Sardine integrated Jev as an automated judgment node in its Sardine Flow workflow builder and is integrating it with Web360 for structured KYB decisions.
We put TypeSafe AI's Jev to work on three fraud problems ↗
What happened
- Sardine reports developing a name-and-email mismatch feature powered by Jev and plans to expose it to client rule engines.
Why it matters to Signicat
- Sardine is embedding sub-100ms SLM/LLM decision nodes into its orchestration flow, raising the technical benchmark for orchestration engines and automated KYB screening.
- Direct integration of automated AI reasoning into live payment and onboarding flows bypasses human analyst bottlenecks in KYB and fraud checks.
Evidence from the source (3 quotes)
- “By integrating Jev into our rule engine, not only can we expose such advanced features to our customers, but we also enable our users to define their own customized features to perform fast checks on all sorts of problems.” source ↗
- “We've added Jev as a node in Sardine Flow, our workflow builder. A flow can now collect the information in its first steps, ask Jev a set of specific questions about it, and write the answers as structured labels.” source ↗
- “The API-facing path, the one other software calls, runs the same information through Jev and returns the structured answers a customer's own agent is waiting for.” source ↗
Orchestration platformAML KYB screeningFraud deepfake injectionAgentic AI identityFeature updateProduct launchGeos/global
2 of 3 facts verified against the source · confidence high · gemini-3.8-flash