fixes

Author: aahill

articles/ai-foundry/agents/how-to/tools/azure-functions-samples.md

@@ -23,7 +23,7 @@ Azure AI Agents supports function calling, which allows you to describe the stru
 * A prepared environment. See the [overview](azure-functions.md) article for details.
 
 > [!NOTE] 
-> You must have a [A deployed agent with the standard setup](/azure/ai-services/agents/ai-services/agents/environment-setupchoose-your-setup). The basic agent setup is not supported.
+> You must have a [A deployed agent with the standard setup](../../environment-setup.md#choose-your-setup). The basic agent setup is not supported.
 
 ::: zone pivot="python"
 

articles/ai-foundry/agents/how-to/tools/azure-functions.md

@@ -27,7 +27,7 @@ To use all features of function calling including parallel functions, you need t
 ## Prerequisites
 
 * [Azure Functions Core Tools v4.x](/azure/azure-functions/functions-run-local)
-* [A deployed agent with the standard setup](/azure/ai-services/agents/ai-services/agents/environment-setupchoose-your-setup)
+* [A deployed agent with the standard setup](/../../environment-setup.md#choose-your-setup)
     > [!NOTE] 
     > The basic agent setup is not supported.
 * [Azurite](https://github.com/Azure/Azurite)

articles/ai-foundry/agents/how-to/tools/bing-code-samples.md

@@ -19,11 +19,11 @@ Use this article to find step-by-step instructions and code samples for Groundin
 
 ## Prerequisites
 
-* A [connected Grounding with Bing Search resource](/azure/ai-services/agents/ai-services/agents/how-to/tools/bing-groundingsetup).
+* A [connected Grounding with Bing Search resource](./bing-grounding.md#setup).
 * Your connection ID needs to be in this format: `/subscriptions/<subscription_id>/resourceGroups/<resource_group_name>/providers/Microsoft.CognitiveServices/accounts/<ai_service_name>/projects/<project_name>/connections/<connection_name>`
 
 > [!IMPORTANT]
-> There are requirements for displaying Grounding with Bing Search results. See the [overview article](/azure/ai-services/agents/ai-services/agents/how-to/tools/bing-groundinghow-to-display-grounding-with-bing-search-results) for details. 
+> There are requirements for displaying Grounding with Bing Search results. See the [overview article](./bing-grounding.md#how-to-display-grounding-with-bing-search-results) for details. 
 
 ::: zone pivot="portal"
 

articles/ai-foundry/agents/how-to/tools/openapi-spec-samples.md

@@ -35,7 +35,7 @@ Use this article to find step-by-step instructions and code samples for using Op
 
 1. Select **Next** and select your authentication method. Choose `connection` for `API key`.
    1. If you choose `connection`, you need to select the custom keys connection you have created before.
-   1. If you choose `managed identity`, you need to input the audience to get your token. An example of an audience would be `https://cognitiveservices.azure.com/` to connect to Azure AI Services. Make sure you have already set up authentication and role assignment (as described in the [section](/azure/ai-services/agents/ai-services/agents/how-to/tools/openapi-specauthenticating-with-managed-identity-microsoft-entra-id) above).
+   1. If you choose `managed identity`, you need to input the audience to get your token. An example of an audience would be `https://cognitiveservices.azure.com/` to connect to Azure AI Services. Make sure you have already set up authentication and role assignment (as described in the [section](./openapi-spec.md#authenticating-with-managed-identity-microsoft-entra-id) above).
 
 1. Copy and paste your OpenAPI specification in the text box.
 

articles/ai-foundry/agents/how-to/triggers.md

@@ -60,13 +60,13 @@ Start by adding the Azure AI Foundry Agent service connectors to your workflow.
 
 1. Depending on your use-case, choose the actions you need. 
 
-    If you want to create a new [thread](/azure/ai-services/agents/ai-services/agents/concepts/threads-runs-messagesthreads) for each new event of your trigger, add the following in sequence: 
+    If you want to create a new [thread](./concepts/threads-runs-messages/md#threads) for each new event of your trigger, add the following in sequence: 
     1. Create thread 
     1. Create run 
     1. Get run 
     1. List messages 
 
-    If you want to create a new [run](/azure/ai-services/agents/ai-services/agents/concepts/threads-runs-messagesruns) in the same thread for each new event, add the following in sequence: 
+    If you want to create a new [run](./concepts/threads-runs-messages.md#runs) in the same thread for each new event, add the following in sequence: 
 
     1. Create run 
     1. Get run
@@ -91,7 +91,7 @@ The **List Agent** connector only lists all the agents you have in your AI proje
 
