cela updates

Author: aahill

articles/ai-foundry/agents/how-to/tools/deep-research.md

@@ -12,7 +12,7 @@ ms.topic: how-to
 
 # Deep Research tool (preview)
 
-The Deep Research model in the Azure AI Foundry Agent Service enables you to use web-based research capability, and integrate it with your systems.
+The Deep Research tool in the Azure AI Foundry Agent Service enables you to integrate a web-based research capability into your systems. The Deep Research capability is a specialized AI capability designed to perform in-depth, multi-step research using data from the public web.  
 
 > [!IMPORTANT]
 > * The Deep Research tool uses **Grounding with Bing Search**. Be sure to read and understand all stipulations of its use, including potential [costs](https://www.microsoft.com/bing/apis/grounding-pricing) that can be incurred, the [terms of use](https://www.microsoft.com/bing/apis/grounding-legal), and [use and display requirements](./bing-grounding.md#how-to-display-grounding-with-bing-search-results). See the [Grounding with Bing Search](./bing-grounding.md) documentation for more information.
@@ -22,25 +22,25 @@ The Deep Research model in the Azure AI Foundry Agent Service enables you to use
 > When using Grounding with Bing Search, only the Bing search query, tool parameters, and your resource key are sent to Bing, and no end user-specific information is included. Your resource key is sent to Bing solely for billing and rate limiting purposes. 
 
 ## Usage support
-The deep research tool is a **code-only release** and available for use using the Agents Python SDK once you complete the AI Foundry project setup described in the following sections.
+The deep research tool is a **code-only release** and available for use using the Agents Python SDK once you complete the Azure AI Foundry project setup described in the following sections.
 
 |Azure AI foundry portal  | Python SDK |	C# SDK | JavaScript SDK | REST API |Basic agent setup | Standard agent setup |
 |---------|---------|---------|---------|---------|---------|---------|
 |  | ✔️ |  |  |  | ✔️  | ✔️ |
 
 > [!NOTE]
-> Once the agent is running, some elements of the agent and thread runs can show up in the Foundry user interface.
+> Once the agent is running, some elements of the agent and thread runs can show up in the Azure AI Foundry user interface.
 
 ## Knowledge source support
 The deep research tool is tightly integrated with Grounding with Bing Search and only supports web-based research.
 
 ## How Deep Research works
 
-At its core, the Deep Research tool orchestrates a multi-step research pipeline that’s tightly integrated with Grounding with Bing Search and the Azure OpenAI deep research model.
+At its core, the Deep Research tool orchestrates a multi-step research pipeline uses the Azure OpenAI's `o3-deep-research` model together with Grounding with Bing Search to autonomously search for and read information from multiple online sources appropriate to the user prompt. This enables the Deep Research tool to generate thorough, documented, and cited reports on complex topics. 
 
 ### Deep research model deployment
 
-The Deep research tool uses the `o3-deep-research` model for its research tasks. It is a fine-tuned version of the `o3` model designed to perform automated detailed analysis of knowledge sources and create detailed research reports.
+The Deep Research tool uses the Azure OpenAI `o3-deep-research` model for its research tasks. The model was fine-tuned on the Azure OpenAI `o3` reasoning model.
 
 **Key features**:
 - Handles text, images, and PDFs as part of its research tasks.
@@ -55,33 +55,33 @@ The Deep research tool uses the `o3-deep-research` model for its research tasks.
 
 ### GPT model deployment for clarifying intent
 
-The deep research tool uses a second model deployment to clarify the question, gather additional context if needed, and precisely scope the research task. This ensures the agent’s output is both relevant and actionable, and that every search is optimized for your business scenario.
+The Deep Research tool uses a second model deployment to clarify the question contained in the user prompt, gather additional context if needed, and precisely scope the research task. This helps make the output of an agent using the Deep Research tool more relevant and actionable, and can help optimize the search for your business scenario.
 
-This second model can be any of the GPT-series models including GPT-4o and GPT-4.1.
+This second model is selected by the customer during configuration of the Deep Research tool and can be any of the GPT-series models including GPT-4o and GPT-4.1.
 
 ### Grounding with Bing Search
 
-Once the task is scoped, the agent invokes the [Grounding with Bing Search](./bing-grounding.md) tool to gather a curated set of high-quality, recent web data. This ensures the research model is working from a foundation of authoritative, up-to-date sources. 
+Once the task is scoped, the agent using the Deep Research tool invokes the [Grounding with Bing Search](./bing-grounding.md) tool to gather a curated set of recent web data designed to provide the research model with a foundation of authoritative, high quality, up-to-date sources. 
 
