Fraud Investigation Agent

The author is building a fraud investigation agent using Jev and TigerGraph. Its flow goes from an alert through graph evidence, a Bayesian update, a pattern, Jev’s extra lookup, policy, a verdict, and human approval.

View on X

Kaushal Chaudhari@Kaushaly4s5s7𝕏

Been building a fraud investigation agent using Jev + TigerGraph. The flow is basically: Alert → graph evidence → Bayesian update → pattern → Jev's one extra lookup → policy → verdict → human approval. Jev isn't the decision-maker. It's the control layer that decides when the agent is allowed to look again and keeps the explanation grounded. That separation made the whole system much easier to reason about. just experimenting this for the @TigerGraphDB & @247pmstudio

Sep 25, 2026X postsView on X

Jev is not the decision-maker; it controls when the agent can look again and keeps the explanation grounded. The author says this separation made the system easier to reason about. The project is experimental for TigerGraphDB and @247pmstudio.

Also filed under Agents & browsers

Evaluates Tool-Using Agents with Jev in CI
The project evaluates a real tool-using AI agent using code checks, a calibrated Jev judge, and an LLM judge. It is wired into CI.
Watchdog for AI Coding Agents
Jev Watch is a watchdog for AI coding agents that stops Codex or OpenCode when they loop, stall, or drift off task, then resumes the same session with a correction.
Coding-Agent Runtime Using Jev Decisions
Distill is a coding-agent runtime that uses Jev decisions for model routing, context retention, and tool selection.
Jevry Desktop Browser
Jevry is a desktop browser where Jev selects executable browser actions while a separate text model handles planning.