Vai al contenuto
AI.info

events

AI Governance Needs a Test Plan: Turning Principles into Evidence

Tanvi Mittal mostra come i framework di governance dell’IA diventino prove verificabili, presentando ai team di QA l’approccio PROBE al red teaming, al monitoraggio e alla valutazione.

AI Governance Needs a Test Plan: Turning Principles into Evidence | Eventi sull’IA

In inglese

Starts
2026-10-27 23:00 UTC
Organizer
Innovate QA Meetup Group
Location
Online event

Innovate QA Meetup Group hosts an online session by Tanvi Mittal on making AI governance testable. Frameworks such as the EU AI Act, the NIST AI Risk Management Framework and ISO/IEC 42001 set expectations for safety, fairness and oversight but leave open how to prove them; the talk connects those requirements to quality engineering practice. Mittal presents PROBE — Probabilistic Baseline, Red Team It, Observe in Production, Behavioral Contracts, Evals Not Assertions — and discusses adversarial test suites, production monitoring and evaluation gates for non-deterministic systems.

Event website