Build custom connectors with AI in Microsoft Sentinel
In brief
The article now uses clearer titles and headings, adds setup and validation guidance, clarifies the AI-assisted Visual Studio Code workflow, and updates screenshots and metadata.
What Defender admins need to know
Administrators and connector developers can follow the revised process more easily when creating, refining, and validating custom Sentinel connectors.
Summaries are generated from the documentation change itself.
Documentation change
The comparison below shows only the changed extract. Use the full-page view for complete context.
Get started withBuild custom connectors usingwith AI agent in Microsoft Sentinel
The Microsoft Sentinel connector builder agent builds data connectors in minutes using the AI‑assisted workflow in GitHub Copilot using the Microsoft Sentinel extension for Visual Studio Code (VS Code). with GitHub Copilot. This low‑code experience guides developers and Independent Software Vendors (ISVs) end‑to‑end by autonomously generating schemas, deployment assets, connector UI, secure secret handling, and polling logic. Built‑in validation surfaces any polling issues early, so you can validate event logs before deploying and ingesting data.
The Sentinel Connectorconnector builder agent helps you:
Reduce manual time and effort in authoring Codeless Connector Framework (CCF)–based connectors
Microsoft Sentinel Contributor role to create or modify Sentinel data connectors
Benefits of Connectorsconnectors with Agenticagentic experience
The Sentinel Connectorconnector builder agent can reduce connector development time from weeks to hours for many common scenarios. Tasks that previously required multiple tools, manual handoffs, and repeated validation cycles can now be completed inline, enabling faster iteration and quicker readiness for deployment.
| Area | Non-AI connector development process | VS Code extension with Connector Builder Agent |
|---|
Create a custom connector using Sentinel connector builder agent
The following steps show how to create, validate, and deploy a custom Microsoft Sentinel connector using the Sentinel Connector Builderconnector builder agent in VS Code.
Step 1: Install and open the Sentinel extension for VS Code
To set up your development environment, follow these steps:
Install Microsoft Sentinel extension for Visual Studio Code and reload VS Code if prompted.
Create and open an empty folder in File explorer. All agent-generated files are locally saved in this folder.
Step 2: Prompt the Sentinel Connectorconnector builder agent
To create a connector with the agent, follow these steps:
Open the VS Code chat and set the chat to Agent mode.
For example, enter the prompt as follows:
@sentinel /create-connector Create a connector for Contoso. Here are the API docs: https://contoso-security-api.azurewebsites.net/v0101/api-doc:::image type="content" source="media/custom-connector-builder-agent/connector-vscode-prompt-agent.png" alt-text="Screenshot of
the agent prompt in custom connector inVS Code Copilot chat in agent mode with the @sentinel /create-connector prompt" lightbox="media/custom-connector-builder-agent/connector-vscode-prompt-agent.png":::Provide the source API
information,information and authentication methods to generate the appropriate connector pattern.
Step 3: Generate or update connector artifacts
Based on your input, the agent generates the following four files:
- Schema and table references aligned with Sentinel requirements
The illustrationfollowing screenshot shows the four JSON connector files the agent generated.
:::image type="content" source="media/custom-connector-builder-agent/connector-files-sample.png" alt-text="Screenshot of four JSON connector files generated by the Sentinel connector file generatedbuilder agent in VS Code" lightbox="media/custom-connector-builder-agent/connector-files-sample.png":::
Refine the connector using the agent or by editing the generated JSON files directly. For example:
Ask the agent to modify the description, author name, or other fields
Update ingestion logic for table name
Validate the connector configuration
To confirm the connector can reach your data source API and retrieve events, follow these steps:
To validate the API for data source events, right click on the folder that contains the ARM template and select Microsoft Sentinel > Test Connector.
:::image type="content" source="media/custom-connector-builder-agent/connector-validation.png" alt-text="Screenshot of the Test Connector pane in VS Code with authentication fields for validating the connector API" lightbox="media/custom-connector-builder-agent/connector-validation.png":::
In the Test Connector pane, enter the authentication details for your data source API, and then select Connect.
- On the Events tab, review the request headers and the events returned by the API.
After you validate the connection, select Disconnect to stop the polling session.
