AI you'll actually use
Omni helps anyone make smarter decisions with data by translating natural language questions into accurate insights, powered by our semantic layer.
Free Trial
See Omni’s AI features in action
Accelerate every step of your analysis
Explore data, refine queries, and interpret results — without needing deep technical knowledge.
Ask questions, get answers
Run your entire analysis with just a conversation. Type a question – “What was revenue last quarter?” — and Omni will generate a query that answers it.
Refine queries with simple prompts — “Show me the last 6 months instead” — and Omni will make updates accordingly. You can even have Omni summarize results in everyday terms: "I’m in sales. Can you explain the results to help me forecast the business?"
Not sure what to look at next? Just ask Omni: “What other questions should I ask?” and continue exploring.
Let Omni write your formulas
Stop looking up spreadsheet syntax. Simply describe the calculation you need, like “Calculate month-over-month revenue growth,” and Omni will generate the correct formula for you. Any helpful metrics you create along the way can be saved to your shared data model for reuse.
Visualize results in seconds
Create charts by providing simple directions and then making adjustments using Omni’s point-and-click visual editor. Go from question → insights → visualization with just a few prompts.
Launch your AI product faster with Omni
Give your customers a fast, intuitive AI experience your competitors can’t beat. With Omni’s AI capabilities, your customers can get insights from their data using natural language.
Build AI experiences with APIs
Deliver easy self-service
Customers still relying on your CSMs for data? AI makes answering a data question as easy as asking it.
Ensure accurate insights
Curated datasets used for in-app analytics are great foundations for accurate AI responses, so your customers get results they can trust.
Enhance existing AI features
Already using chatbots or AI suggestions? Omni seamlessly integrates via API so you can bring reliable analytics into the AI tools your customers already use.
Create new revenue streams
Add an AI-powered analytics offering to your premium pricing tiers to create new upsell opportunities and close larger deals.
AI that isn’t a black box
Omni was designed from day one as a platform for reliable AI analytics for everyone. With Omni’s semantic layer, you can control how AI interprets your data, so you get answers you can trust.
Guide AI to better answers
Teach Omni exactly how your business thinks about data. Add descriptions, synonyms, instructions, and other context to your semantic layer, so Omni’s AI can deliver relevant insights.
Built on existing business logic
Omni’s AI uses the same metrics, joins, and metadata you’ve already defined in your data model to generate queries, keeping insights consistent across your organization.
Secure by design
Omni never sends your data to an external LLM without your permission, and you can turn off AI features at any time.
Unlock new use cases with ML models from your warehouse
Integrate data enrichment, sentiment analysis, and more into your Omni workflows.
Use Cortex LLM functions to return insights on large volumes of data, directly within Omni – no Snowflake setup required.
Learn More
Utilize custom-deployed ML models, Databricks-hosted models, or external models to enrich data in Omni, instantly.
Learn MoreWow, AI did something useful for me 🙂— Travis Mitchell, Sr Principal Product Operations Manager
FAQs
Does Omni use its own LLM, or does it leverage external LLMs?
Omni currently uses AWS Bedrock-hosted Claude models for most tasks and OpenAI models for some specific tasks. Omni does not have its own LLM. For more, see our docs.
How does Omni’s AI work behind the scenes?
When a user enters a prompt, Omni shares the prompt with AWS Bedrock to categorize the request and determine how to respond.
Then, depending on the request, we use AWS Bedrock or OpenAI models to deliver a response. The output of the AI's processing is a new Omni query, which is a collection of metadata – including field names, filters, sorts, pivots, topic name, and limit – that is translated into SQL. This new query is then run within the current workbook to provide an answer to the user's prompt.
How does Omni’s AI compare to other AI tools?
While other tools are solely focused on enabling an “AI chatbot” experience, Omni’s AI lets you do more than just ask questions and get black-box answers. AI in Omni can accelerate every part of your data analysis workflow – including creating queries, filtering, writing Excel formulas, and more.
In addition, AI is embedded into Omni’s workbook experience rather than a separate interface, making it interoperable with the rest of Omni’s analysis methods. As you query with AI, you can drop into the point-and-click UI, SQL, or spreadsheet formulas at any point. Users aren’t locked into AI, even if that’s their starting point.
Omni’s semantic model also lets you feed important context and nuance into the AI to promote reliable responses, instead of expecting LLMs to deliver precise answers based on your raw data.
Can I test the accuracy of Omni’s AI?
Omni currently doesn’t offer a way to “test” the accuracy of responses. However, we encourage data teams to optimize their data models for AI and experiment with adding context to deliver more reliable results. By using this human-in-the-loop approach, teams can continually evolve their data model for AI to deliver more accurate, relevant answers.
Why is your semantic model important to AI?
Omni’s semantic model ensures AI responses aren’t a black box. For example, you might provide ChatGPT specific prompts like “You’re an expert on the economy. Summarize this article in 50 words” to get the results you want. Omni lets you do the same – you can provide instructions, context, and nuance to your data for more reliable responses.
For example, in your “Sales & Revenue” Topic, you might add context like: “Make sure your responses are easy for a busy sales leader to understand and act on.” You might get even more detailed on your Revenue field and specify: “This is the source of truth for our sales and finance reporting. It is the gross revenue from all of our sales channels. For any questions that ask for total sales, total revenue, total sold, or similar metrics, use this field.” Including these details helps AI better understand your data and deliver more helpful, trustworthy results.
How does Omni handle data security?
Omni never shares your data without your permission. When AI features are toggled on, only necessary data is shared with external LLMs. For example, when asking AI to generate queries, or write formulas, only query metadata (column names, sorts, limits, etc.) is shared. If asking AI to summarize a query, then the results set is shared. Learn more in our docs.
