AB-100 exam prep: Agentic AI Business Solutions Architect

Name: AB-100 exam prep: Agentic AI Business Solutions Architect
Rating: 4.7 (86 reviews)

Use Copilot Studio to create AI agents, including autonomous and multi-agent solutions, for the AB-100 exam

Bestseller

Created byPhillip Burton • over one million students so far, I Do Data Limited

Last updated 3/2026

English

What you'll learn

Plan AI-powered business solutions
Design AI and agents for business solutions
Design extensibility of AI solutions
Deploy AI-powered business solutions

Course content

18 sections • 108 lectures • 10h 49m total length

Introduction2:46
Welcome to Udemy0:37
How to get the best out of your Udemy course3:05
Do you want auto-translated subtitles in more languages?1:20
Curriculum5:59
Resources0:07

Signing into Microsoft Copilot Studio3:50
Sign into Microsoft Copilot Studio to create agents that handle input and output with natural language and generative AI. Learn pricing, trial access, and work or school email requirements.
Why do I need a Work email address? And how can I get one, if I don't have it?12:27
1, 7. What are agents, and looking at Copilot Studio prebuilt agents6:20
Creating a new environment and solution10:08
Create a new environment and a new solution to organize agents and their objects. Select a region, set a publisher name, and apply a unique prefix for object identifiers.
5, 35. Design the strategy for building AI and agents, creating a blank agent4:51
25, 30, 35. Adding Key Phrases to a trigger and Sending a message to the user9:17
25, 30, 35. Asking a question, using a variable, and adding a condition9:57
25, 30, 35. Other topic nodes4:31
30. Design topics for Copilot Studio, including fallback8:40
Practice Activity 10:58
Practice Activity 1 - The Solution8:54
Prepare for AB-100 exam by creating and testing a classic orchestration agent in Copilot Studio, building a new solution, and configuring hotel pricing with topics, variables, and room rates.
Creating Copilot Studio classic orchestrated single-agent

27. Design prompt and response agents9:45
8, 27. Define the solution rules and constraints using instructions9:03
Explore building a generative ai agent using a spreadsheet as the knowledge source, avoid assuming the logged-in employee, and craft clear, active instructions with markup.
71. Review solution for adherence to responsible AI principles3:16
9, 73a. Using generative AI and knowledge sources in Copilot Studio agents9:12
Explore how generative AI and diverse knowledge sources power Copilot Studio agents, comparing classic and generative orchestration, and configuring web search, documents, and databases.
35, 42. Publishing and Design agent behaviors in Copilot Studio6:53
Practice Activity 20:29
Practice Activity 2 - The Solution4:37
Create a generative AI orchestration agent that returns room rates for a room type from the attached room rates spreadsheet, grounding it with this data source.
Creating Copilot generative AI single-agents

31, 61. Design data processing for AI models and grounding5:47
2, 3. Review data for grounding and organizing business solution data9:25
72a. Validate data residency and movement compliance4:50
Identify data residency rules and cross-region movement for CoPilot Studio by reviewing environment regions, Bing search data boundaries, and configurable options across EU, UK, Australia, and US.
11b, 35. Using different AI models in Copilot Studio8:03
Grounding, Data and AI model integration

26. Design autonomous agents: what are triggers?7:55
26. Adding a trigger to our agent to make it autonomous, and then testing it6:31
Add an email trigger to make the agent autonomous, configure Outlook inbox filtering, test the trigger, review permissions and Power Automate flow, and publish.
35. Adding a tool which sends emails to our autonomous agent9:44
Practice Activity 30:29
Practice Activity 3 - The Solution9:55
Create an autonomous agent that triggers on emails containing the word room and uses a room rates spreadsheet to determine room type and price, then publish and test.
Creating autonomous agents with tools

6. Creating a second agent for tracking leave8:05
6. Child (inline) agents versus connected agents6:58
6. Designs for a multi-agent solution8:48
6. Creating a third agent which uses the two other agents9:54
6. Creating a fourth agent which writes to a spreadsheet9:49
39. Design agent extensibility in Copilot Studio using Agent Flows10:16
39, 40. Design agent extensibility with Model Context Protocol in Copilot Studio5:32
Practice Activity 50:17
Practice Activity 5 - The Solution8:26
Designing multi-agent solutions in Copilot Studio

