Vai al contenuto
AI.info

events

Policy-Checked, Attributable, Revocable, Provable AI Agent Authorization

Intervento online su Caracal, un sistema open source per l’autorizzazione dell’IA, dedicato all’autorizzazione basata su regole, all’attribuzione, alla revoca e alla verificabilità delle azioni degli…

Policy-Checked, Attributable, Revocable, Provable AI Agent Authorization | Eventi sull’IA

In inglese

Starts
2026-10-02 14:00 UTC
Organizer
LFDT Milano
Location
Online event

A talk on securing autonomous AI agents, presented online by the Caracal team, Ryan Madhuwala and Shubham Sharma, with LFX mentees Mohammad Ali Haider and Ashutosh Singh also presenting their work. Caracal is an open source AI authorization system in development through the LFDT LFX Mentorship program, with support from GitHub, Microsoft and Vercel. The session covers why API key and identity models fall short for agents, what authority means in autonomous systems, Caracal's architecture for policy-based authorization, attribution, revocation and auditability, and practical approaches to securing agents in production.

Event website