Skip to content

Commit 69da66e

Browse files
committed
snapshot state
1 parent 27b1303 commit 69da66e

File tree

8 files changed

+66
-28
lines changed

8 files changed

+66
-28
lines changed
Lines changed: 25 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,25 @@
1+
### YamlMime:ModuleUnit
2+
uid: learn.wwl.orchestrate-sk-multi-agent-solution.agent-framework-components
3+
title: $agent-framework-components
4+
metadata:
5+
title: $agent-framework-components
6+
description: "TODO this field is for search engine optimization and is not user-visible; use 2-3 complete, grammatically correct sentences to describe the unit; include relevant search keywords."
7+
ms.date: 3/18/2025
8+
author: ivorb
9+
ms.author: berryivor
10+
ms.topic: interactive-tutorial
11+
###########################################################################
12+
###
13+
### If your content is related to a product or service, apply one value from the either the ms.prod allowlist
14+
### or the ms.service allowlist. You can’t use both ms.prod and ms.service.
15+
###
16+
### If your content isn't about a product or service, you can omit both ms.prod and ms.service.
17+
###
18+
### The list of approved ms.prod values is here: https://review.learn.microsoft.com/help/platform/metadata-taxonomies?branch=main#msprod
19+
### The list of approved ms.service values is here: https://review.learn.microsoft.com/help/platform/metadata-taxonomies?branch=main#msservice
20+
### If you need to request new values, follow the process here: https://review.learn.microsoft.com/en-us/help/platform/metadata-allowlist-requests?branch=main
21+
ms.prod: TODO
22+
ms.service: TODO
23+
durationInMinutes: 1
24+
content: |
25+
[!include[](includes/3-agent-framework-components.md)]

learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/6-design-agent-collaboration.yml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -10,4 +10,4 @@ metadata:
1010
ms.topic: unit
1111
durationInMinutes: 6
1212
content: |
13-
[!include[](includes/5-design-agent-collaboration.md)]
13+
[!include[](includes/6-design-agent-collaboration.md)]

learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/9-summary.yml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -10,4 +10,4 @@ metadata:
1010
ms.topic: unit
1111
durationInMinutes: 2
1212
content: |
13-
[!include[](includes/7-summary.md)]
13+
[!include[](includes/9-summary.md)]
Lines changed: 17 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -1,8 +1,20 @@
1-
TODO fluff intro, devops scenario
1+
AI agents offer a powerful combination of technologies, able to complete tasks with the use of generative AI. However, in some situations, the task required might be larger than is realistic for a single agent. For those scenarios, consider a **multi-agent** solution. A multi-agent solution allows agents to collaborate within the same conversation.
22

3-
In this module, you'll learn how to use the Semantic Kernel SDK to develop your own AI agents that can collaborate for a multi-agent solution.
3+
Imagine you are trying to address common DevOps challenges such as monitoring application performance, identifying issues, and deploying fixes. A multi-agent system could consist of four specialized agents working collaboratively:
4+
5+
1. The Monitoring Agent continuously ingests logs and metrics, detects anomalies using natural language processing (NLP), and triggers alerts when issues arise.
6+
1. The Root Cause Analysis Agent then correlates these anomalies with recent system changes, leveraging machine learning models or predefined rules to pinpoint the root cause of the problem.
7+
1. Once the root cause is identified, the Automated Deployment Agent takes over to implement fixes or roll back problematic changes by interacting with CI/CD pipelines and executing deployment scripts.
8+
1. Finally, the Reporting Agent generates detailed reports summarizing the anomalies, root causes, and resolutions, and notifies stakeholders via email or other communication channels.
9+
10+
This modular, scalable, and intelligent multi-agent system streamlines the DevOps process, reducing manual intervention and improving efficiency while ensuring timely communication and resolution of issues.
11+
12+
In this module, we will explore how to leverage the powerful capabilities of Semantic Kernel to design, implement, and orchestrate intelligent agents that work collaboratively to solve complex problems.
13+
14+
In this module, you'll learn how to use the Semantic Kernel Agents Framework to develop your own AI agents that can collaborate for a multi-agent solution.
415

516
After completing this module, you'll be able to:
6-
- Build AI agents using the Semantic Kernel SDK
7-
- Use tools and plugins with your AI agents
8-
- Develop multi-agent solutions
17+
18+
- Build AI agents using the Semantic Kernel SDK
19+
- Use tools and plugins with your AI agents
20+
- Develop multi-agent solutions
Lines changed: 12 additions & 16 deletions
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
Semantic Kernel is an open-source SDK that enables developers to integrate AI models into their applications. Using the SDK, developers can create "plugins" to interface with the LLMs and perform various tasks. Semantic Kernel bridges the gap between AI and software development by offering tools to create AI-driven agents that can execute tasks, interact with APIs, and perform complex workflows.
1+
Semantic Kernel is an open-source SDK that enables developers to integrate AI models into their applications. Part of that SDK is the *Semantic Kernel Agents Framework*, enabling the creation of agents using the same features that exist in the core Semantic Kernel framework.
22

