You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: learn-pr/wwl-data-ai/develop-ai-agent-azure/5-exercise.yml
+1-1Lines changed: 1 addition & 1 deletion
Original file line number
Diff line number
Diff line change
@@ -6,7 +6,7 @@ metadata:
6
6
description: Learn how to build an agent using Azure AI Agent Service. This unit provides a hands-on exercise to build an agent using Azure AI Agent Service.
description: This unit contains a knowledge check which can help learners reinforce their understanding of the material.
6
+
description: This unit contains a knowledge check, which can help learners reinforce their understanding of the material.
7
7
author: ivorb
8
8
ms.author: berryivor
9
-
ms.date: 02/24/2025
9
+
ms.date: 04/03/2025
10
10
ms.topic: unit
11
11
durationInMinutes: 3
12
12
content: |
@@ -23,26 +23,26 @@ quiz:
23
23
- content: "Make API calls using SDKs"
24
24
isCorrect: false
25
25
explanation: "Incorrect. Making API calls using SDKs is the third step after deploying a compatible model."
26
-
- content: "Which feature of Azure AI Agent Service ensures data privacy and compliance?"
26
+
- content: "Which element of an agent definition is used to specify its behavior and restrictions?"
27
27
choices:
28
-
- content: "Automatic tool calling"
28
+
- content: "Model"
29
29
isCorrect: false
30
-
explanation: "Incorrect. Automatic tool calling handles the tool-calling lifecycle but does not specifically ensure data privacy and compliance."
31
-
- content: "Enterprise-grade security"
30
+
explanation: "Incorrect. The model is used to interpret and respond to prompts."
31
+
- content: "Instructions"
32
32
isCorrect: true
33
-
explanation: "Correct. Enterprise-grade security ensures data privacy and compliance with secure data handling and keyless authentication."
34
-
- content: "Customizable storage solutions"
33
+
explanation: "Correct. You use instructions to tell the agent how to behave."
34
+
- content: "Tools"
35
35
isCorrect: false
36
-
explanation: "Incorrect. Customizable storage solutions provide visibility and control over storage but do not specifically ensure data privacy and compliance."
37
-
- content: "You are tasked with creating an AI agent that can interpret code and interact with data sources like Bing. Which feature of Azure AI Agent Service should you utilize?"
36
+
explanation: "Incorrect. Tools are used to enable the agent to retrieve data and perform tasks."
37
+
- content: "Which tool should you use to enable an agent to dynamically generate code to perform tasks or access data in files?"
38
38
choices:
39
-
- content: "Out-of-the-box tools"
39
+
- content: "Code Interpreter"
40
40
isCorrect: true
41
-
explanation: "Correct. Out-of-the-box tools include capabilities for code interpretation and interaction with data sources like Bing, making them ideal for this task."
42
-
- content: "Securely managed data"
41
+
explanation: "Correct. The code interpreter tool enables agents to generate code in a sandbox."
42
+
- content: "Azure Functions"
43
43
isCorrect: false
44
-
explanation: "Incorrect. Securely managed data handles conversation states but does not specifically provide tools for code interpretation or data source interaction."
45
-
- content: "Enterprise-grade security"
44
+
explanation: "Incorrect. Azure Function tools are used to enable the agent to call serveless Azure Functions."
45
+
- content: "Azure AI Search"
46
46
isCorrect: false
47
-
explanation: "Incorrect. Enterprise-grade security ensures data privacy and compliance but does not specifically provide tools for code interpretation or data source interaction."
47
+
explanation: "Incorrect. The Azure AI Search tool enables the agent to ground prompts using data from an index in Azure AI Search."
Copy file name to clipboardExpand all lines: learn-pr/wwl-data-ai/develop-ai-agent-azure/includes/1-introduction.md
+1-6Lines changed: 1 addition & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -2,10 +2,5 @@ Azure AI Agent Service is a fully managed service designed to empower developers
2
2
3
3
Imagine you're working in the healthcare industry, where there's a need to automate patient interactions and streamline administrative tasks. Your organization wants to develop an AI agent that can handle patient inquiries, schedule appointments, and provide medical information based on real-time data. However, managing the infrastructure and ensuring data security are significant challenges. Azure AI Agent Service offers a solution by allowing you to create AI agents tailored to your needs through custom instructions and advanced tools. This service simplifies the development process, reduces the amount of code required, and manages the underlying infrastructure, enabling you to focus on building high-quality AI solutions.
4
4
5
-
In this module, you'll learn about the purpose, key features, setup process, and integration capabilities of Azure AI Agent Service.
5
+
In this module, you'll learn how to use the Azure AI Agent Service to develop agents.
