An AI co-pilot for risk analysts at financial firms and transaction platforms. It catches account takeovers, clears good customers, and keeps the final decision in code so persuasion can’t lower the risk.
This runs Sentinel’s deterministic rules and manipulation detector in your browser. The anomaly score here is a simplified stand-in for the Isolation Forest, and the AI investigator runs only in the full app.
All public, no sign-in needed.
Two minutes: the Binance breach, the live demo, the charts and the takeaways, narrated with captions.
Watch on YouTube →The 16-slide pitch: the Binance breach, what Sentinel is, how it holds the line, real-data results, weaknesses and next steps. Arrow keys to navigate, N for speaker notes.
Open the slides →A five-minute core script: one case end to end, the techniques, seven weaknesses with fixes, a Q&A cheat sheet and every number to quote.
Read the script →Sentinel’s rules and manipulation detector running in your browser. Nine scenarios, every field editable.
Jump to the tester →Twelve interactive charts in five acts: the threat, detection, decisions, holding the line, and the scenario lab.
See the charts → Chart scriptPython + Streamlit: live cases, attacker chat, red team and the chart story. Runs offline; add keys for the AI investigator and tracing.
Quick start →Benchmark outputs, the attributed RBA sample, red-team logs and the scoring code, all in the repo.
Browse the data →Five layers; code keeps the last word.
Each session compared with the user’s own history and with all users.
Impossible travel, credential stuffing, reset-then-payout set a minimum risk.
An Isolation Forest flags what is unusual for this user.
Claude explains the case and may raise risk, never lower it.
Plain code picks allow, MFA challenge or lock.
Observability and guardrails for AI agents. Every investigation is sent as a trace (case, floor, verdict, rules fired) so an auditor can replay why an account was locked; support-chat text goes through PRISM’s prompt-injection guardrail.
Visit PRISM → DocsOne OpenAI-compatible API for many models. Sentinel calls Claude Sonnet 5.5 / Opus 5.5 through it, with failover and free cached answers for repeat cases. A full 695-session run cost about $0.75.
Visit Nicrron →Streamlit console with live cases, an attacker chat and the five-act chart story. Works offline without keys; add Nicrron and PRISM keys to turn on the AI and tracing.
Quick start →Click any chart for the interactive version. Real data: 87 takeover and ~76k legitimate logins from the RBA dataset; held-out users, thresholds set without labels.