AIQB
TutorialsOrdinary

The calibration bug that taught our fraud agent to wave fraud through

Source: DEV Community·

Summary

An agentic fraud investigator on TigerGraph: GSQL, GraphRAG, MCP, and a deterministic policy core the LLM cannot touch.
CategoryAI Tutorials & Practice
TierOrdinary
Published
Indexed by AIQB
SourceDEV Community
AIQB record IDintel-8659e8006a3d012c816f6f10
Read original source ↗More Tutorials

Related stories

Matched by category, entity tags and source

TutorialsOrdinary
I spent hours on App Store screenshots, so I built a tool that makes them
The most useful thing I learned building this: if you want an image model to work well with text,...
Source: DEV Community
TutorialsOrdinary
KV cache cut by ~45% with near‑same accuracy
Grouped Value Attention slashes transformer KV memory by roughly 45 % without hurting benchmark...
Source: DEV Community
TutorialsOrdinary
Matrix – Check whether your AI agent actually did what it claimed
Agents report success for actions that never happened — no error, clean trace, and every...
Source: DEV Community
TutorialsOrdinary
Why a swarm of AI agents is the hardest thing this series has tried to tame
AI Harness Engineering · Essay Eight · derek wang (derekwang85) Kevin Kelly opens Out of...
Source: DEV Community
TutorialsOrdinary
Building a fraud investigation agent on TigerGraph for Hacker House Goa
For the TigerGraph Hacker House Goa challenge we built an agent that works fraud alerts the way an...
Source: DEV Community
TutorialsOrdinary
I Think AI Is Making Coding Easier and Learning Harder
I can write code faster today than I could a few years ago. AI can explain an unfamiliar...
Source: DEV Community
TutorialsOrdinary
Building AICore: An Adaptive Computer Control Layer in Rust
Modern personal computers are becoming heterogeneous computing systems. A single machine may now...
Source: DEV Community
TutorialsOrdinary
Two AI APIs die this weekend: Perplexity Sonar (Sep 27) and Appsmith AI (Sep 30)
Perplexity retires Sonar on Sunday and Appsmith shuts down its managed AI plugin three days later. Here is how to find out if you are exposed in 15 minutes.
Source: DEV Community
TutorialsOrdinary
Launching LemonBeam: Onboarding Guides for GitHub Repos That You Can Verify
Today we're launching LemonBeam, an open-source tool that scans a public GitHub repository and...
Source: DEV Community
TutorialsOrdinary
Your Agent's Free-Text Output Is an API You Never Designed
Parsing a recommendation out of an LLM's prose is a fragile interface. Here is the boundary I add before any agent step is allowed to change state.
Source: DEV Community