6
6
7
-
After completing this module, you’ll be able to:
8
-
- Describe the purpose of AI agents
9
-
- Explain the key features of Azure AI Agent Service
10
-
- Build an agent using the Azure AI Agent Service
11
-
- Integrate an agent in the Azure AI Agent Service into your own app
Copy file name to clipboardExpand all lines: learn-pr/wwl-data-ai/develop-ai-agent-azure/includes/2-what-is-ai-agent.md
+5-10Lines changed: 5 additions & 10 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,4 +1,4 @@
1
-
An AI agent is a software service that uses generative AI to understand and perform tasks on behalf of a user or another program. These agents leverage advanced AI models to understand context, make decisions, utilize grounding data, and take actions to achieve specific goals. Unlike traditional applications, AI agents can operate independently, executing complex workflows and automating processes without the need of constant human intervention. The evolution of generative AI enables agents to behave intelligently on our behalf, transforming how we can leverage and integrate these agents.
1
+
An AI agent is a software service that uses generative AI to understand and perform tasks on behalf of a user or another program. These agents use advanced AI models to understand context, make decisions, utilize grounding data, and take actions to achieve specific goals. Unlike traditional applications, AI agents can operate independently, executing complex workflows and automating processes without the need of constant human intervention. The evolution of generative AI enables agents to behave intelligently on our behalf, transforming how we can use and integrate these agents.
2
2
3
3
Understanding what an AI agent is and how to utilize them is crucial for effectively using AI to automate tasks, make informed decisions, and enhance user experiences. This knowledge enables organizations to deploy AI agents strategically, maximizing their potential to drive innovation, improve efficiency, and achieve business objectives.
4
4
@@ -7,14 +7,13 @@ Understanding what an AI agent is and how to utilize them is crucial for effecti
7
7
AI agents are incredibly useful for several reasons:
8
8
9
9
-**Automation of Routine Tasks**: AI agents can handle repetitive and mundane tasks, freeing up human workers to focus on more strategic and creative activities. This leads to increased productivity and efficiency.
10
-
-**Enhanced Decision-Making**: By processing vast amounts of data and providing insights, AI agents support better decision-making. They can analyze trends, predict outcomes, and offer recommendations based on real-time data.
11
-
-**Decision-Making Capabilities**: AI Agents can use advanced decision-making algorithms and machine learning models to analyze data and make informed decisions. This allows them to handle complex scenarios and provide actionable insights, whereas generative AI chat models primarily focus on generating text-based responses.
12
-
-**Scalability**: AI agents can scale operations without the need for proportional increases in human resources. This is particularly beneficial for businesses looking to grow without significantly increasing operational costs.
10
+
-**Enhanced Decision-Making**: By processing vast amounts of data and providing insights, AI agents support better decision-making. They can analyze trends, predict outcomes, and offer recommendations based on real-time data. AI Agents can even use advanced decision-making algorithms and machine learning models to analyze data and make informed decisions autonomously. This allows them to handle complex scenarios and provide actionable insights, whereas generative AI chat models primarily focus on generating text-based responses.
11
+
-**Scalability**: AI agents can scale operations without the need for proportional increases in human resources. This is beneficial for businesses looking to grow without significantly increasing operational costs.
13
12
-**24/7 Availability**: Like all software, AI agents can operate continuously without breaks, ensuring that tasks are completed promptly and customer service is available around the clock.
14
13
15
14
Agents are built to simulate human-like intelligence and can be applied in various domains such as customer service, data analysis, automation, and more.
16
15
17
-
## Examples of AI agent use Casesc
16
+
## Examples of AI agent use cases
18
17
19
18
AI agents have a wide range of applications across various industries. Here are some notable examples:
20
19
@@ -41,9 +40,5 @@ Developer agents help in software development tasks such as code review, bug fix
41
40
> [!TIP]
42
41
> To learn more about GitHub Copilot, explore the [GitHub Copilot fundamentals](/training/paths/copilot/) learning path.
43
42
44
-
## How to build an agent
45
-
46
-
Agents can be built with various services and platforms, including Microsoft 365, Semantic Kernel, and Azure AI Agent Service. The rest of this module will focus on the AI Agent Service, however there are independent learning paths on Microsoft Learn for the other services.
47
-
48
-
> [!TIP]
43
+
> [!NOTE]
49
44
> You can explore more about agents in general with the [Fundamentals of AI agents](/training/modules/ai-agent-fundamentals) module.
Copy file name to clipboardExpand all lines: learn-pr/wwl-data-ai/develop-ai-agent-azure/includes/3-how-use-agent-service.md
+16-27Lines changed: 16 additions & 27 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -4,7 +4,15 @@ Azure AI Agent Service is a fully managed service designed to empower developers
4
4
5
5
Azure AI Agent Service allows developers to create AI agents tailored to their needs through custom instructions and advanced tools like code interpreters and custom functions. These agents can answer questions, perform actions, or automate workflows by combining generative AI models with tools that interact with real-world data sources. The service simplifies the development process by reducing the amount of code required and managing the underlying infrastructure.
