The platform evaluates events such as sign-ups, payments, and payouts to return risk scores and decisions including approve, step up, review, or block. A core component is Grayson, a specialized decision model that interprets unstructured information like names and emails using calibrated probabilities. Organizations can self-host the system using Docker and connect with it through an HTTP API, a command-line interface, or SDKs for Python and TypeScript.
Key points
AI coding agents can directly design experiments, build workflows, and deploy winning fra…: AI coding agents can directly design experiments, build workflows, and deploy winning fraud models on user data.
The proprietary Grayson model analyzes unstructured attributes like addresses and emails…: The proprietary Grayson model analyzes unstructured attributes like addresses and emails to feed into logistic regression or XGBoost models.
Teams can self-host the infrastructure with Docker while interacting through dedicated Py…: Teams can self-host the infrastructure with Docker while interacting through dedicated Python and TypeScript SDKs.
Sources checked by our analysis pipeline: 1
Kairos decides every sign-up, login, order, payment and payout as it happens, and keeps each decision with the signals behind it. It is an open-source alternative to Sardine, Sift, Riskified and SEON, with two things they don't have: your coding agent tunes it, and decision models catch fraud before you have the labels to train on.
- Real-time decisions: one call returns approve, step up, review or block, with a risk score and the reasons, from the subject's history, the devices, cards and addresses it shares with others, and the session.
- Workflows: ask a decision model, score with a model, branch, call webhooks, open cases, and decide again later.
- Queues and cases: review work for people, whose resolutions become labels.
- MCP server: Claude Code, Cursor or Codex read your decisions and build workflows, with every action recorded under its key.
- Experiments: your agent proposes model variants, Kairos trains and tests them on your data, and the agent ships the winner.
- Grayson: Finic's decision model answers questions about each request in plain language. It works with…
Apple is testing new Audio Intelligence capabilities designed to act as factual memory aids rather than commercial assistants. Currently restricted to developer betas on the newest smartwatches, the system focuses strictly on recent speech transcription and conversation recaps without incorporating emotional analysis or purchasing prompts. This approach emphasizes user privacy controls, requiring explicit opt-ins and hardware-based calibration before any audio capture occurs.
Continuous integration setups now allow teams to bypass creating placeholder deployments simply to test code changes. Developers can activate automated testing workflows straight from their local terminal, provided their accounts are properly connected and hold the appropriate repository permissions. This change removes previous administrative friction by letting builds run immediately upon code updates.
Observability teams gain broader dashboard visualization capabilities and system-level workload tracking across shared infrastructure in versions 2.39 through 2.42. The updates refine investigation workflows through experimental ad hoc multi-source filtering and an automated tool designed for agentic service health analysis. These changes improve operational visibility while modernizing collector telemetry alignments and query attribution.