Deploy the connector
To deploy the connector to a Microsoft Sentinel workspace, follow these steps:
After the validation test succeeds, select Deploy in the chat window to start deploying the connector.
:::image type="content" source="media/custom-connector-builder-agent/connector-deploy.png" alt-text="Screenshot of VS Code Copilot chat window with the Deploy button to deploy the Sentinel connector" lightbox="media/custom-connector-builder-agent/connector-deploy.png":::
The extension opens a panel where you can choose from your available Microsoft Sentinel workspaces.
Select a workspace, then select Deploy to deploy the connector to that workspace.
:::image type="content" source="media/custom-connector-builder-agent/connector-workspace-deploy.png" alt-text="Screenshot of the Microsoft Sentinel workspace selection panel in VS Code for deploying the connector" lightbox="media/custom-connector-builder-agent/connector-workspace-deploy.png":::
Alternatively, right-click the folder that contains the generated files, select Microsoft Sentinel > Deploy Connector.
:::image type="content" source="media/custom-connector-builder-agent/connector-files-deploy.png" alt-text="Screenshot of the VS Code right-click context menu showing the Microsoft Sentinel Deploy Connector option" lightbox="media/custom-connector-builder-agent/connector-files-deploy.png":::
When deployment completes, a success message appears in the Output window.
:::image type="content" source="media/custom-connector-builder-agent/successful-deployment.png" alt-text="Screenshot of the VS Code Output window showing a successful connector deployment message" lightbox="media/custom-connector-builder-agent/successful-deployment.png":::
Get help
- For ISV partners building integrations, contact: [email protected]
- For technical questions, use Microsoft Q&A with the tag 'azure-sentinel'
@@ -1,20 +1,22 @@ ----title: Get started with custom connectors using AI agent in Microsoft Sentinel-description: Custom Data connectors using AI agent in Microsoft Sentinel Visual Studio Code extension+title: Build custom connectors with AI in Microsoft Sentinel+description: Build custom Microsoft Sentinel data connectors in minutes with the AI connector builder agent in Visual Studio Code. Reduce development time from weeks to hours. ms.author: edbaynash author: EdB-MSFT ms.reviewer: krishsa-ms.topic: feature-availability-ms.date: 03/27/2026+ms.topic: how-to+ms.date: 03/27/2026+ai-usage: ai-assisted+ms.custom: msecd-doc-authoring-1012 #customer intent: As a security analyst, I want to easily create custom connectors in Microsoft Sentinel using an AI agent, so that I can quickly integrate new data sources without extensive manual effort. --- -# Get started with custom connectors using AI agent in Microsoft Sentinel+# Build custom connectors with AI in Microsoft Sentinel -The Microsoft Sentinel connector builder agent builds data connectors in minutes using the AI‑assisted workflow in GitHub Copilot using the Microsoft Sentinel extension for Visual Studio Code (VS Code). This low‑code experience guides developers and Independent Software Vendors (ISVs) end‑to‑end by autonomously generating schemas, deployment assets, connector UI, secure secret handling, and polling logic. Built‑in validation surfaces any polling issues early, so you can validate event logs before deploying and ingesting data.+The Microsoft Sentinel connector builder agent builds data connectors in minutes using the AI‑assisted workflow in the Microsoft Sentinel extension for Visual Studio Code (VS Code) with GitHub Copilot. This low‑code experience guides developers and Independent Software Vendors (ISVs) end‑to‑end by autonomously generating schemas, deployment assets, connector UI, secure secret handling, and polling logic. Built‑in validation surfaces any polling issues early, so you can validate event logs before deploying and ingesting data. -The Sentinel Connector builder agent helps you:+The Sentinel connector builder agent helps you: - Reduce manual time and effort in authoring Codeless Connector Framework (CCF)–based connectors @@ -37,9 +39,9 @@ Before you begin, ensure that you meet the following requirements: - Microsoft Sentinel [Contributor](../roles.md#built-in-azure-roles-for-microsoft-sentinel) role to create or modify Sentinel data connectors - [Claude Sonnet 4.5 or later](https://claude.ai/login) -## Benefits of Connectors with Agentic experience+## Benefits of connectors with agentic experience -The Sentinel Connector builder agent can **reduce connector development time from weeks to hours** for many common scenarios. Tasks that previously required multiple tools, manual handoffs, and repeated validation cycles can now be completed inline, enabling faster iteration and quicker readiness for deployment.+The Sentinel connector builder agent can **reduce connector development time from weeks to hours** for many common scenarios. Tasks that previously required multiple tools, manual handoffs, and repeated validation cycles can now be completed inline, enabling faster iteration and quicker readiness for deployment. |Area|Non-AI connector development process|VS Code extension with Connector Builder Agent| | -------- | -------- | -------- |@@ -50,15 +52,19 @@ The Sentinel Connector builder agent can **reduce connector development time fro ## Create a custom connector using Sentinel connector builder agent -The following steps show how to create, validate, and deploy a custom Microsoft Sentinel connector using the Sentinel Connector Builder agent in VS Code.+The following steps show how to create, validate, and deploy a custom Microsoft Sentinel connector using the Sentinel connector builder agent in VS Code. -### Step 1: Install and open the Sentinel extension for VS Code +### Install and open the Sentinel extension for VS Code ++To set up your development environment, follow these steps: 1. [Install Microsoft Sentinel extension for Visual Studio Code](/azure/sentinel/datalake/notebooks) and reload VS Code if prompted. 1. Create and open an empty folder in File explorer. All agent-generated files are locally saved in this folder. -### Step 2: Prompt the Sentinel Connector builder agent+### Prompt the Sentinel connector builder agent++To create a connector with the agent, follow these steps: 1. Open the VS Code chat and set the chat to Agent mode. @@ -66,17 +72,17 @@ The following steps show how to create, validate, and deploy a custom Microsoft For example, enter the prompt as follows: - ``` + ```text @sentinel /create-connector Create a connector for Contoso. Here are the API docs: https://contoso-security-api.azurewebsites.net/v0101/api-doc ``` - :::image type="content" source="media/custom-connector-builder-agent/connector-vscode-prompt-agent.png" alt-text="Screenshot of the agent prompt in custom connector in VS Code" lightbox="media/custom-connector-builder-agent/connector-vscode-prompt-agent.png":::+ :::image type="content" source="media/custom-connector-builder-agent/connector-vscode-prompt-agent.png" alt-text="Screenshot of VS Code Copilot chat in agent mode with the @sentinel /create-connector prompt" lightbox="media/custom-connector-builder-agent/connector-vscode-prompt-agent.png"::: -1. Provide the source API information, authentication methods to generate the appropriate connector pattern.+1. Provide the source API information and authentication methods to generate the appropriate connector pattern. -### Step 3: Generate or update connector artifacts+### Generate or update connector artifacts Based on your input, the agent generates the following four files: @@ -88,16 +94,16 @@ Based on your input, the agent generates the following four files: - Schema and table references aligned with Sentinel requirements -The illustration shows the JSON connector files generated.+The following screenshot shows the four JSON connector files the agent generated. - :::image type="content" source="media/custom-connector-builder-agent/connector-files-sample.png" alt-text="Screenshot of the connector file generated in VS Code" lightbox="media/custom-connector-builder-agent/connector-files-sample.png"::: + :::image type="content" source="media/custom-connector-builder-agent/connector-files-sample.png" alt-text="Screenshot of four JSON connector files generated by the Sentinel connector builder agent in VS Code" lightbox="media/custom-connector-builder-agent/connector-files-sample.png"::: >[!NOTE] > During agent evaluation, select **Allow responses once** to approve changes, or select the option **Bypass Approvals** in the chat. It might take up to several minutes for the evaluations to finish. -Iteratively refine the connector using agent or inline directly into the JSON files generated. For example:+Refine the connector using the agent or by editing the generated JSON files directly. For example: -- Ask the agent to modify description, author name etc.