Add Feature Settings, update GenAI settings

explore-analyze/ai-features/agent-builder/chat.md

@@ -111,7 +111,7 @@ Click the three-dot menu icon in the top-right corner to access additional optio
 The options menu provides access to:
 
 - **Agent details**: View information about the currently selected agent.
-- **GenAI Settings**: Open the global GenAI settings page to configure default connectors and other AI settings.
+- **GenAI Settings**: Open the global GenAI settings page to configure default connectors and other AI settings. Refer to [](/explore-analyze/ai-features/manage-access-to-ai-assistant.md).
 
 :::{image} images/more-actions-menu-options-9.4.png
 :screenshot:

explore-analyze/ai-features/agent-builder/models.md

@@ -65,7 +65,7 @@ To learn more, refer to [select a different model](/explore-analyze/ai-features/
 To change which model is used by default:
 
 1. Search for **Model management / Feature settings** in the global search field.
-2. Select your preferred connector from the **Default model** dropdown.
+2. Select your preferred model from the **Default model** dropdown.
 3. Save your changes.
 
 The **Feature settings** page also provides per-feature model configuration, allowing you to assign specific models to individual AI capabilities across your deployment. This enables more granular control over model selection.
@@ -82,6 +82,8 @@ To change which model is used by default:
 
 ::::
 
+For more information about these settings, refer to [](/explore-analyze/ai-features/manage-access-to-ai-assistant.md).
+
 ## Use additional models
 
 To use additional models that aren't preconfigured, create a connector for your model provider.

explore-analyze/ai-features/manage-access-to-ai-assistant.md

@@ -11,42 +11,58 @@ products:
 
 # Manage access to AI features
 
-The GenAI Settings page lets you control access to AI-powered features in the following ways:
-
-- Manage which AI connectors are available in your environment. 
-- Enable or disable AI Assistant and other AI-powered features in your environment.
-- {applies_to}`stack: ga 9.2+` {applies_to}`serverless: unavailable` Specify in which Elastic solutions the `AI Assistant for Observability and Search` and the `AI Assistant for Security` appear.
+The **GenAI Settings** and **Feature Settings** pages let you control the list of models available for each AI feature, turn on token usage tracking, install documentation, and more.
 
 ## Requirements
 
-- To access the **GenAI Settings** page, you need the `Actions and connectors: all` or `Actions and connectors: read` [{{kib}} privilege](/deploy-manage/users-roles/cluster-or-deployment-auth/kibana-privileges.md).
-- To modify the settings on this page, you need the `Advanced Settings: all` {{kib}} privilege.
+- To access **GenAI Settings**, you need the `Actions and connectors: all` or `Actions and connectors: read` [{{kib}} privilege](/deploy-manage/users-roles/cluster-or-deployment-auth/kibana-privileges.md).
+- To modify the settings, you need the `Advanced Settings: all` {{kib}} privilege.
 
-## The GenAI Settings page
+<!--
+- To access **Feature Settings**, you need the `Actions and connectors: all` or `Actions and connectors: read` [{{kib}} privilege](/deploy-manage/users-roles/cluster-or-deployment-auth/kibana-privileges.md).
+- To modify the settings, you need the `Advanced Settings: all` {{kib}} privilege.
+-->
 
-To manage these settings, go to the **GenAI Settings** page by using the navigation menu or the [global search field](/explore-analyze/find-and-organize/find-apps-and-objects.md).
+## GenAI settings
 
-::::{applies-switch}
+Go to the **GenAI Settings** page by using the navigation menu or the [global search field](/explore-analyze/find-and-organize/find-apps-and-objects.md).
 
