Show HN: Kairos – Open-source risk and fraud decisioning platform

Re:Show HN: Kairos – Open-source risk and fraud decisioning ... by tehsurf on Wednesday November 04, 2026 @03:08AM (#50362649)

Thanks for showing Keiros! This looks very promising!

Could you explain how "System One" differs from the traditional, rule based, approach? Sticking to your example: How would the question 'Is this a throwaway email?' be translated into Kairos business logic?

When using the MCP Server: How does Claude develop such models, e.g. feature engineering? Is this an MLOps pipeline behind an MCP?

[ Parent | on HN ]

Re:Show HN: Kairos – Open-source risk and fraud decisioning ... by agileAlligator on Wednesday November 04, 2026 @03:10AM (#50362664)

System one is just a Jev API Call presumably. Or one of the open source alternatives to Jev. https://typesafe.ai/blog/introducing-system-one-models-and-j...

[ Parent | on HN ]

Re:Show HN: Kairos – Open-source risk and fraud decisioning ... by tehsurf on Wednesday November 04, 2026 @03:57AM (#50362985)

Thanks!

[ Parent | on HN ]

Re:Show HN: Kairos – Open-source risk and fraud decisioning ... by citguru on Wednesday November 04, 2026 @05:54AM (#50363798)

Actually while similar to Jev and uses the popularized architecture by Jev, Kairos uses an underlying model called Grayson trained by Finic but for Fraud. You can check it out - https://finic.ai/

[ Parent | on HN ]