project

Secure Agent Findings Exchange

Industry effort to build shared infrastructure for reporting AI agent failures and vulnerabilities across companies, modelled on software vulnerability disclosure.

Current clusters

build1 publisher

Telling an agent's harness bug from a model bug takes a replay of the whole run

Nvidia's Adel el Hallak told The New Stack that logs and outputs are not enough to diagnose an agent failure. The industry's shared answer so far is SAFE, a findings exchange backed by roughly 140 companies.

Publishers:thenewstack.io

Reality

Evidence44
Adoption30
Hype gap+24
Incentives82
Confidence44