-:::{applies-item} serverless: ga
+:::::{applies-switch}
 
-![GenAI Settings page for Serverless](/explore-analyze/images/ai-assistant-settings-page-serverless.png "")
+::::{applies-item} serverless: ga
+:::{image} /explore-analyze/images/genai-settings.png
+:alt: GenAI Settings for Serverless
+:screenshot:
+:::
 
 The **GenAI Settings** page has the following settings:
 
-- **Default AI Connector**: Click **Manage connectors** to open the **Connectors** page, where you can create or delete AI connectors. To update these settings, you need the `Actions and connectors: all` [{{kib}} privilege](/deploy-manage/users-roles/cluster-or-deployment-auth/kibana-privileges.md).
-- **AI feature visibility**: Click **Go to Permissions tab** to access the active {{kib}} space's settings page, where you can specify which features each [user role](/deploy-manage/users-roles/cluster-or-deployment-auth/kibana-privileges.md) has access to in your environment. This includes AI-powered features. 
+- **Chat experience**: Select whether to use AI Assistant or AI Agent. To learn about the differences, go to [Compare AI Agent and AI Assistant](/explore-analyze/ai-features/ai-chat-experiences/ai-agent-or-ai-assistant.md).
+- **Token usage tracking**: Turn on tracking of token usage by AI features.
+- **Documentation**: Install Elastic documentation or content from Security labs to improve Agent Builder responses.
+::::
+::::{applies-item} stack: ga 9.4+
 
+:::{image} /explore-analyze/images/genai-settings-stack.png
+:alt: GenAI Settings for Stack in 9.4
+:screenshot:
 :::
 
-:::{applies-item} stack: ga 9.2+
+The **GenAI Settings** page has the following settings:
 
-![GenAI Settings page for Stack](/explore-analyze/images/ai-assistant-settings-page.png "")
+- **AI feature visibility**: This button opens the current Space's settings page, where you can specify which features are enabled in your environment, including AI-powered features.
+- **Chat experience**: Select whether to use AI Assistant or AI Agent. To learn about the differences, go to [Compare AI Agent and AI Assistant](/explore-analyze/ai-features/ai-chat-experiences/ai-agent-or-ai-assistant.md).
+- **Documentation**: Install Elastic documentation or content from Security labs to improve Agent Builder responses.
+::::
+::::{applies-item} stack: ga 9.2-9.3
 
+:::{image} /explore-analyze/images/ai-assistant-settings-page.png
+:alt: GenAI Settings page for Stack in 9.2 and 9.3
+:::
 
 The **GenAI Settings** page has the following settings:
 
-- **Default AI Connector**: Use this setting to specify which connector is selected by default when you access AI-powered features. Default setting: **No default connector**.
+- **Default AI Connector**: Use this setting to specify which connector is selected by default when you access AI-powered features. For available connectors and tested models, refer to [Configure access to LLMs](/explore-analyze/ai-features/llm-guides/llm-connectors.md). Default setting: **No default connector**.
   - If **No default connector** is selected, AI-powered features will default to the connector that was most recently used in your environment.
   - If an **Elastic Managed LLM** or a custom LLM connector is selected, AI-powered features will default to that connector regardless of which connector was used most recently in your environment.
 - **Disallow all other connectors**: When this setting is disabled, whenever you use an AI-powered feature you can select which connector should power it. Enable it to prevent connectors other than the default connector from being used in your space. Default setting: disabled.
@@ -58,11 +74,21 @@ The **GenAI Settings** page has the following settings:
   - **Security AI Assistant in other apps**: The Security AI Assistant appears throughout {{kib}} regardless of solution. The {{obs-ai-assistant}} does not appear anywhere.
   - **Hide all assistants**: Turns off AI Assistant throughout {{kib}}.
 