51-54a. Monitor agent performance and metrics in Copilot Studio9:09
55. Interpret telemetry data for performance and model tuning6:39
Access telemetry data for your Copilot Studio agent with Azure Application Insights, log custom events and node executions, and use kql queries and monitoring workbooks to improve performance.
56a, 60. Recommend the process and metrics to test agents5:33
62, 65-66. Unmanaged and managed solutions5:58
Learn the application lifecycle management for Co-Pilot Studio and Power Platform items, distinguishing unmanaged versus managed solutions, and how to develop, test, and deploy across development, test, and production environments.
Analyze, monitor, and tune AI-powered business solutions - Part 1
62, 65-66. Design the ALM process for Copilot Studio agents, connectors, actions6:02
67a. Design security for agents7:38
70. Analyze solution and AI vulnerabilities and mitigations8:15
68a. Design governance for agents4:52
Analyze, monitor, and tune AI-powered business solutions - Part 2

Creating an agent in Microsoft Foundry9:56
Looking at models and tools in Microsoft Foundry9:02
Practice Activity 71:32
Practice Activity 7 - The Solution6:47
11a, 37, 57, 64. Creating a fine-tuned AI model9:41
11a, 37, 57, 64. Custom models2:37
13. Develop the use cases for customized small language models for the solution5:21
20. Implement a model router4:31
Explore how a model router in Microsoft Foundry directs prompts to the most suitable LLM, reducing costs and latency while preserving quality.
Agents and models in Microsoft Foundry

Requirements

Before beginning, you will need to know how to use a Windows computer, including a mouse.
It would be useful to have either a Business or Enterprise version of Office, but that is not essential.
We will get free trial of Copilot Studio

Description

The Microsoft AB-100 certification is the new certification for Copilot Studio, Microsoft Foundry, and Microsoft 365 Copilot. Microsoft says that this certification demonstrates that you have the proficiency in working with agents and a working knowledge of language models to create intelligent solutions by earning the Agentic AI Business Solutions Architect certification.

Please note: This course is not affiliated with, endorsed by, or sponsored by Microsoft.

In this AB-100 exam preparation course:

We'll start with Copilot Studio, creating classic orchestrated agents and generative AI single-agents. We'll add key phrases to a trigger, and use messages, questions, and conditions using variables in a topic. We'll creating instructions and knowledge sources, design data processing and reviewing data for grounding, and validate data residency and movement compliance.
We'll continue with Copilot Studio, looking at autonomous agents, which run based on an event, agents which use other agents, tools, Model Context Protocol servers, and Computer Use tools. We'll also look at how to analyze, monitor and tune AI-powered business solutions.
We'll then look at other services which can use AI agents. We'll look at Microsoft Foundry, and create custom models, Foundry Tools, security and governance. We'll see how we can create agents in Microsoft 365 and SharePoint. Finally, we'll see how we can use AI in Power Apps and the AI Hub, and how to modify existing agents and more in Dynamics 365.

No prior knowledge is required, but some knowledge of some of these services is preferable. This course comes complete with quizzes, Copilot Studio practice activities, and practice tests, so you can be sure that you are learning.

Once you have completed this course, you will have an expanded knowledge of how to create agents. With some practice, you could even take the official Microsoft AB-100 exam. If you pass this exam and you have one of the 12 pre-requisite exams (in Power Platform, Dynamics 365 or the AI-102 exam), you would then receive the "Agentic AI Business Solutions Architect" certificate. This would look good on your CV or resume.

Who this course is for:

This course is for you if you want to develop your knowledge of Microsoft Copilot Studio.
This course is also for you if you want to study towards the Microsoft AB-100 exam.
This course is also for you if you want to plan, design and deploy AI business solutions

AB-100 exam prep: Agentic AI Business Solutions Architect

What you'll learn

Explore related topics

Course content

Introduction6 lectures • 14min

Creating Copilot Studio classic orchestrated single-agent11 lectures • 1hr 20min

Creating Copilot generative AI single-agents7 lectures • 43min

Grounding, Data and AI model integration4 lectures • 28min

Creating autonomous agents with tools5 lectures • 35min

Adding custom prompts to our Copilot Studio agent4 lectures • 21min

Designing multi-agent solutions in Copilot Studio9 lectures • 1hr 8min

Adding Computer Use into Copilot Studio4 lectures • 27min

Analyze, monitor, and tune AI-powered business solutions8 lectures • 54min

Agents and models in Microsoft Foundry8 lectures • 49min

Requirements

Description

Who this course is for: