Make the call while it still matters
Sigma Assistant and Sigma Agents find what changed, explain why, and take the next step, on the governed data your team already trusts.
Answers you can check
Answers show their steps, sources, and the SQL they ran, from your data models.
Insights that find you
Agents watch the numbers on a schedule and send what changed to the people who own it.
Straight to action
Write the decision back or route it for approval, in the same place you saw the answer.
Trusted by 2,000+ leading enterprises around the world
Answers that act
Analysis that finishes the job
Most AI on data answers when asked and stops there. Sigma explains the answer and carries it through to the decision.
| AI chat on data | With Sigma |
|---|---|
| Answers you can’t trace back to a definition | Answers from your data models with the steps and SQL |
| Waits for someone to ask | Agents that watch the numbers on a schedule |
| Stops at the answer | Writeback and approvals in the same place |
| A separate window for each warehouse agent | Cortex Agents and Genie Agents working in the same workbook |
From “what changed” to “done”
The same governed data answers the question, explains it, and acts on it.
Checkable answers
See the work behind every answer
Sigma Assistant answers from your data models with a chart, its steps, and the SQL behind it, so anyone can check the number before using it.
Countable text
Turn each comment into a number you can track
Add an AI Column and one prompt classifies each row of free text, from reviews to support tickets. Chart it, filter a KPI by it, and see which theme moved. AI Columns are in beta.
Root causes
Find out why it moved
Ask why a number changed and get the drivers ranked, with context from your Snowflake Cortex Agents, Databricks Genie Agents, and MCP connectors.
Early warning
Hear about it before anyone asks
Put an agent on a schedule to check the numbers that matter and send what changed by email or Slack.
Decisions done
Turn the answer into the next step
Agents write the change back to an input table or call your systems, and ask a person to approve before anything changes.
Answers and actions follow your rules
Questions, answers, and agent actions run as the person asking, inside the permissions you already manage.
Answers you can audit
Audit logs record AI conversations and agent actions, so you can see what was asked and what changed.
Human approval
Require sign-off in chat before an agent changes any data.
Your choice of model
Admins pick the AI provider for the org, from models in your data warehouse or OpenAI, Gemini, Amazon Bedrock, and more.
Per-user OAuth
Connect with OAuth so queries run with each person’s own warehouse role.
Row- and column-level security
Reads and writes both inherit your table policies.
Audit trail
Audit logs record user activity, AI conversations, and input table edits, so you can see who changed what.
Teams putting AI to work on Sigma
See how customers bring AI to governed data with Sigma
500+ business users empowered with real-time insights. 15-16 terabytes of compressed data in dashboards. $20 billion assets under management.AB CarVal Harnesses AI in Sigma to Unlock Secure, Real-Time Investment Insights
Weeks to days to ship new workflows. 14K+ r&d orgs on luma. 2M+ scientists using the data.How Dotmatics ships new workflows in days with Sigma
“Using Sigma, I was able to make a dashboard in under two hours that got the answers. The AI features let our team move faster than ever before.”How Duolingo Democratized Data Access While Protecting Sensitive InformationStraight from the source
“Through Sigma's MCP server, anyone with Sigma access can query governed data from our AI assistant (Claude) in plain language, and builders can have the AI create workbooks.”
VP, Data and AnalyticsConstruction · Gartner Peer Insights (opens in a new tab)“Warehouse and Sigma agents help users find reports and get answers without routing everything through the data team…”
Ryan M.Mid-Market · G2 (opens in a new tab)“I love being able to talk to our data in natural language and creating apps to empower other users to do the same”
Data and Analytics ManagerSoftware · Gartner Peer Insights (opens in a new tab)“AI integration helps a lot with users being able to ask questions directly on the data.”
Hunter VenableBusiness Analyst · Mid-Market · G2 (opens in a new tab)“I like the governance and ease of use to build. But the introduction of the MCP server has been a game changer…”
Operations ManagerSoftware · Gartner Peer Insights (opens in a new tab)“AI assistance gives me a starting point for building formulas, workbooks, and agents, and helps reduce trial and error and save time during development.”
Vidhusha P.Enterprise · G2 (opens in a new tab)“Intuitive, business-user friendly experience when deploying AI-enabled complex applications with write-back functionalities”
VP, Data and AnalyticsMiscellaneous · Gartner Peer Insights (opens in a new tab)“Quicker data insights for our end users. I will be less hands on with end users as well with the AI chat capability.”
Mikayla McCordEnterprise Data Steward · Enterprise · G2 (opens in a new tab)
Agentic analytics FAQ
What is agentic analytics?
Agentic analytics is AI that does the analysis itself. It finds what changed, explains why, and takes or recommends the next step, on governed data.
How is it different from a BI copilot?
A copilot answers when asked. In Sigma, agents can also watch the numbers on a schedule and write the next step back, with a person’s approval if you want one.
Can we check how an answer was reached?
Yes. Sigma Assistant shows its steps, the sources it used, and the SQL behind the answer.
Which AI model runs it?
Your admins choose the AI provider as an org setting, from models hosted in your data warehouse or external providers. Queries run on your warehouse compute either way.
Does it work with Snowflake Cortex Agents and Databricks Genie Agents?
Yes. Sigma agents can call your Snowflake Cortex Agents and Databricks Genie Agents and use their answers alongside Sigma’s own data models.
Bring the question your team asks on Monday mornings
We’ll show you how Sigma answers it, explains it, and acts on it, on your live data.