 ### Task execution
 
-The Deep Research model then starts the research task execution. This involves thinking reasoning, analyzing, and synthesizing information across all discovered sources. Unlike simple summarization, it reasons step-by-step, pivots as it encounters new insights, and composes a comprehensive answer that's sensitive to nuance, ambiguity, and emerging patterns in the data. 
+The Deep Research model then executes the research task. This involves reasoning, analyzing, and synthesizing information across all discovered sources. Unlike simple summarization, it reasons step-by-step, pivots as it encounters new insights, and composes a comprehensive answer that's sensitive to nuance, ambiguity, and emerging patterns in the data. 
 
 ### Transparency, safety, and compliance
 
-The output is a structured report that documents not only the answer, but also the model's reasoning path, source citations, and any clarifications requested during the session. This makes every answer fully auditable.
+The output is a structured report that documents not only the comprehensive answer, but also provides source citations and describes the model's reasoning path, including any clarifications requested during the session. This makes every answer fully auditable. See the [Transparency note for Azure OpenAI](/azure/ai-foundry/responsible-ai/openai/transparency-note) for more information.
 
 ## Prerequisites
-- If you already have access to the `o3` model no request is required for the deep research model. Otherwise, fill out the [request form](https://aka.ms/OAI/deepresearchaccess). 
+- If you already have access to the Azure OpenAI `o3` model, no request is required to access the `o3-deep-research`  model. Otherwise, fill out the [request form](https://aka.ms/OAI/deepresearchaccess). 
 - An Azure subscription with the ability to create resources [Set up your environment](../../environment-setup.md)
-- [Grounding with Bing Search tool](./bing-grounding.md) resource for connecting to your AI Foundry project.
+- [Grounding with Bing Search tool](./bing-grounding.md) resource for connecting to your Azure AI Foundry project.
 - [Model deployments](../../../model-inference/how-to/create-model-deployments.md) for the following models
     - `o3-deep-research` version `2025-06-26`. This model is available in `West US` and `Norway East`.
-    - Any GPT model like the `gpt-4o` for intent clarification.
+    - Any Azure OpenAI GPT model like `gpt-4o` for intent clarification.
 
 ## Setup 
 
-To use the Deep Research tool, you need to create the AI Foundry type project, add your Grounding with Bing Search resource as a new connection, deploy the deep research model, and deploy the GPT model. 
+To use the Deep Research tool, you need to create the Azure AI Foundry type project, add your Grounding with Bing Search resource as a new connection, deploy the `o3-deep-research-model`, and deploy the selected Azure OpenAI GPT model. 
 
 :::image type="content" source="../../media/tools/deep-research/setup-deep-research-tool.png" alt-text="A diagram of the steps to set up the deep research tool." lightbox="../../media/tools/deep-research/setup-deep-research-tool.png":::
 
@@ -105,13 +105,13 @@ To use the Deep Research tool, you need to create the AI Foundry type project, a
 
     :::image type="content" source="../../media/tools/deep-research/deep-research-tool-step-5.png" alt-text="A screenshot of the models and endpoints page." lightbox="../../media/tools/deep-research/deep-research-tool-step-5.png":::
 
-1. Deploy the deep research model.
+1. Deploy the `o3-deep-research-model` model.
 
     :::image type="content" source="../../media/tools/deep-research/deep-research-tool-step-6.png" alt-text="A screenshot of a deep research model deployment." lightbox="../../media/tools/deep-research/deep-research-tool-step-6.png":::
 
-1. Deploy a GPT model. For example gpt-4o.
+1. Deploy a Azure OpenAI GPT model. For example `gpt-4o`.
 
-    :::image type="content" source="../../media/tools/deep-research/deep-research-tool-step-7.png" alt-text="A screenshot of a GPT 4o model deployment." lightbox="../../media/tools/deep-research/deep-research-tool-step-7.png":::
+    :::image type="content" source="../../media/tools/deep-research/deep-research-tool-step-7.png" alt-text="A screenshot of an Azure OpenAI GPT 4o model deployment." lightbox="../../media/tools/deep-research/deep-research-tool-step-7.png":::
 
 ## Next steps