Merge pull request #287 from MicrosoftDocs/main638888346275146148sync_temp

Repo sync for protected branch

Author: westey-m

semantic-kernel/Frameworks/agent/agent-orchestration/concurrent.md

@@ -14,7 +14,9 @@ ms.service: semantic-kernel
 > [!IMPORTANT]
 > Agent Orchestration features in the Agent Framework are in the experimental stage. They are under active development and may change significantly before advancing to the preview or release candidate stage.
 
-The concurrent pattern enables multiple agents to work on the same task in parallel. Each agent processes the input independently, and their results are collected and aggregated. This approach is well-suited for scenarios where diverse perspectives or solutions are valuable, such as brainstorming, ensemble reasoning, or voting systems.
+Concurrent orchestration enables multiple agents to work on the same task in parallel. Each agent processes the input independently, and their results are collected and aggregated. This approach is well-suited for scenarios where diverse perspectives or solutions are valuable, such as brainstorming, ensemble reasoning, or voting systems.
+
+To learn more about the pattern, such as when to use the pattern or when to avoid the pattern, see [Concurrent orchestration](/azure/architecture/ai-ml/guide/ai-agent-design-patterns#concurrent-orchestration).
 
 ## Common Use Cases
 

semantic-kernel/Frameworks/agent/agent-orchestration/group-chat.md

@@ -16,6 +16,8 @@ ms.service: semantic-kernel
 
 Group chat orchestration models a collaborative conversation among agents, optionally including a human participant. A group chat manager coordinates the flow, determining which agent should respond next and when to request human input. This pattern is powerful for simulating meetings, debates, or collaborative problem-solving sessions.
 
+To learn more about the pattern, such as when to use the pattern or when to avoid the pattern in your workload, see [Group chat orchestration](/azure/architecture/ai-ml/guide/ai-agent-design-patterns#group-chat-orchestration).
+
 ## Common Use Cases
 
 Agents representing different departments discuss a business proposal, with a manager agent moderating the conversation and involving a human when needed:

semantic-kernel/Frameworks/agent/agent-orchestration/handoff.md

@@ -14,7 +14,9 @@ ms.service: semantic-kernel
 > [!IMPORTANT]
 > Agent Orchestration features in the Agent Framework are in the experimental stage. They are under active development and may change significantly before advancing to the preview or release candidate stage.
 
-Handoff orchestration allows agents to transfer control to one another based on the context or user request. Each agent can “handoff” the conversation to another agent with the appropriate expertise, ensuring that the right agent handles each part of the task. This is particularly useful in customer support, expert systems, or any scenario requiring dynamic delegation.
+Handoff orchestration allows agents to transfer control to one another based on the context or user request. Each agent can "handoff" the conversation to another agent with the appropriate expertise, ensuring that the right agent handles each part of the task. This is particularly useful in customer support, expert systems, or any scenario requiring dynamic delegation.
+
+To learn more about the pattern, such as when to use the pattern or when to avoid the pattern in your workload, see [Handoff orchestration](/azure/architecture/ai-ml/guide/ai-agent-design-patterns#handoff-orchestration).
 
 ## Common Use Cases
 

semantic-kernel/Frameworks/agent/agent-orchestration/index.md

@@ -22,9 +22,13 @@ Traditional single-agent systems are limited in their ability to handle complex,
 
 ## Orchestration Patterns
 
-Semantic Kernel supports several orchestration patterns, each designed for different collaboration scenarios. These patterns are available as part of the framework and can be easily extended or customized.
+Like well-known cloud design patterns, agent orchestration patterns are technology agnostic approaches to coordinating multiple agents to work together towards a common goal. To learn more about the patterns themselves, refer to the [AI agent orchestration patterns](/azure/architecture/ai-ml/guide/ai-agent-design-patterns) documentation.
 
-## Supported Orchestration Patterns
+<a name='supported-orchestration-patterns'></a>
+
+## Supported Orchestration Patterns in Semantic Kernel
+
+Semantic Kernel supports you by implementing these orchestration patterns directly in the SDK. These patterns are available as part of the framework and can be easily extended or customized so you can tune your agent collaboration scenario.
 
 | Pattern                       | Description                                                                                                                                                                         | Typical Use Case                                                      |
 | ----------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------- |

semantic-kernel/Frameworks/agent/agent-orchestration/magentic.md

@@ -24,6 +24,8 @@ The Magentic manager maintains a shared context, tracks progress, and adapts the
 > [!TIP]
 > The name "Magentic" comes from "Magentic-One". "Magentic-One" is a multi-agent system that includes a set of agents, such as the `WebSurfer` and `FileSurfer`. The Semantic Kernel Magentic orchestration is inspired by the Magentic-One system where the `Magentic` manager coordinates a team of specialized agents to solve complex tasks. However, it is not a direct implementation of the Magentic-One system and does not feature the agents from the Magentic-One system.
 
+To learn more about the pattern, such as when to use the pattern or when to avoid the pattern in your workload, see [Magentic orchestration](/azure/architecture/ai-ml/guide/ai-agent-design-patterns#magentic-orchestration).
+
 ## Common Use Cases
 
 A user requests a comprehensive report comparing the energy efficiency and CO₂ emissions of different machine learning models. The Magentic manager first assigns a research agent to gather relevant data, then delegates analysis and computation to a coder agent. The manager coordinates multiple rounds of research and computation, aggregates the findings, and produces a detailed, structured report as the final output.

semantic-kernel/Frameworks/agent/agent-orchestration/sequential.md

@@ -14,7 +14,9 @@ ms.service: semantic-kernel
 > [!IMPORTANT]
 > Agent Orchestration features in the Agent Framework are in the experimental stage. They are under active development and may change significantly before advancing to the preview or release candidate stage.
 
-In the sequential pattern, agents are organized in a pipeline. Each agent processes the task in turn, passing its output to the next agent in the sequence. This is ideal for workflows where each step builds upon the previous one, such as document review, data processing pipelines, or multi-stage reasoning.
+In sequential orchestration, agents are organized in a pipeline. Each agent processes the task in turn, passing its output to the next agent in the sequence. This is ideal for workflows where each step builds upon the previous one, such as document review, data processing pipelines, or multi-stage reasoning.
+
+To learn more about the pattern, such as when to use the pattern or when to avoid the pattern in your workload, see [Sequential orchestration](/azure/architecture/ai-ml/guide/ai-agent-design-patterns#sequential-orchestration).
 
 ## Common Use Cases
 

semantic-kernel/Frameworks/agent/agent-types/responses-agent.md

@@ -94,7 +94,7 @@ AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME=""
 Set the appropriate variable depending on which provider you're using.
 
 > [!TIP]
-> The minimum allowed Azure OpenAI api version is `2025-03-01-preview`. Please visit the following [link](azure/ai-services/openai/how-to/responses) to view region availability, model support, and further details.
+> The minimum allowed Azure OpenAI api version is `2025-03-01-preview`. Please visit the following [link](/azure/ai-services/openai/how-to/responses) to view region availability, model support, and further details.
 
 To create an `AzureResponsesAgent` to use with Azure OpenAI models: