Omni Agent

The Omni Agent provides a standalone, conversational interface for exploring your data. Ask questions, generate queries, and visualize results without needing to work directly in a workbook.

Requirements

To use the Omni Agent, you’ll need:

Restricted Querier, Querier, Modeler, or Connection Admin permissions
To verify that the following settings in AI Hub > General > Features are enabled. These settings are enabled by default, but Organization Admins can modify them as needed.
- Omni Agent - Required to use the Omni Agent
- Omni Agent > Chat - Required to access the chat interface
- Omni Agent > Chat > Chat in navigation - Required to show the standalone chat in the main sidebar

Accessing the Omni Agent

To access the Omni Agent, you can:

Click the New button in the sidebar, then select Chat.
Click Omni Agent in Omni’s main sidebar.
The Omni Agent sidebar item may display differently or not at all if your organization uses a custom sidebar. Your organization's AI branding settings can also change the label of this item in the sidebar.

The chat interface opens in a dedicated page where you can begin asking questions about your data.

Capabilities

The Omni Agent can:

Answer natural-language questions about your data
Search existing dashboards for tiles and visualizations that already answer your question before generating a new query
Generate queries based on your prompts, routed through topics or any view in your model
Create visualizations directly from your prompts
Create dashboards based on the queries and visualizations in the session
Create input columns to annotate query results inline
Create, edit, find, run, and delete routines
Accept files and images as context:
- Upload files including text and Markdown files to provide additional context alongside your queries
- Attach images by pasting from your clipboard to provide visual context for your questions
Save information about you to memory to provide more personalized responses
Search the Omni docs to answer questions about how to use Omni
Search the web for real-time information, when enabled in AI settings
Answer questions about your organization’s Omni usage, such as activity, adoption, and AI usage. Available to Organization Admins when enabled in AI settings. Not available in Slack or in scheduled runs.

Getting help

If you’re stuck and can’t remember how to do something in Omni, ask the Omni Agent. Questions like “How do I do [thing]?” will prompt the agent to search the official Omni docs and provide you with an answer, all without leaving your Omni workflow. You can also directly tell the agent to search the docs when researching the answer to your question.

Working in an embedded context? If you have the Hide Omni watermark setting enabled to provide a fully white-labeled experience, the AI doc search feature will respect it. Omni doc links will not be returned in chat, even if explicitly requested.

Tuning responses

You can shape how the Omni Agent responds by scoping which data it draws from, controlling the context it can access, and choosing which underlying AI model handles your prompts.

Scoping responses

The Omni Agent uses pickers to scope responses to specific connections, models, and topics. Click the button at the bottom of the chat box to open the pickers:

Connection, model, and topic picker in Omni's chat interface

Up to three pickers can display in the chat interface:

Connections - Lists the connections you have access to. Only displays if more than one connection is available. This setting can’t be changed if you’re using the chat in a workbook or dashboard.
Organization Admins can configure a default connection in AI Hub > Setup > Features to set which connection the Omni Agent opens with by default.
Models - Lists the available models in the selected connection. Only displays if:
- The connection has more than one model, and
- At least one topic in the model is accessible. This could mean that the model’s ai_chat_topics is unset, making all topics accessible, or that it specifies at least one topic:
  ai_chat_topics: [ Products ]
  Organization Admins can configure a default model in AI Hub > Setup > Features to set which model the Omni Agent opens with by default.
Topics - Lists the available topics in the model. Only displays if at least two topics in the model are accessible. This could mean that the model’s ai_chat_topics is unset, or that it specifies at least two topics:
ai_chat_topics: [ Products, Orders ]
Organization Admins can configure a default topic in AI Hub > Setup > Features to set which topic the Omni Agent opens with by default.

Scoping connections and models

If you haven’t selected a connection or model using the pickers, the Omni Agent can automatically switch between the connections and models you have access to, choosing whichever one can best answer your question. To scope the AI’s response to a specific connection or model, use the pickers to select one. The AI will remain “locked” to your selection until you change it.

Set your approval preference for automatic switching from AI approvals.

Scoping topics

If a prompt is entered and a topic isn’t selected - meaning that Auto-select a topic is selected in the topic picker - the AI will attempt to select the most relevant topic. To scope the AI’s response to a specific dataset, use the pickers to select a specific topic or composite topic. The AI will remain “locked” to the selected topic until the selection is changed. If an Organization Admin has configured a default topic along with a default connection and model, a new chat starts “locked” to that topic the same way - the AI asks for confirmation before switching away from it.

Save your answer as a standing choice from the confirmation card or manage it anytime from AI approvals.

Additionally, the picker menus won’t display when a model only has one AI-accessible topic. If a connection has one model with a single AI-accessible topic - determined by the value of the model’s ai_chat_topics parameter - the AI will be scoped only to that topic and the pickers will not display.

Managing AI integrations

This feature is not supported in embedded Omni instances.

The Omni Agent can use AI integrations to access context from tools like Google Drive, Google Calendar, Slack, GitHub, and Notion. To manage which integrations are available during your chat session, click the button at the bottom of the chat box, then click Connectors to open the submenu. The Connectors submenu lists AI integrations that an Organization Admin has enabled for your organization; custom connections, if enabled, are listed below a divider. Each connector shows one of two states:

Connect - If you haven’t connected your account yet, click Connect to launch the OAuth flow. This is the same authentication flow available from your user account settings.
On/Off toggle - If you’ve already connected your account, the integration displays an on/off toggle. Turning the toggle off temporarily withholds that integration’s tools from the Omni Agent for your session without disconnecting your account. You can turn the integration back on at any time.

The on/off toggle is per-user and doesn’t affect other users in your organization. It only controls whether the integration’s tools are available to the agent in your current and future chat sessions.

Saving information to memory

The Omni Agent > AI memory AI setting must be enabled to use this feature. Additionally, user memory is not supported for embedded instances.

The Omni Agent can remember information about you between chat sessions. Memory holds personal context — such as your team, the region you cover, how you like results presented — and the agent draws on it when it’s relevant to your prompt. With memory, you add personal context once and it automatically applies in every session when relevant. For example, a prompt like “how did we do last quarter?” can be automatically filtered to your region and presented in your preferred format based on memory, instead of needing to enter the prompt in every new session.

Omni Agent
Omni UI

The agent can also list your personal context files, or read one in full by name, when relevant to your prompt.

Information the agent saves from chat won’t display on your AI context page, and any changes you make on that page won’t affect what the agent saves from chat.

Click your user icon in the top right corner of the page to open the profile menu.
Click Manage account.
Next to AI context, click the Set up button to initially add personal context, or Manage to modify existing context.
Click Add file.

Use the Markdown editor to add information you want to store, up to 8,000 characters. For example, you could specify your current role and team, specific terms and their meanings, or the default scope for your questions:

 - I'm an analyst on the Growth team
 - I cover EMEA — assume EMEA unless I ask for another region
 - When I say "recent", I mean the last 90 days
 - Show revenue in thousands
 - I mostly work in the Sales topic

Choose when the Omni Agent should read the file — Every message or When needed.
When finished, click Save.

Memory is personal and scoped to a single organization. It isn’t shared with your team and the agent never uses it in anyone else’s conversations. If you belong to more than one Omni organization, each organization uses its own memory. Use memory for facts about you and how you work. Definitions that apply to everyone — information about your business or customers, terminology, and so on - belong in global context, where the whole organization benefits from them.

Selecting an LLM

The Omni Agent provides an LLM picker that allows you to choose which LLM answers your prompt. Only LLMs that an Organization Admin approved in LLM settings display in the picker. New chats start by using your organization’s default LLM. To select a different LLM, click the LLM picker next to the icon and choose an LLM from the dropdown menu. Your selection applies to prompts sent after you make it and persists until you select a different LLM. If you close the chat and open it again, the chat still uses the LLM you selected. To return the chat to your organization’s default LLM and thinking level, choose Reset to defaults in the picker. This clears both your LLM pick and any thinking level you chose. If the current LLM supports thinking levels, you’ll see an Effort submenu below the LLM section of the picker. Use this to select a thinking level for the LLM.

The LLM picker won’t display if your organization only has one approved LLM or you’re in an embedded Omni session.

Checking your credit usage

The usage meter described in this section isn’t supported for embedded Omni sessions or organizations using a custom model provider.

When you’re close to an AI credit limit, the LLM picker displays a usage meter above the list of LLMs. Use this section to check how many credits you’ve used, your overall limit, and when the limit resets. If your organization is nearing or has reached its downgrade threshold, this section will notify you. When you the downgrade threshold, the picker shows only the lower-cost LLM that Omni switches to.

Setting approval preferences

When the AI is about to take certain actions — like writing to your model or deleting a routine — it pauses and asks you to confirm first. The AI approvals page lets you set a standing choice for how the AI should handle each of these confirmation prompts, so you aren’t asked to approve the same type of action every time. Approval settings are personal and only apply to your own AI sessions.

Omni Agent
Omni UI

When the AI pauses to ask for confirmation, the confirmation card includes a Don’t ask again checkbox next to the Allow and Deny buttons. Select it before you respond to save your answer as a standing choice for that approval scope.

To open the page, click your avatar in the top-right corner of Omni to open the profile menu, then click AI approvals.You can set preferences for the following scopes:

Scope	Description
Apply model edits	Apply the agent’s edits to view, topic, and relationship files in the model
Create branches	Create a branch of a shared model for the agent to make its changes on
Update workbook models	Add the fields and changes the agent proposes, such as new measures or field descriptions, to a workbook’s model
Delete routine	Delete a routine; this is not reversible. The routine stops running immediately. Routines must be enabled for this scope to be visible.
Publish draft	Publish a draft, which replaces the published version for everyone who can view it
Switch models	Switch the conversation to a different connection or model and leave the selected topic
Run queries outside the selected topic	Run a query on the topic you selected for the chat, which can be another topic or a view outside the topic
Switch topics	Switch the agent from the topic you picked to another topic or to automatic topic selection

To reset a scope to its default (Ask), click Reset in the scope’s row.

Setting a scope to Ask or Never applies only when using the agent in the Omni UI. Slack, routines, APIs, and the MCP server proceed automatically with these actions whenever available.

Searching existing dashboards

Before generating new queries, the Omni Agent can search for existing dashboards that might already answer your question. When you ask a question, the AI analyzes your prompt and searches through:

Dashboard names - Searches the content index for dashboards with relevant titles
Tile and chart names - Searches for specific visualizations that match your question

The AI uses multiple search variations of your keywords to improve the chance of finding relevant content. For example, if you ask about “inventory items count”, it might search for “inventory items”, “items count”, and “inventory” separately. You can also provide the AI with a dashboard’s ID or custom identifier. When the AI finds potentially relevant dashboards, it:

Evaluates tiles

Uses semantic matching to identify which specific tile or chart from a dashboard best matches your question

Shows live previews

Executes the underlying query and displays the actual chart or table visualization inline in the chat

Highlights direct answers

If a tile directly answers your question, it displays in a highlighted card with an AI-generated explanation of why it’s relevant

This helps you discover existing content before creating new queries, promoting reuse of trusted dashboards and reducing duplicate analysis work.

Generating queries

When the Omni Agent answers a question, it generates a live query you can inspect, refresh, or roll up into a dashboard alongside other charts from the session.

Verifying queries

The Omni Agent > Query Verification AI setting must be enabled to use this feature.

Visualization tiles use the same chip as the query that produced it. If a chart is built from an earlier prompt’s query, it won’t have a chip.

Label	Reason
Off topic	Reads views outside the model’s topics
Not modeled	Uses CTEs or derived tables (`allow_ctes`)
New fields	Defines custom fields (`allow_custom_fields`)
Review suggested	Two or more of the above

Limitations

Chips won’t display in:

Embed sessions
Eval chats
Error tiles, including a failed inline re-run
Chats in workbooks
Chat with Content

Additionally, a chat session has to be aware of a model for verification to run. If the session doesn’t have a model selected and hasn’t used it before, chips won’t display on tiles built from the model.

Viewing query field details

When the Omni Agent generates a query, you can view details about the fields used in the results. This helps you understand what data the AI selected and how each field is defined. To view field details, hover over the top right corner of the query. Click the icon that appears, then Query details. A panel displays information for each field in the query, including:

Field name - The field’s label and identifier in the model
Definition - The SQL or calculation that defines the field
Description - Additional context about the field, if defined in the model

This feature provides transparency into AI-generated queries, helping you verify the AI selected appropriate fields and understand the underlying data structure. To improve the quality of field definitions displayed here, refer to Optimizing your models for AI.

Refreshing query results

When you revisit a previous chat session, query results may be stale. To update the results with the latest data, click the icon floating above the chat box:

Re-run all queries icon in the Omni Agent

Clicking this icon re-runs all queries in the conversation, updating visualizations and results with current data. To optimize performance, only the most recent queries are re-run.

Adding files as context

The Omni Agent > File uploads AI setting must be enabled to upload files and attach images.

You can upload text and Markdown files or paste images from your clipboard to give the Omni Agent additional context for your questions. Files are processed in your browser and are not stored on Omni’s servers.

Uploading files

You can upload text (.txt), Markdown (.md), LookML (.lkml), XML (.xml), HTML (.html, .htm), CSV (.csv), and images to the Omni Agent to provide additional context for your questions. This is useful when you need to reference additional information alongside your data queries.