+- Ask the agent to modify the description, author name, or other fields - Update ingestion logic for table name @@ -106,11 +112,13 @@ Iteratively refine the connector using agent or inline directly into the JSON fi >[!IMPORTANT] > Do not edit or modify the file while it is building. If a field on the file shows an error, it means the build is still in progress. -### Step 4: Validate the connector configuration+### Validate the connector configuration++To confirm the connector can reach your data source API and retrieve events, follow these steps: 1. To validate the API for data source events, right click on the folder that contains the ARM template and select **Microsoft Sentinel** > **Test Connector**. - :::image type="content" source="media/custom-connector-builder-agent/connector-validation.png" alt-text="Screenshot of the validation step for custom connector in VS Code" lightbox="media/custom-connector-builder-agent/connector-validation.png":::+ :::image type="content" source="media/custom-connector-builder-agent/connector-validation.png" alt-text="Screenshot of the Test Connector pane in VS Code with authentication fields for validating the connector API" lightbox="media/custom-connector-builder-agent/connector-validation.png"::: 1. In the **Test Connector** pane, enter the authentication details for your data source API, and then select **Connect**. @@ -119,34 +127,36 @@ Iteratively refine the connector using agent or inline directly into the JSON fi - On the **Events** tab, review the request headers and the events returned by the API. > [!NOTE]- > This test confirms that the API call succeeded and returns events. It doesn’t confirm that events are being written to your Sentinel table. Table ingestion is validated when you finish setting up the connector in the Data connectors page in Microsoft Sentinel.+ > This test confirms that the API call succeeded and returns events. It doesn't confirm that events are being written to your Microsoft Sentinel table. Table ingestion is validated when you finish setting up the connector in the Data connectors page in Microsoft Sentinel. After you validate the connection, select **Disconnect** to stop the polling session. -### Step 5: Deploy+### Deploy the connector++To deploy the connector to a Microsoft Sentinel workspace, follow these steps: 1. After the validation test succeeds, select **Deploy** in the chat window to start deploying the connector. - :::image type="content" source="media/custom-connector-builder-agent/connector-deploy.png" alt-text="Screenshot of the deploy step for custom connector in VS Code" lightbox="media/custom-connector-builder-agent/connector-deploy.png":::+ :::image type="content" source="media/custom-connector-builder-agent/connector-deploy.png" alt-text="Screenshot of VS Code Copilot chat window with the Deploy button to deploy the Sentinel connector" lightbox="media/custom-connector-builder-agent/connector-deploy.png"::: 1. The extension opens a panel where you can choose from your available Microsoft Sentinel workspaces. 1. Select a workspace, then select **Deploy** to deploy the connector to that workspace. - :::image type="content" source="media/custom-connector-builder-agent/connector-workspace-deploy.png" alt-text="Screenshot of the deploy step to choose workspace" lightbox="media/custom-connector-builder-agent/connector-workspace-deploy.png":::+ :::image type="content" source="media/custom-connector-builder-agent/connector-workspace-deploy.png" alt-text="Screenshot of the Microsoft Sentinel workspace selection panel in VS Code for deploying the connector" lightbox="media/custom-connector-builder-agent/connector-workspace-deploy.png"::: Alternatively, right-click the folder that contains the generated files, select **Microsoft Sentinel** > **Deploy Connector**. - :::image type="content" source="media/custom-connector-builder-agent/connector-files-deploy.png" alt-text="Screenshot of the alternate way of deploying in VS Code" lightbox="media/custom-connector-builder-agent/connector-files-deploy.png":::+ :::image type="content" source="media/custom-connector-builder-agent/connector-files-deploy.png" alt-text="Screenshot of the VS Code right-click context menu showing the Microsoft Sentinel Deploy Connector option" lightbox="media/custom-connector-builder-agent/connector-files-deploy.png"::: When deployment completes, a success message appears in the **Output** window. - :::image type="content" source="media/custom-connector-builder-agent/successful-deployment.png" alt-text="Screenshot of successful deployment" lightbox="media/custom-connector-builder-agent/successful-deployment.png":::+ :::image type="content" source="media/custom-connector-builder-agent/successful-deployment.png" alt-text="Screenshot of the VS Code Output window showing a successful connector deployment message" lightbox="media/custom-connector-builder-agent/successful-deployment.png"::: > [!NOTE] > After deployment into a Sentinel workspace, this connector focuses on ingesting data into Microsoft Sentinel tables. It doesn’t include a complete solution package or prebuilt end-to-end SOAR workflows for security coverage. If you need automation, create the required playbooks and workflows for your scenario. -## Getting Help+## Get help - For ISV partners building integrations, contact: [[email protected]](mailto:[email protected]) - For technical questions, use [Microsoft Q&A](/answers/topics/azure-sentinel.html) with the tag 'azure-sentinel' 