Discover
Explore without limits. Chat with data and agents to uncover instant insights on live cloud data.
POINT, CLICK, AND BUILD AGENTS AT THE CONTEXT LAYER
Deploy Sigma Agents. Secure by default.
Sigma Agents inherit your warehouse's row-level security and role-based access so that your team can begin securely orchestrating action across the enterprise on day one.
Get a Demo
Trusted by finance and corporate strategy teams at leading global enterprises
Agents where your data lives
Every agent action compiles to SQL and executes on your warehouse. No extraction, no stale copies, no separate vector databases.
Everyone is a builder
Define agent behavior, conditions, and thresholds in a spreadsheet interface. No Python, SQL, or engineering tickets required.
Insight to action, instantly
Agents write to the warehouse, trigger opportunities, update Jira tickets, or fire Slack alerts. The insight-to-action gap disappears.
Same platform. Same governance.
No dead ends or new integrations. Sigma Agents take governed action across your stack.
Agents that can detect, reason, and act
Agents run on a schedule, monitoring billions of rows of live warehouse data. When critical conditions are met — inventory depletion, contract over-utilization, anomalous spend — the agent executes actions or dispatches notifications automatically.
- Schedule-driven execution on live warehouse data
- Threshold and anomaly detection across billions of rows
- Automatic notifications via Slack, email, or webhooks
- Full audit trail of every detection and action
Transparent chat-driven exploration
Users query the agent in natural language. The agent responds with complete visibility into its logic including its planning process and every table queried, every calculation performed. No black boxes. The user can ask the agent to take a subsequent action based on the findings.
- Natural language conversation with the agent
- Transparent chain-of-thought reasoning
- Human-in-the-loop approval before execution
- Frictionless progression from insight to action
Close the insight-to-action loop
Realize the value of your technology investments today. Using the Sigma Actions framework, agents execute REST API calls to external tools. Create a Salesforce opportunity, update a Jira ticket, dispatch a Slack alert, or trigger a stored procedure to transform analytical signal into operational execution.
- API calls to CRMs, ticketing, and messaging tools
- Webhook triggers for custom integrations
- Stored procedure execution in your warehouse
- Governed writeback to warehouse tables
Turn trusted analysis into instant action
Build
Use AI to build dashboards, reports, and apps you need on the data you trust.
Act
Deploy AI agents to automate workflows, trigger actions in external systems, and eliminate software your team has outgrown.
Scale
Deploy at scale with security and governance inherited directly from your cloud data warehouse.
When an agent is triggered, the LLM plans which tools to call and in what order based on context.
Sigma then compiles these operations and reasons over your business logic, executing the best path via data fetches, in-browser calculations, or warehouse pushdowns.
Warehouse-native reasoning
All agent processing runs on warehouse compute, grounded in existing semantic models and logic.
Auditable actions
When an agent takes an action, it writes back to the warehouse with a full audit trail.
Inherited governance
Sigma Agents pass the identity or role to the warehouse. Agents never see data the user shouldn't.
Transparent lineage
See every planning step that Sigma Agents take. Review the table, calculation, and its reasoning.
Enterprise-Grade Scale
Sigma is built for teams that need flexibility without sacrificing governance or performance.
Warehouse RBAC
Passes the user's explicit Snowflake or Databricks role during query execution. Leverages your existing, mature role hierarchies without manual mapping.
Secure Writeback
Writeback is executed natively within the warehouse using the Sigma Actions framework. All operations inherit row-level and column-level security policies.
OAuth Passthrough
Authenticated user identity passed directly to the warehouse execution layer. Agent access is constrained by database rules.
Sigma User Attributes
RLS / CLS enforced at the apps layer via SCIM-synced attributes enables secure multi-tenant embeddings where external customers share infrastructure.
Immutable Audit Trail
Every agent-initiated read, write, and API call is logged directly in the warehouse. Compliance gets a full audit trail of who accessed, when, and what was changed.
Session Variables
Dynamic variable injection into the engine at runtime allows personalization. Lightweight, high-performance filtering without per-user warehouse accounts.
SOC 2
ISO/IEC 27701
GDPR
CCPA
Related Resources
Sigma's Query Engine (caching tiers + Alpha Query)
A technical walkthrough of the execution lanes: browser cache, Alpha Query, results cache via query ID, materialization, and warehouse cache behavior.
Learn more
Query History (generated SQL, execution path, request IDs)
How to inspect what Sigma generated, where it ran (browser vs warehouse/cache/materialized), and the timing breakdown you'll use when tuning.
Learn more
Set up PrivateLink / Private Service Connect
Step-by-step guides for AWS, Azure, and GCP private connectivity patterns.
Learn more
Sigma Agents FAQ
The questions we think every enterprise should ask when evaluating AI Agents.