more edits

Author: HeidiSteen

articles/search/search-agentic-retrieval-how-to-pipeline.md

@@ -105,12 +105,12 @@ Development tasks on the Azure AI Search side include:
 + [Call the retriever](search-agentic-retrieval-how-to-retrieve.md) and provide a query, conversation, and override parameters.
 + Parse the response for the parts you want to include in your chat application. For many scenarios, just the content portion of the response is sufficient. You can also try [answer synthesis](search-agentic-retrieval-how-to-synthesize.md) for a simpler workflow.
 
-Developments in Azure AI Agent side include:
+Developments on the Azure AI Agent side include:
 
 + Set up the AI project client and an AI agent.
 + Add a tool to coordinate calls from the AI agent to the retriever and knowledge agent.
 
-Query processing is initiated by a client app, such as a chat bot, that calls the AI agent. The AI agent is configured to use a tool that orchestrates the requests and directs the responses. When the chat bot calls the agent, the tool calls the retriever on Azure AI Search, waits for the response, and then sends the response back to the AI agent and chat bot.
+Query processing is initiated by user interaction in a client app, such as a chat bot, that calls an AI agent. The AI agent is configured to use a tool that orchestrates the requests and directs the responses. When the chat bot calls the agent, the tool calls the [retriever](search-agentic-retrieval-how-to-retrieve.md) on Azure AI Search, waits for the response, and then sends the response back to the AI agent and chat bot. In Azure AI Search, you can use [answer synthesis](search-agentic-retrieval-how-to-synthesize.md) to obtain an LLM-generated response from within the query pipeline, or you can call an LLM in your code if you want more control over answer generation.
 
 ## Components of the solution
 

articles/search/search-agentic-retrieval-how-to-retrieve.md

@@ -16,7 +16,7 @@ ms.date: 08/29/2025
 
 In Azure AI Search, *agentic retrieval* is a new parallel query architecture that uses a large language model (LLM) for query planning. It generates subqueries that broaden the scope of what's searchable and relevant. It incorporates chat history for context. The LLM studies the query and subdivides it into more targeted queries, using different phrases and terminology for subquery composition.
 
-This article explains how to use the [**retrieve method**](/rest/api/searchservice/knowledge-retrieval/retrieve?view=rest-searchservice-2025-08-01-preview&preserve-view=true) that invokes a knowledge agent and parallel query processing. It's updated for the new 2025-08-01-preview, which introduces breaking changes from the 2025-05-01-preview. For help with breaking changes, see [Migrate your agentic retrieval code](search-agentic-retrieval-how-to-migrate.md).
+This article explains how to use the [**retrieve action**](/rest/api/searchservice/knowledge-retrieval/retrieve?view=rest-searchservice-2025-08-01-preview&preserve-view=true) that invokes a knowledge agent and parallel query processing. It's updated for the new 2025-08-01-preview, which introduces breaking changes from the 2025-05-01-preview. For help with breaking changes, see [Migrate your agentic retrieval code](search-agentic-retrieval-how-to-migrate.md).
 
 This article also explains the three components of the retrieval response: 
 
@@ -27,7 +27,9 @@ This article also explains the three components of the retrieval response:
 The retrieve request can include instructions for query processing that override the defaults set on the knowledge agent.
 
 > [!NOTE]
-> By default, there's no model-generated "answer" in the response and you should pass the extracted response to an LLM so that it can ground its answer based on the search results. For an end-to-end example that includes this step, see [Build an agent-to-agent retrieval solution ](search-agentic-retrieval-how-to-pipeline.md) or [Azure OpenAI Demo](https://github.com/Azure-Samples/azure-search-openai-demo). Alternatively, you can use [answer synthesis](search-agentic-retrieval-how-to-synthesize.md) to bring answer formulation into the agentic pipeline. In this workflow, the knowledge agent output consists of LLM-formulated answers instead of the raw search results.
+> By default, there's no model-generated "answer" in the response and you should pass the extracted response to an LLM so that it can ground its answer based on the search results. For an end-to-end example that includes this step, see [Build an agent-to-agent retrieval solution ](search-agentic-retrieval-how-to-pipeline.md) or [Azure OpenAI Demo](https://github.com/Azure-Samples/azure-search-openai-demo).
+>
+>Alternatively, you can use [answer synthesis](search-agentic-retrieval-how-to-synthesize.md) to bring answer formulation into the agentic pipeline. In this workflow, the retriever response consists of LLM-formulated answers instead of the raw search results.
 
 ## Prerequisites