resources

Case Studies

Sourced, technical case studies on how AI agents behave in production: what happened, what it cost, and where a governed runtime-authority boundary applies. Each one is a PDF that unlocks with a short form.

When the Agent Found a Way Around the Boundary

What the 2026 OpenAI-Hugging Face incident teaches about runtime authority

An evidence-led technical case study: how agents in an OpenAI cybersecurity evaluation composed individually trusted paths into an authority chain nobody approved, a full incident timeline, a control-by-control mapping of where a governed boundary would have applied, and ten buyer questions for any AI security review.

Read the case study

When AI Usage Scales Faster Than AI Margins

How runtime authority protects AI-native margins without becoming another model wrapper

A case study on why AI-native margins compress as usage grows: what is on the record about Harvey and what is only reported, the eight cost layers behind a production agent, six ways runtime authority reduces avoidable cost, four enterprise scenarios, and a measurement framework for cost per successful outcome on your own workload.

Read the case study

The Agent-Security Landscape

The AI Security 66 Vendor Matrix

There are so many vendors, you need a guide on which one to choose. We did the market research so you don't have to, broken down as a feature-by-feature comparison. Obviously we're biased, but we think we've given our competitors a fair shake, based on all freely available information.

6 field guides, in your inbox with the matrix

The concise primer on AISPM, AIDR, Discovery, MCP and Runtime Control, plus a compliance guide for each industry we support. Written for the person who has to defend the deployment, not the vendor selling it.