-:::
-
 ::::
+:::::
 
-## Choose models for AI features
+## Feature settings
+```{applies_to}
+stack: ga 9.4+
+serverless: ga
+```
 
-**Default AI Connector** sets which LLM powers AI-powered features by default. For connectors and tested models, refer to [Configure access to LLMs](/explore-analyze/ai-features/llm-guides/llm-connectors.md).
+You can configure the lists of models that are available for each feature or specify single model for all features.
+Find **Feature Settings** in the main menu or use the [global search field](/explore-analyze/find-and-organize/find-apps-and-objects.md).
+
+:::{image} /explore-analyze/images/feature-settings.png
+:alt: Feature Settings app
+:screenshot:
+:::
 
+To change the order of precedence for assigned models for each feature, select and drag items in the list.

explore-analyze/workflows/steps/ai-steps.md

@@ -23,7 +23,13 @@ The `ai.prompt` step sends a prompt to an AI connector and returns the response.
 * Make context-aware decisions based on data in your workflow
 * Generate structured output based on a defined schema
 
-To use a specific AI connector, configure it through {{kib}}'s [{{connectors-ui}} framework](/deploy-manage/manage-connectors.md). If you don't configure a connector, this step uses the connector selected as the **Default AI Connector** in [GenAI Settings](/explore-analyze/ai-features/manage-access-to-ai-assistant.md#the-genai-settings-page). [Elastic Managed LLMs](kibana://reference/connectors-kibana/elastic-managed-llm.md) are available out of the box and require no setup.
+To use a specific AI connector, configure it through {{kib}}'s [{{connectors-ui}} framework](/deploy-manage/manage-connectors.md).
+If you don't configure a connector, this step uses
+
+- {applies_to}`serverless: ga` {applies_to}`stack: ga 9.4` the default model specified in [Feature Settings](/explore-analyze/ai-features/manage-access-to-ai-assistant.md#feature-settings).
+- {applies_to}`stack: ga 9.0-9.3` the default AI connector specified in [GenAI Settings](/explore-analyze/ai-features/manage-access-to-ai-assistant.md#genai-settings).
+
+[Elastic Managed LLMs](kibana://reference/connectors-kibana/elastic-managed-llm.md) are available out of the box and require no setup.
 
 :::{note}
 :applies_to: { self: }
@@ -37,7 +43,7 @@ Use the following parameters in the `with` block to configure the step:
 | Parameter | Type | Required | Description |
 |-----------|------|----------|-------------|
 | `prompt` | string | Yes | The prompt text to send to the AI connector. Can include template variables to reference data from previous steps, inputs, or constants. |
-| `connectorId` | string | No | The ID or name of the AI connector to use. If omitted, uses the [default AI connector](/explore-analyze/ai-features/manage-access-to-ai-assistant.md#the-genai-settings-page). |
+| `connectorId` | string | No | The ID or name of the AI connector to use. If omitted, uses the [default AI connector or model](/explore-analyze/ai-features/manage-access-to-ai-assistant.md). |
 | `schema` | object | No | A JSON Schema object that defines the structure of the expected response. When provided, the AI connector returns structured data matching the schema. |
 | `temperature` | number | No | Controls randomness in the AI response. Accepts values from `0` to `1` (for example, `0.3`). Lower values produce more deterministic responses; higher values produce more random responses. |
 

solutions/security/ai/ai-assistant.md

@@ -42,14 +42,12 @@
 serverless: ga
 ```
 
-The [**GenAI settings**](/explore-analyze/ai-features/manage-access-to-ai-assistant.md) page allows you to:
+The [GenAI and Feature Settings](/explore-analyze/ai-features/manage-access-to-ai-assistant.md) pages allow you to:
 
-- Manage which AI connectors are available in your environment.
+- Manage which AI connectors or models are available in your environment.
 - Enable or disable AI Assistant and other AI-powered features in your environment.
 - {applies_to}`stack: ga 9.2+` {applies_to}`serverless: unavailable` Specify in which Elastic solutions the `AI Assistant for Observability and Search` and the `AI Assistant for Security` appear.
 
-
-
 ## Your data and AI Assistant [data-information]
 
 Elastic does not store or examine prompts or results used by AI Assistant, or use this data for model training. This includes anything you send the model, such as alert or event data, detection rule configurations, queries, and prompts. However, any data you provide to AI Assistant will be processed by the third-party large language model (LLM) provider you connected to as part of AI Assistant setup.