Skip to content

Commit 58c274f

Browse files
committed
content updates
1 parent c8509b3 commit 58c274f

File tree

7 files changed

+28
-33
lines changed

7 files changed

+28
-33
lines changed

learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/3-agent-collaboration-components.yml

Lines changed: 0 additions & 13 deletions
This file was deleted.
Lines changed: 13 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,13 @@
1+
### YamlMime:ModuleUnit
2+
uid: learn.wwl.orchestrate-sk-multi-agent-solution.design-agent-selection-strategy
3+
title: Design an agent selection strategy
4+
metadata:
5+
title: Design an agent selection strategy
6+
description: Design a strategy that determines which agent should take the next turn.
7+
ms.date: 3/18/2025
8+
author: buzahid
9+
ms.author: buzahid
10+
ms.topic: unit
11+
durationInMinutes: 1
12+
content: |
13+
[!include[](includes/3-design-agent-selection-strategy.md)]
Original file line numberDiff line numberDiff line change
@@ -1,13 +1,13 @@
11
### YamlMime:ModuleUnit
2-
uid: learn.wwl.orchestrate-sk-multi-agent-solution.define-chat-completion
3-
title: Define chat completion
2+
uid: learn.wwl.orchestrate-sk-multi-agent-solution.define-chat-termination-strategy
3+
title: Define a chat termination strategy
44
metadata:
5-
title: Define chat completion
5+
title: Define a chat termination strategy
66
description: Learn how to manage the completion state of the multi-agent collaboration.
77
author: buzahid
88
ms.author: buzahid
99
ms.date: 03/14/2025
1010
ms.topic: unit
1111
durationInMinutes: 6
1212
content: |
13-
[!include[](includes/4-define-chat-completion.md)]
13+
[!include[](includes/4-define-chat-termination-strategy.md)]

learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/includes/2-understand-agent-framework.md

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -34,12 +34,12 @@ The features that power Semantic Kernel are also still available within the Agen
3434

3535
The Semantic Kernel Agent Framework supports several different types of agents, including:
3636

37-
- Azure AI Agent
38-
- Chat Completion Agent
39-
- OpenAI Assistant Agent
37+
- **Azure AI Agent** - a specialized agent within the Semantic Kernel Agent Framework. The `AsureAIAgent` type is designed to provide advanced conversational capabilities with seamless tool integration. It automates tool calling and securely manages conversation history using threads, reducing the overhead of maintaining state. The `AzureAIAgent` also supports a variety of built-in tools, including file retrieval, code execution, and data interaction via Bing, Azure AI Search, Azure Functions, and OpenAPI.
4038

41-
## Why you should use the Semantic Kernel Agent Framework
39+
- **Chat Completion Agent**: designed for chat completion and conversation interfaces. The `ChatCompletionAgent` type mirrors the features and patterns in the underlying AI Service to support natural language processing, contextual understanding, and dialogue management.
40+
41+
- **OpenAI Assistant Agent**: designed for more advanced capabilities and multi-step tasks. The `OpenAIAssistantAgent` type supports goal-driven interactions with additional features like code interpretation and file search.
4242

43-
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.
43+
## Why you should use the Semantic Kernel Agent Framework
4444

45-
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.
45+
The Semantic Kernel Agent Framework offers a robust platform for building intelligent, autonomous, and collaborative AI agents. The 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. The framework also 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: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
A key part of the Semantic Kernel Agent Framework is a system designed to facilitate intelligent, multi-agent interactions. Agent collaboration, called `AgentGroupChat`, has critical components to consider that aren't necessary with single agents or non-agentic Semantic Kernel applications.
22

3-
Each of these sections discusses an example multi-agent solution, where we have two agents:
3+
The following units discuss an example multi-agent solution, where we have two agents in a writer-reviewer scenario:
44

55
- A copywriter agent who writes online content, called _CopywriterAgent_.
66
- A creative director only reviewing the proposals, called _ReviewingDirectorAgent_.

learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/includes/4-define-chat-completion.md renamed to learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/includes/4-define-chat-termination-strategy.md

Lines changed: 1 addition & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -1,15 +1,10 @@
11
Multi-turn conversations have responses returned asynchronously, so the conversation can develop naturally. However, the agents need to know when to stop a conversation, which is determined by the **termination strategy**
22

3-
This unit uses the example multi-agent solution where we have two agents:
4-
5-
- A copywriter agent who writes online content, called _CopywriterAgent_.
6-
- A creative director only reviewing the proposals, called _ReviewingDirectorAgent_.
7-
83
## Termination strategy
94

105
A termination strategy ensures that conversations or tasks conclude appropriately. This strategy prevents unnecessary messages to the user, limits resource usage, and improves the overall user experience.
116

12-
For example, once the _ReviewingDirectorAgent_ reviews and approves our scrubbing brush slogan from the _CopywriterAgent_, us humans know the conversation should be over. However, if we don't define when to terminate the conversation, the _CopywriterAgent_ is going to keep submitting slogans unnecessarily.
7+
For example, in the writer-reviewer agent scenario, once the _ReviewingDirectorAgent_ reviews and approves our scrubbing brush slogan from the _CopywriterAgent_, us humans know the conversation should be over. However, if we don't define when to terminate the conversation, the _CopywriterAgent_ is going to keep submitting slogans unnecessarily.
138

149
### Why use a termination strategy?
1510

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

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -13,8 +13,8 @@ summary: Learn how to use the Semantic Kernel SDK to develop your own AI agents
1313
abstract: |
1414
By the end of this module, you'll be able to:
1515
- Build AI agents using the Semantic Kernel SDK
16-
- Create custom plugin functions for your AI agents
1716
- Develop multi-agent solutions
17+
- Create custom selection and termination strategies for agent collaboration
1818
prerequisites: |
1919
- Familiarity with Azure and the Azure portal.
2020
- An understanding of generative AI. You can learn more with [Fundamentals of Generative AI](/training/modules/fundamentals-generative-ai/).
@@ -34,8 +34,8 @@ 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-collaboration-components
38-
- learn.wwl.orchestrate-sk-multi-agent-solution.define-chat-completion
37+
- learn.wwl.orchestrate-sk-multi-agent-solution.design-agent-selection-strategy
38+
- learn.wwl.orchestrate-sk-multi-agent-solution.define-chat-termination-strategy
3939
- learn.wwl.orchestrate-sk-multi-agent-solution.exercise
4040
- learn.wwl.orchestrate-sk-multi-agent-solution.knowledge-check
4141
- learn.wwl.orchestrate-sk-multi-agent-solution.summary

0 commit comments

Comments
 (0)