Raddat's foundation model learns your users and your company's risk landscape
Ingest
Ingest
Raddat ingests historical and live event data through a single API (CreateEvent). Our foundation model, Lion, builds a real-time embedding of every user — capturing behavior, device, and counterparty signals in a single representation.
Your labels
Live Events
Each event re-embeds its user the moment it arrives.
Decide
Decide
Raddat detects risk vectors and conducts investigations using a single API (Decide). Lion powers deep investigations — finding rings, tracing counterparties, and building evidence trails.
Infer
Infer
We also offer an API (Infer) that lets you use Lion's embeddings directly in your own models — enriching your existing ML pipeline with behavioral features that update in real time.
Live event stream
Embedding distribution
Your ATO model
Previous sessions
Past session embedding
Historical distribution
Deploy
Deploy
All of the data you share with Raddat is scoped per tenant and by default is never used to train models for other customers. For engineering teams, Raddat supports features like webhook callbacks, batch processing, and custom model endpoints.
STANDARD
- Hosted in Raddat's secure cloud
- Data encrypted at rest and in transit
- SOC 2 Type II certified
PRIVATE CLOUD
- Deployed in your own VPC
- No data leaves your environment
- Custom data retention policies