Insights

Blog

Insights on AI runtime security, healthcare AI governance, and cryptographic proof for regulated industries.

Runtime proof · OVERT

The OVERT series

Evidence-grade explainers on verifiable AI, runtime attestation, and proving what your controls actually did.

AI Security

AI Security Solutions That Leave a Receipt

Most AI security solutions stop at alerts. The real differentiator is proof — runtime controls that emit signed, verifiable OVERT receipts.

Joe Braidwood · · 6 min read
Security

After a Prompt Injection Attack, Prove What Held

A single prompt injection attack can move markets. Prevention is never perfect — so hold tamper-evident proof of which guardrails fired.

Joe Braidwood · · 5 min read
Agentic AI

Agentic AI Security Needs Proof, Not Promises

Agentic AI security can't rest on self-reported logs. Make autonomous agents witnessed — independent, tamper-evident proof of what ran and which controls held.

Joe Braidwood · · 6 min read
Agent Security

AI Agent Security: Prove What the Agent Did

AI agent security means enforcing controls at the action boundary and producing signed OVERT receipts that prove what the agent actually did at runtime.

Joe Braidwood · · 6 min read
Cybersecurity

AI in Cyber Security: The Missing Evidence Layer

Detection and response made the SOC faster — but neither proves a control held. AI in cyber security needs the runtime evidence layer the SOC is missing.

Joe Braidwood · · 6 min read
Data Security

AI Data Security: Verify a Receipt, Not the Data

AI data security proven without exposing the data: a signed OVERT receipt lets a third party verify a runtime control fired — only hashes and signatures cross the line.

Joe Braidwood · · 6 min read
Attestation

Independent AI Attestation: Proof, Not Promises

Independent AI attestation is tamper-evident proof a third party can verify that your AI controls executed — without protected data leaving home.

Joe Braidwood · · 6 min read
Governance

Your AI Governance Documentation Isn’t Evidence

AI governance documentation records intent, not proof. See why policies and self-reported logs aren’t evidence — and what a tamper-evident receipt is.

Joe Braidwood · · 6 min read
Governance

AI Governance Solutions Need a System of Proof

Most AI governance solutions are a system of record for intent. Add a system of proof — signed runtime receipts that show the control actually ran.

Joe Braidwood · · 7 min read
Governance

AI Governance Tools Need a System of Proof

AI governance tools state intent — policies, registers, approvals. None proves a control ran. OVERT receipts add the runtime proof: asserted, then proven.

Joe Braidwood · · 5 min read
Governance

An AI Governance Maturity Model: From Policy to Proof

An AI governance maturity model that stops at “documented” measures intent, not evidence. Reframe maturity from policy to verifiable proof at runtime.

Joe Braidwood · · 6 min read
Governance

AI Governance Challenges: The One No One Names

Most AI governance challenges are problems of intent. The hardest one is a problem of execution: proving what your AI systems actually did.

Joe Braidwood · · 5 min read
Governance

What Is AI Governance? Intent vs. Proof

What is AI governance? It's how an organisation directs and proves its AI behaves — the policies that state intent, and the runtime evidence that proves controls ran.

Joe Braidwood · · 6 min read
Team

Why our new CTO left Microsoft after 19 years

Rohit Tatachar joins as co-founder & CTO after nearly two decades at Azure. The inside story.

Joe Braidwood · · 5 min read
White paper

Healthcare AI is uninsurable

The first framework for underwriting healthcare AI risk. Four case studies. Three liability domains.

Jennifer Shannon · · 7 min read
OVERT 1.0 launch

We couldn’t ship our own AI

Why we open-sourced auto-redteam and published OVERT 1.0 — the open standard for AI runtime trust.

Joe Braidwood · · 10 min read
Open source

Why autoredteam.com is an open-source commitment

Why open-source auto-hardening matters and how autoredteam.com connects to safer AI deployment at scale.

Joe Braidwood · · 6 min read
AI safety

Voluntary AI safety just died

Anthropic abandoned its RSP. The voluntary era is over. Here’s what replaces it.

Joe Braidwood · · 8 min read
Conference

ViVE 2026: Healthcare AI gets asked for its receipts

We’re in LA Feb 22–25. The AI accountability conversation healthcare has been building toward.

Joe Braidwood · · 5 min read
Year ahead

2026: the year Healthcare AI gets real

JPM kicks off a pivotal year. State laws take effect, consent litigation accelerates, and governance committees want proof.

Joe Braidwood · · 5 min read
AI governance

The three layers of AI security

Most AI security solutions cover runtime protection. But there’s a critical third layer.

Joe Braidwood · · 8 min read
Regulation

EU AI Act Healthcare: what to know

Most healthcare AI is classified as high-risk, triggering strict logging requirements.

Joe Braidwood · · 10 min read
Clinical AI safety

When AI hallucinations become malpractice

“One beer at a wedding” becomes “daily heroin use.” Without evidence, who’s liable?

Jennifer Shannon · · 9 min read
Compliance

Why SOC 2 won’t protect you from AI risk

SOC 2 and HITRUST are essential for IT security. But they weren’t designed for AI.

Joe Braidwood · · 7 min read
State regulation

Colorado AI Act for Healthcare vendors

Colorado repealed and replaced its 2024 AI Act with SB 26-189, covering automated decision-making technology from January 1, 2027.

Joe Braidwood · · 8 min read
AI governance

Building AI trust through evidence

The difference between “we have guardrails” and “here’s proof.”

Joe Braidwood · · 7 min read
Technical deep dive

How we used AI without a BAA

Deploying an in-line redaction proxy that strips PHI before it reaches external APIs.

Rohit Tatachar · · 12 min read
Infrastructure

Why we built GLACIS on Cloudflare

Global latency, edge compute, and enterprise security via Cloudflare Workers Launchpad.

Rohit Tatachar · · 6 min read
AI governance

Free AI runtime security assessment

Discover your AI runtime security posture with our free 2-minute assessment. Get your score and personalised recommendations.

Joe Braidwood · · 4 min read
Compliance

ISO 42001: is certification worth it?

Costs, benefits, and limitations. When certification makes sense vs. using the framework internally.

Joe Braidwood · · 8 min read

Ready to unblock your deals?

Runtime coverage starts on one named workflow that gives AI vendors evidence for deals, audits, and internal assurance.

Get runtime coverage