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
Welcome to the "AI Agents for Beginners" course! This course will give you fundamental knowledge and applied samples for building with AI Agents.
3
+
Welcome to the "AI Agents for Beginners" course! This course gives you fundamental knowledge and applied samples for building with AI Agents.
4
4
5
-
Join the Azure AI Discord Community to meet other learners, and AI Agent Builders and ask any questions you have on this course.
5
+
Join the Azure AI Discord Community to meet other learners, and AI Agent Builders and ask any questions you have on this course.
6
6
7
-
To start this course, we will begin by getting a better understanding of what AI Agents are and how we can use them in the applications and workflows we build.
7
+
To start this course, we begin by getting a better understanding of what AI Agents are and how we can use them in the applications and workflows we build.
8
8
9
9
## Introduction
10
10
11
-
This lesson will cover:
11
+
This lesson covers:
12
12
13
13
- What are AI Agents and what are the different types of agents?
14
14
- What use cases are best for AI Agents and how they can help us?
15
15
- What are some of the basic building blocks when designing Agentic Solutions?
16
16
17
17
## Learning Goals
18
18
19
-
After completing this lesson you should have:
19
+
After completing this lesson, you should be able to:
20
20
21
-
-Have a better understanding of AI Agents and how they differ from other AI solutions.
22
-
-Knowledge of where best to apply AI Agents most efficiently.
23
-
-How to design Agentic solutions productively for both users and customers.
21
+
-Understand AI Agent concepts and how they differ from other AI solutions.
22
+
-Apply AI Agents most efficiently.
23
+
-Design Agentic solutions productively for both users and customers.
24
24
25
25
## Defining AI Agents and Types of AI Agents
26
26
@@ -30,68 +30,67 @@ AI Agents are **systems** that enable **Large Language Models(LLMs)** to **perfo
30
30
31
31
Let's break this definition into smaller parts:
32
32
33
-
**System** - It's important to think about agents not as just a single component but as a system of many components. At the basic level, the components of an AI Agent are:
33
+
-**System** - It's important to think about agents not as just a single component but as a system of many components.
34
34
35
-
-**Environment** - this is the defined space where the AI Agent is operating. For example, if we had an AI Agent that handles travel booking, the environment could be the travel booking system that the AI Agent will use to complete tasks.
36
-
-**Sensors** - Environments have information and provide feedback. AI Agents use sensors to gather and interpret this information about the current state of the environment. In the example of the Travel Booking Agent, the travel booking system can provide information such as hotel availability or flight prices.
37
-
-**Actuators** - Once the AI Agent receives the current state of the environment, it needs to determine what action to perform to change the environment based on the task at hand. For the travel booking agent, it may be to book an available room for the user.
35
+
At the basic level, the components of an AI Agent are:
38
36
39
-
**Large Language Models** - The concept of agents existed before the creation of LLM's. The advantage of building AI Agents with LLMs is their ability to interpret human language and data. This enables LLMs to interpret environmental information and define a plan to change the environment.
37
+
- **Environment** - The defined space where the AI Agent is operating. For example, if we had a travel booking AI Agent, the environment could be the travel booking system that the AI Agent uses to complete tasks.
38
+
- **Sensors** - Environments have information and provide feedback. AI Agents use sensors to gather and interpret this information about the current state of the environment. In the Travel Booking Agent example, the travel booking system can provide information such as hotel availability or flight prices.
39
+
- **Actuators** - Once the AI Agent receives the current state of the environment, For the current task the agent determines what action to perform to change the environment. For the travel booking agent, it might be to book an available room for the user.
40
40
41
-
**Perform Actions** - Outside of AI Agent systems, LLMs are limited to situations where the action is generating content or information based on a user's prompt. Inside AI Agent systems, LLMs can accomplish tasks by interpreting the user's request and what tools are available in its environment.
41
+
**Large Language Models** - The concept of agents existed before the creation of LLMs. The advantage of building AI Agents with LLMs is their ability to interpret human language and data. This ability enables LLMs to interpret environmental information and define a plan to change the environment.
42
42
43
-
**Access To Tools** - What tools the LLM has access to is defined by 1) the environment it is operating in and 2) the developer of the AI Agent. Continuing with our travel agent example, the agent's tools can be limited both by the operations available in the booking system, and/or the developer can define the agent as being only for a certain type of travel such as flights.
43
+
**Perform Actions** - Outside of AI Agent systems, LLMs are limited to situations where the action is generating content or information based on a user's prompt. Inside AI Agent systems, LLMs can accomplish tasks by interpreting the user's request and using tools that are available in its environment.
44
44
45
-
**Knowledge** - Outside of the information provided by the environment, AI Agents can also retrieve knowledge from other systems, services, tools, and even other agents. In the case of the travel agent, this could be the information on the user's travel preferences located in a customer database.
45
+
**Access To Tools** - What tools the LLM has access to is defined by 1) the environment it's operating in and 2) the developer of the AI Agent. For our travel agent example, the agent's tools are limited by the operations available in the booking system, and/or the developer can limit the agent's tool access to flights.
46
46
47
+
**Knowledge** - Outside of the information provided by the environment, AI Agents can also retrieve knowledge from other systems, services, tools, and even other agents. In the travel agent example, this knowledge could be the information on the user's travel preferences located in a customer database.
47
48
48
49
### The different types of agents
49
50
50
-
Now that we have covered a general definition of AI Agents, let us look at some specific agent types and how they would be applied to a travel booking AI agent.
