Spark starts immediately
Open a managed account, build a focused first model, and keep local file export available.
Self-serve Causal AI workbench
Build Bayesian-network models in the browser. Run evidence, interventions, counterfactuals, CPT sensitivity, and Studio influence-diagram policy or VOI analysis before sharing or SDK delivery.

Open a managed account, build a focused first model, and keep local file export available.
Cloud documents, autosave, larger limits, sharing, and authenticated support unlock as work grows.
Protected WASM grants tie inference access to the account and entitlement state.
Causal modeling
Build directed causal graphs, edit node states and probability tables, and keep layouts readable as networks grow.
Inspect evidence, posteriors, lift, interventions, and counterfactuals without leaving the workspace.
Rank which CPT entries move a target probability most, using the current evidence or intervention state.
Studio adds influence diagrams, policy solving, expected utility, and value-of-information ranking.
Generate sample rows, test scenarios, export synthetic data, and inspect how assumptions move through the model.
Cloud-native learning runs constraint, search-and-score, and optimization workflows from reviewed datasets in the same product surface.
Example models
The public model corpus gives users meaningful networks to inspect, query, and export before committing paid cloud storage.
Protected runtime
Spark, paid plans, support credits, and commercial SDK licenses all resolve through the same account boundary, so product access stays explainable.