 ## Configure the "create thread" connector
 
-The **create thread** connector creates a new [thread](/azure/ai-services/agents/ai-services/agents/concepts/threads-runs-messagesthreads), which is a conversation session between an Agent and a user. Threads store [messages](/azure/ai-services/agents/ai-services/agents/concepts/threads-runs-messagesmessages) and automatically handle truncation to fit content into a model's context. You can configure the **create thread** connector with the following:
+The **create thread** connector creates a new [thread](./concepts/threads-runs-messages.md#threads), which is a conversation session between an Agent and a user. Threads store [messages](./concepts/threads-runs-messages.md#messages) and automatically handle truncation to fit content into a model's context. You can configure the **create thread** connector with the following:
 
 **messages (optional)**: You can add the message you want the AI agent to respond to. Add the role as **user** for the message you want the agent to respond to. It can be the event payload from the trigger, for example a form response field. It can also be a constant message, for example always triggering with the phrase "*what is the latest AI news this week?*"  
 
@@ -120,7 +120,7 @@ The **create thread** connector creates a new [thread](/azure/ai-services/agents
 
 ## Configure the "create run" connector
 
-The **create run** connector creates a new [run](/azure/ai-services/agents/ai-services/agents/concepts/threads-runs-messagesruns), which is an activation of an Agent to begin running based on the contents of the thread. The agent uses its configuration (such as tool resources) and the thread's messages to perform tasks by calling models and tools. As part of a run, the agent appends messages to the thread. 
+The **create run** connector creates a new [run](./concepts/threads-runs-messages.md#runs), which is an activation of an Agent to begin running based on the contents of the thread. The agent uses its configuration (such as tool resources) and the thread's messages to perform tasks by calling models and tools. As part of a run, the agent appends messages to the thread. 
 
 To configure the **create run** connector, click on it and provide the following information:
 

articles/ai-foundry/agents/includes/quickstart-rest.md

@@ -6,7 +6,7 @@ ms.service: azure-ai-agent-service
 ms.topic: include
 ms.date: 02/15/2025
 ---
-| [Reference documentation](../../openai/assistants-reference.md) |
+| [Reference documentation](/rest/api/aifoundry/aiagents/) |
 
 ## Prerequisites
 

articles/ai-foundry/agents/index.yml

@@ -44,8 +44,6 @@ landingContent:
     linkLists:
       - linkListType: concept
         links:
-          - text: What are agents?
-            url: ./concepts/agents.md
           - text: Tracing with Application Insights
             url: ./concepts/tracing.md
 

articles/ai-foundry/agents/overview.md

@@ -99,7 +99,7 @@ Azure AI Foundry Agent Service provides a production-ready foundation for deploy
 
 | Capability | Azure AI Foundry Agent Service | 
 |------------|--------------------------------|
-| **1. Visibility into conversations** | Full access to structured [threads](/azure/ai-services/agents/ai-services/agents/concepts/threads-runs-messagesthreads), including both user↔agent and agent↔agent messages. Ideal for UIs, debugging, and training |
+| **1. Visibility into conversations** | Full access to structured [threads](./concepts/threads-runs-messages.md#threads), including both user↔agent and agent↔agent messages. Ideal for UIs, debugging, and training |
 | **2. Multi-agent coordination** | Built-in support for agent-to-agent messaging. |
 | **3. Tool orchestration** | Server-side execution and retry of [tool calls](how-to\tools\overview.md) with structured logging. No manual orchestration required. |
 | **4. Trust and safety** | Integrated [content filters](/azure/ai-services/agents/ai-services/openai/how-to/content-filters) help prevent misuse and mitigate prompt injection risks (XPIA). all outputs are policy-governed. |

articles/ai-foundry/agents/toc.yml

@@ -105,7 +105,7 @@ items:
         - name: Use your own resources
           href: how-to/use-your-own-resources.md
         - name: Content filtering
-          href: ../openai/how-to/content-filters.md?context=/azure/ai-services/agents/context/context
+          href: ../../ai-services/openai/how-to/content-filters.md?context=/azure/ai-services/agents/context/context
         - name: Use virtual networks
           href: how-to/virtual-networks.md
     - name: Multi-agent workflows
@@ -151,6 +151,6 @@ items:
 - name: Resources
   items: 
     - name: Support and help options
-      href: ../cognitive-services-support-options.md?context=/azure/ai-services/agents/context/context
+      href: ../../ai-services/cognitive-services-support-options.md?context=/azure/ai-services/agents/context/context
     - name: Terms of use
       href: https://www.microsoft.com/licensing/terms/productoffering/MicrosoftAzure/MCA#ServiceSpecificTerms