CSV files can be up to 50 MB. If a CSV is too large for the Omni Agent to read in full, the file stays in your browser and only its header row (column names) is sent to the agent. When this happens, the agent can’t answer questions about the file’s data, and will suggest uploading the CSV as a topic so you can query it.

Uploads can use up to 250,000 tokens total on an Omni-managed, 1M-context-window Claude or GPT model, or 50,000 tokens on other LLMs. This allowance is tied to the conversation_prune_length parameter.

To upload a file:

Click the icon at the bottom of the chat box.
Select Attach file.
Select a file from your computer.
The file appears as a file chip in the chat box, indicating it’s ready to be sent with your message.

The Omni Agent can then read and reference the contents of the uploaded files when generating responses, allowing you to ask questions that combine your data with external context or documentation.

Attaching images

You can paste images directly from your clipboard into the chat to provide visual context alongside your questions. This works with screenshots, images copied from web pages, or any image data on your clipboard. To attach an image:

Copy an image to your clipboard (for example, take a screenshot or copy an image from a web page)
Click into the chat box
Paste the image using your system’s paste command (Cmd+V on Mac, Ctrl+V on Windows/Linux)

The image appears as a file chip in the chat box, indicating it’s ready to be sent with your message. You can attach multiple images to a single message by pasting them one after another.

Image pasting is supported in Chrome and Safari. Firefox does not currently support pasting images into textarea elements due to browser limitations.

Each conversation with the Omni Agent is saved as a chat session you can revisit and share with other users in your organization.

Navigating prompt history

You can quickly recall previous prompts using keyboard shortcuts, similar to a command-line interface:

Press the Up arrow key to cycle backward through your previous prompts
Press the Down arrow key to cycle forward through your prompt history

When you reach your oldest prompt and press Up arrow again, the navigation wraps to your most recent prompt. Pressing Down arrow after your newest prompt restores any in-progress text you were typing before navigating the history.

Arrow key navigation only works when your cursor is at the beginning of the input field or when the field is empty. This preserves normal cursor movement when editing text.

The prompt history displays only your own prompts from the current chat session.

Queuing prompts while the agent responds

If you submit a new prompt while the Omni Agent is still responding to a previous one, Omni queues the new prompt and sends it after the agent finishes responding. To cancel the response in progress and send your new prompt immediately, press Cmd+Enter (Mac) or Ctrl+Enter (Windows/Linux). If you click Stop while a prompt is queued, the queued prompt returns to the chat box so you can edit it before sending.

Prompts are capped at 400,000 characters. If your prompt is over the cap, Omni doesn’t send it and keeps it in the chat box with a message explaining why. This also applies when a queued prompt combines with your current draft, since the two send as a single message.

Managing long conversations

As your conversation with the Omni Agent grows, it consumes more of the available context window. Omni automatically prunes older messages from the conversation history in the background to stay within that window, governed by the conversation_prune_length parameter. This happens automatically and requires no configuration or action from you. You can share a chat session by copying the URL from your browser’s address bar and sending it to another user. Query results stored in the chat history are cached from when the creator ran them. The viewer of the shared chat will see those same cached results. Therefore, Omni requires that the viewer of the shared chat have Querier, Modeler, or Connection Admin permissions, as well as the same connection environment, to view the session. Users with Restricted Querier permissions or lower will not be able to access shared chat sessions. The following rules determine who can see a chat:

The owner of the chat can always view the chat.
Any user with the Querier role or above on all relevant models can view the chat. Because Queriers can already write SQL queries directly in Omni, this doesn’t expose any data they couldn’t otherwise access.
Viewers and Restricted Queriers are blocked from viewing, preventing access to data they are not authorized to see.

Customizing and embedding the Omni Agent

Organization Admins can tailor the agent’s appearance to match their brand and surface it inside external applications.

Applying branding

Organization Admins can customize the appearance of the AI chat interface, including the agent’s name, icon, and greeting messages. Refer to the AI branding settings for more information.

Embedding the agent

The Omni Agent can also be embedded into external applications. Refer to the embedding the Omni Agent guide for setup instructions.

Next steps

Optimize your models for AI to improve the quality of AI-generated responses
Configure topics to organize and scope the data the Omni Agent can access
Customize the Omni Agent appearance with your own branding

Getting started

Manage content

Analyze & build

Visualize & present

Deliver content

Model data

Manage integrations

Requirements

Accessing the Omni Agent