported Metrics, and Root Causes3:43
Identify the Differences Between Expected and Actual Workflow Throughput3:52
Implement AI for Continuous Improvement3:22
Monitor AI Components for Availability7:00
Learn how Azure Monitor powers availability for AI infrastructure by integrating web apps, containers, and virtual machines with Application Insights, Log Analytics, and automation for dashboards and reports.
Recommend Changes to an AI Solution Based on Performance Data5:11
Analyze performance data to recommend changes to an AI solution, scaling up compute and storage, scaling out web apps, and upgrading pricing plans to remove bottlenecks and balance cost.
Course Conclusion - AI 1001:20
AI Solution Review with a Strategic Advisor
Module 3: Implement and monitor Al solutions (25-30%- Quiz

Requirements

This path is intended for learners who are familiar with common AI workflows and concepts, but who do not have experience applying these concepts using Microsoft Azure services.
Basic Python or Javascript
Basic idea about HTTP, REST
Usage of Visual Studio

Description

Course Update:

While the original content is based on the AI-100 exam, learners preparing for AI-102 can still benefit from the existing modules, as the core concepts and practical knowledge remain highly relevant and applicable to the updated certification.

Course Overview:
Microsoft Azure provides a comprehensive suite of services designed to enable rapid development, deployment, and operationalization of intelligent AI-driven solutions. This course is structured to help you understand how these services integrate to support the design, implementation, monitoring, optimization, and security of AI applications in real-world scenarios.

Originally tailored for the Microsoft AI-100 certification exam, the course remains highly valuable for those pursuing AI-102, as it covers the foundational and advanced topics that are critical to success in the evolving AI landscape on Azure.

What You’ll Learn:
The course offers deep, hands-on exploration of Azure Cognitive Services APIs, including:

Vision APIs: Face detection, content tagging, and Optical Character Recognition (OCR)
Language APIs: Language detection, sentiment analysis, and key phrase extraction

You’ll implement these services using both Python and JavaScript, ensuring a practical, real-world learning experience that prepares you for modern AI development tasks.

Detailed Course Content:

1. Analyze Solution Requirements (25–30%)

Recommend and select Azure Cognitive Services APIs
Choose appropriate data processing technologies and AI models
Map security and automation needs to technologies and tools
Align with data privacy, protection, and compliance regulations
Identify software, services, and storage to support the AI solution

2. Design AI Solutions (40–45%)

Create AI workflows and data ingestion/egress strategies
Integrate pipelines using Azure Machine Learning and AI apps
Build solutions using Vision, Speech, Language, and Knowledge APIs
Design and integrate bots using the Microsoft Bot Framework and LUIS
Select the right compute infrastructure (GPU, FPGA, CPU) and ensure cost-efficiency
Incorporate governance, compliance, and security principles in AI design

3. Implement and Monitor AI Solutions (25–30%)

Develop and manage AI pipelines and data flow
Construct custom AI service interfaces and solution endpoints
Integrate Azure Cognitive Services and the Microsoft Bot Framework
Implement Azure Cognitive Search
Monitor key performance metrics and optimize AI performance

Whether you are aiming to pass the AI-102 certification or seeking to apply AI concepts in your organization, this course will equip you with both theoretical understanding and practical expertise.

If you have any questions or need guidance, feel free to reach out. I’m here to support your learning journey.

Welcome to the course — let’s get started!

Who this course is for:

Participants who intend to learn common AI workflows and concepts
Participants who want to Secure AI solutions
Participants preparing for AI 100 Microsoft Certification

AI-100: Designing and Implementing an Azure AI Solutions

What you'll learn

Explore related topics

Course content

Introduction1 lecture • 2min

Overview of Azure Services9 lectures • 1hr 3min

Module 1 : Analyze solution requirements (25-30%)16 lectures • 1hr 20min

Module 2 : Design AI solutions (40-45%)20 lectures • 1hr 32min

Module 3 : Implement and monitor AI solutions (25-30%)17 lectures • 1hr 3min

Requirements

Description

Who this course is for: