ConsultingWorkbench-backed AI security engagements — map, attack, defend, and prove your AI systems.
Scope a Review
Deliverablesfield-guide
field-guide

Field Guide Chapter DSL Sample

A sample field guide chapter using the Publication DSL for teaching and advisory content.

Sample0 offers0 CTAs0 personas
Publication overview
public-sample
pages0 offers0 personas0 CTAs
System
Field Guide Chapter DSL Sample
Environment
Production pilot
# Field Guide Chapter DSL Sample
Field Guide

How to read AI trust boundaries

AI systems fail at the points where trust changes: user to app, app to gateway, gateway to retrieval, gateway to model provider, gateway to tools, and gateway to logs.

Quote
The boundary is where the control belongs.
Field Guide
technical

Practical rule

When an AI component receives new data, authority, or context, ask what trust assumption just changed.

Boundary review checklist

Identify the actor.
Identify the data.
Identify the authority.
Identify the system receiving it.
Identify the control.
Identify the log.
Identify the owner.

Common AI boundaries

BoundaryMain riskControl
User to promptuntrusted inputinput policy
Prompt to retrievalunauthorized contextsource authorization
Gateway to providerthird-party data exposureminimization
Gateway to toolsstate changepermission matrix
Tools to logsweak reconstructionaudit trail
Decision · implemented

Reader decision

If you cannot name the control at a boundary, the system is not ready for serious review.