51
+
Now that we have a general definition of AI Agents, let us look at some specific agent types and how they would be applied to a travel booking AI agent.
|**Simple Reflex Agents**| Perform immediate actions based on predefined rules. | Travel agent interprets the context of the email and forwards travel complaints to customer service. |
55
-
|**Model-Based Reflex Agents**| Perform actions based on a model of the world and changes to that model. | Travel agent prioritizes routes with significant price changes based on historical pricing data it has access to. |
56
+
|**Model-Based Reflex Agents**| Perform actions based on a model of the world and changes to that model. | Travel agent prioritizes routes with significant price changes based on access to historical pricing data. |
56
57
|**Goal-Based Agents**| Create plans to achieve specific goals by interpreting the goal and determining actions to reach it. | Travel agent books a journey by determining necessary travel arrangements (car, public transit, flights) from current location to destination. |
57
58
|**Utility-Based Agents**| Consider preferences and weigh tradeoffs numerically to determine how to achieve goals. | Travel agent maximizes utility by weighing convenience vs. cost when booking travel. |
58
59
|**Learning Agents**| Improve over time by responding to feedback and adjusting actions accordingly. | Travel agent improves by using customer feedback from post-trip surveys to make adjustments to future bookings. |
59
-
|**Hierarchical Agents**| Feature multiple agents in a tiered system, with higher-level agents breaking tasks into subtasks for lower-level agents to complete. | Travel agent cancels a trip by dividing the task into subtasks (e.g., canceling specific bookings) and having lower-level agents complete them, reporting back to the higher-level agent. |
60
+
|**Hierarchical Agents**| Feature multiple agents in a tiered system, with higher-level agents breaking tasks into subtasks for lower-level agents to complete. | Travel agent cancels a trip by dividing the task into subtasks (for example, canceling specific bookings) and having lower-level agents complete them, reporting back to the higher-level agent. |
60
61
|**Multi-Agent Systems (MAS)**| Agents complete tasks independently, either cooperatively or competitively. | Cooperative: Multiple agents book specific travel services such as hotels, flights, and entertainment. Competitive: Multiple agents manage and compete over a shared hotel booking calendar to book customers into the hotel. |
61
62
62
-
63
63
## When to Use AI Agents
64
64
65
65
In the earlier section, we use the Travel Agent use-case to explain how the different type of agents can be used in different scenarios of travel booking.
66
66
67
67
Let's look at when to use AI Agents more generally:
68
68
69
-
-**Open-Ended Problems** - allowing the LLM to determine needed steps to complete a task because it cannot alway be hardcoded into a workflow.
70
-
-**Multi-Step Processes** - tasks that require a level of complexity in which the AI Agent will need to use tools or information over multiple turns vs single shot retrieval.
69
+
-**Open-Ended Problems** - allowing the LLM to determine needed steps to complete a task because it can't always be hardcoded into a workflow.
70
+
-**Multi-Step Processes** - tasks that require a level of complexity in which the AI Agent needs to use tools or information over multiple turns instead of single shot retrieval.
71
71
-**Improvement Over Time** - tasks where the agent can improve over time by receiving feedback from either its environment or users in order to provide better utility.
72
72
73
-
We will cover more considerations of using AI Agents in the Building Trustworthy AI Agents lesson.
73
+
We cover more considerations of using AI Agents in the Building Trustworthy AI Agents lesson.
74
74
75
75
## Basics of Agentic Solutions
76
76
77
77
### Agent Development
78
78
79
-
Defining the tools, actions, and behaviors is the first place to start when designing an AI Agent system. In this course, we will focus on using the **Azure AI Agent Service** to define our Agents. It offers features like:
79
+
The first step in designing an AI Agent system is to define the tools, actions, and behaviors. In this course, we focus on using the **Azure AI Agent Service** to define our Agents. It offers features like:
80
80
81
-
-Open Model Selection. - use of OpenAI, Mistral, and Llama
81
+
-Selection of Open Models such as OpenAI, Mistral, and Llama
82
82
- Use of Licensed Data through providers such as Tripadvisor
83
83
- Use of standardized OpenAPI 3.0 tools
84
84
85
85
### Agentic Patterns
86
86
87
-
Communication with LLMs is through prompts. Given the semi-autonomous nature of AI Agents, it is not always possible or required to manually re-prompt the LLM after a change in the environment. We use **Agentic Patterns** that allow us to prompt the LLM over multiple steps in a more scalable and way.
87
+
Communication with LLMs is through prompts. Given the semi-autonomous nature of AI Agents, it isn't always possible or required to manually reprompt the LLM after a change in the environment. We use **Agentic Patterns** that allow us to prompt the LLM over multiple steps in a more scalable way.
88
88
89
89
This course is divided into some of the current popular Agentic patterns.
90
90
91
91
### Agentic Frameworks
92
92
93
-
Agentic Frameworks allow developers to implement agentic patterns through code. These frameworks offer templates, plugins, and tools for better AI Agent collaboration. With these benefits comes the ability for better observability and troubleshooting of AI Agent systems.
93
+
Agentic Frameworks allow developers to implement agentic patterns through code. These frameworks offer templates, plugins, and tools for better AI Agent collaboration. These benefits provide abilities for better observability and troubleshooting of AI Agent systems.
94
94
95
-
In this course, we will explore the research-driven Autogen framework and the production ready Agent framework from Semantic Kernel.
95
+
In this course, we will explore the research-driven AutoGen framework and the production ready Agent framework from Semantic Kernel.
96
96
97
-
Go to Lesson 2 where we will explore the differences between these AI Agent frameworks and tools.
0 commit comments