6
6
7
-
Previously, developers could create an agent-like experience by using standard APIs in Azure AI Foundry and connect to custom functions or other tools, but doing so would take a significant coding effort. Azure AI Agent Service handles all of that for you through AI Foundry to build agents via the portal or in your own app in fewer than 50 lines of code. The exercise in the module explores both methods of building an agent.
7
+
Previously, developers could create an agent-like experience by using standard APIs in Azure AI Foundry and connect to custom functions or other tools, but doing so would take a significant coding effort. Azure AI Agent Service handles all of that for you through AI Foundry to build agents via the portal or in your own app in fewer than 50 lines of code. The exercise in the module explores both methods of building an agent.e
8
+
9
+
Azure AI Agent Service is ideal for scenarios requiring advanced language models for workflow automation. It can be used to:
10
+
11
+
- Answer questions using real-time or proprietary data sources.
12
+
- Make decisions and perform actions based on user inputs.
13
+
- Automate complex workflows by combining generative AI models with tools that interact with real-world data.
14
+
15
+
For example, an AI agent can be created to generate reports, analyze data, or even interact with users through apps or chatbots, making it suitable for customer support, data analysis, and automated reporting.
8
16
9
17
## Key features of Azure AI Agent Service
10
18
@@ -19,36 +27,17 @@ Azure AI Agent Service offers several key features:
19
27
20
28
Azure AI Agent Service provides a more streamlined and secure way to build and deploy AI agents compared to developing with the Inference API directly.
21
29
22
-
## Setting up your agent
23
-
24
-
To set up Azure AI Agent Service, follow these steps:
25
-
26
-
1.**Create an Azure AI Foundry hub and project**: Start by creating an AI hub and project in your Azure subscription.
27
-
1.**Deploy a compatible model**: Deploy a model such as GPT-4o to your project.
28
-
1.**Define parameters and instructions**: Once the model is deployed, you can define instructions for your agent and connect tools for enhanced functionality.
29
-
1.**Call your agent**: Once you're set up, you can chat with your agent in Azure AI Foundry portal or integrate it into your app.
30
-
31
-
## Tools available to your agent
32
-
33
-
Much of the enhanced functionality of an agent comes from the agent's ability to determine when and how to use *tools*. Tools are additional functionality available to your agent, and if the conversation or task warrants the use of one or more of the tools, the agent calls that tool and handle the response.
34
-
35
-
36
-
37
-
For example, one of the tools available is the *code interpreter*. This tool enables your agent to run custom code it writes to achieve something, such as MATLAB code to create a graph or solve a data analytics problem.
38
-
39
-
Available tools are split into two categories:
30
+
## Azure AI Agent Service resources
40
31
41
-
-**Knowledge tools**: These tools enhance the context or knowledge of your agent. This can include things like Azure AI Search for grounding context (effectively implementing a RAG pattern), uploading files for context, or integrating with Bing to provide real-time data.
32
+
Azure AI Agent Service is fully managed and designed to help developers build agents without having to worry about underlying resources. Through Azure, AI Foundry and the Agent Service will provision the necessary cloud resources. If desired, you can choose to connect your own resources when building your agent, giving you the flexibility to utilize Azure however works best for you.
42
33
43
-
34
+
At a minimum, you need to create an Azure AI hub with an Azure AI project for your agent. You can add more Azure services as required. You can create the resources using the Azure AI Foundry portal, or you can use [predefined bicep templates](https://github.com/Azure/azure-quickstart-templates/tree/master/quickstarts/microsoft.azure-ai-agent-service) to deploy the resources in your subscription. Two common architectures for Azure AI Agent Service solutions are:
44
35
45
-
-**Action tools**: These tools perform an action or run a function. This includes the code interpreter to execute code and custom function calling through OpenAPI specifications, Azure Functions, and more.
36
+
-**Basic agent setup**: A minimal configuration that includes Azure AI hub, Azure AI project, and Azure AI Services resources.
46
37
47
-
By connecting built-in and custom tools, you can allow your agent to perform countless tasks on your behalf.
38
+
48
39
49
-
> [!NOTE]
50
-
> For more information on integrating Azure AI Agent Service with Azure Functions, see the [integration guide](/azure/ai-services/agents/how-to/tools/azure-functions?azure-portal=true).
40
+
-**Standard agent setup**: A more comprehensive configuration that includes the basic agent setup plus Azure Key Vault, Azure AI Search, and Azure Storage.
51
41
52
-
## Integrating an agent in your app
42
+
53
43
54
-
Azure AI Agent Service provides several SDKs and a REST API for you to integrate agents into your app using your preferred programming language. This module focuses mostly on Python and C#, but the process will be the same for REST or other language SDKs.
0 commit comments