Skip to the card

Card 919 of 9932026-09-21 issue

Observed arrival · 2026-09-21

VAIS Boundary: Keep Authority Outside the Model

vaisboundary.com Visit website
Editorial interest 84/100 Selection signal · not a rating of the site

An AI security boundary that mediates agent tool calls, applies trusted policy, and independently checks observable effects.

Landing page captured for the 2026-09-21 issue.
For
AI security engineers evaluating agent tool access
Worth noticing
The site reports 4,603 evaluable episodes and explicitly excludes two remaining target failures from defended conclusions.

Field notes

The project separates authority from the model and frames agent security as a measurable sequence rather than a single guardrail. Its evidence section records 14 of 15 models completing the full stage and leaves two unevaluated target failures outside defended conclusions. The page also reports that a separate lab experiment failed to validate both preregistered primary outcomes, making the limitations unusually visible alongside the results.

Observed signals

Read the marks

Editorial observations of this landing page, not a rating.

OpenPublic substance visible
PrettyNotable craft visible
ProPolished or operationally mature
NicheUnusually specific use

One card from the complete issue

A Passport-Sized Place to Begin

246,713 arrived 999 judged 993 catalogued Enter the complete issue
vaisboundary.com

Landing page observed 2026-09-21. The live site may have changed.