33
## What is the Semantic Kernel Agent Framework?
44

@@ -11,35 +11,31 @@ The Semantic Kernel Agent Framework is a framework designed to help developers b
1111
The kernel is the central component of the Semantic Kernel. The kernel acts as the execution engine, managing AI interactions, function orchestration, and memory.
1212

1313
- **Agents**
14-
14+
1515
Agents are intelligent, AI-driven entities capable of reasoning and executing tasks. They use language models, functions, and memory to make decisions dynamically.
1616

17-
- **Plugins**
17+
- **Tools and Plugins**
1818

19-
Agents use plugins to perform specific tasks. Plugin functions enable agents to dynamically interact with external services or execute complex tasks.
19+
Agents use tools and plugins to perform specific tasks. Tools provide additional functionality to your agents, such as file searching or code interpreter. Plugins enable agents to dynamically interact with external services or execute complex tasks through function calling.
2020

2121
- **History**
2222

2323
Agents can maintain chat history across multiple interactions, allowing them to track previous interactions and adapt responses accordingly.
2424

25+
- **Agent Collaboration**
26+
27+
Agents can collaborate together through an **agent group chat**, which enables multiple agents to join the same chat. Agent group chats determine which agent should respond and how to determine if the conversation is finished.
28+
2529
### Types of Agents
2630

27-
The Semantic Kernel Agent Framework supports several different types of agents.
31+
The Semantic Kernel Agent Framework supports several different types of agents, including:
2832

2933
- Chat Completion Agent
3034
- OpenAI Assistant Agent
3135
- Azure AI Agent
3236

33-
## Why Use the Semantic Kernel Agent Framework?
34-
35-
TODO
36-
37-
### Getting Started
38-
39-
TODO - Create AI Foundry Project
37+
## Why you should use the Semantic Kernel Agent Framework
4038

41-
To use the Semantic Kernel Agent Framework, install the necessary package with dependencies:
39+
The Semantic Kernel Agent Framework offers a robust platform for building intelligent, autonomous, and collaborative AI agents. By leveraging this framework, you can create modular AI components that seamlessly integrate into your applications, enabling them to perform complex tasks with minimal manual intervention. The framework's design emphasizes flexibility, allowing developers to define agents tailored to specific needs, such as data analysis, API interactions, or natural language processing. This modularity ensures that your application remains adaptable as requirements evolve or new technologies emerge.
4240

43-
```sh
44-
pip install semantic-kernel[azure]
45-
```
41+
The Semantic Kernel Agent Framework can integrate agents from multiple sources, including Azure AI Agent Service, and supports both multi-agent collaboration and human-agent interaction. Agents can work together to orchestrate sophisticated workflows, where each agent specializes in a specific task, such as data collection, analysis, or decision-making. Additionally, the framework facilitates human-in-the-loop processes, enabling agents to augment human decision-making by providing insights or automating repetitive tasks. This combination of autonomy, collaboration, and interactivity makes the Semantic Kernel Agent Framework an ideal choice for applications requiring dynamic, goal-oriented behavior.
Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,6 @@
1+
Talk about parts that are unique to agent framework
2+
3+
Termination strategy
4+
handling multi agents/agent selection
5+
chat completion/conversation state
6+
streaming?
Lines changed: 3 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -1,10 +1,8 @@
1-
Now it's your opportunity to build a multi agent solution with the Semantic Kerenl SDK. In this exercise, you'll create an application that automatically triages and resolves issues presented in log files of a system. Using Azure AI Agents, you'll create an incident manager agent an a devops agent that will collaborate to fix the issues.
2-
3-
[!INCLUDE [Lab note](../../../includes/wwl/launch-exercise-note.md)]
1+
Now it's your opportunity to build a multi agent solution with the Semantic Kernel Agent Framework. In this exercise, you'll create an application that automatically triages and resolves issues presented in log files of a system. Using Azure AI Agents, you'll create an incident manager agent an a devops agent that will collaborate to fix the issues.
42

53
Launch the exercise and follow the instructions.
64

7-
[![Button to launch exercise.](../media/launch-exercise.png)](https://go.microsoft.com/fwlink/?linkid=2305092&azure-portal=true)
5+
[![Button to launch exercise.](../media/launch-exercise.png)](https://go.microsoft.com/fwlink/?linkid=2310729&azure-portal=true)
86

97
> [!TIP]
10-
> After completing the exercise, if you're finished exploring Azure AI Agents, delete the Azure resources that you created during the exercise.
8+
> After completing the exercise, if you're finished exploring multi-agents with Semantic Kernel Agent Framework, delete the Azure resources that you created during the exercise.

learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/index.yml

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -34,6 +34,7 @@ subjects:
3434
units:
3535
- learn.wwl.orchestrate-sk-multi-agent-solution.introduction
3636
- learn.wwl.orchestrate-sk-multi-agent-solution.understand-agent-framework
37+
- learn.wwl.orchestrate-sk-multi-agent-solution.agent-framework-components
3738
- learn.wwl.orchestrate-sk-multi-agent-solution.create-azure-ai-agent
3839
- learn.wwl.orchestrate-sk-multi-agent-solution.add-plugins-to-agents
3940
- learn.wwl.orchestrate-sk-multi-agent-solution.design-agent-collaboration

0 commit comments

Comments
 (0)