Free Resources

Everything here is free. No email gate, no upsell. Just stuff I built that might help you.

Last updated: April 11, 2026

Security Series

An ongoing series on AI security, local deployment, and enterprise reality. Start here.

Want the full MCP arc in one place? The MCP Security Hub has every episode, the defense framework, and free governance templates.

View the MCP Security Hub
Series Progress 17 of 17 episodes published
SECURITY SERIES

The Week Anthropic Leaked. The Internet Met an Owl.

Two incidents in one week. Anthropic's system prompt leaked. Then the source code. The internet met Zornix. Here's what operators actually need to know.

SECURITY SERIES

The Blueprints Are Public Now.

Anthropic fought the Pentagon in court to protect its architecture. Days later, a missing .npmignore line published the entire blueprint to NPM. The fortress fell to a config file.

SECURITY SERIES

Anthropic Did It Again.

A missing .npmignore line exposed 512,000 lines of Claude Code source. An intern found it. Then axios got hijacked. One config file, two incidents, zero excuses.

SECURITY SERIES

Anthropic Didn't Get Hacked. It Still Had a Security Problem.

A CMS misconfiguration exposed roughly 3,000 unpublished assets. One described a model nobody was supposed to see yet. That was enough.

SECURITY SERIES

MCP 201: The Governance Deficit

Shadow IT at scale. Audit trails that don't exist. Seven governance frameworks launched in sixty days.

BONUS

Your Policy Isn't Ready: Everything Anthropic Shipped in March 2026

Anthropic shipped Claude 3.7, Claude Code, and an updated usage policy in the same month. Your governance docs didn't keep up. Here's the gap.

EP.1

How I Turned a Gaming PC Into a Sovereign AI Server

The Nuclear Option. Why local AI on gaming hardware beats cloud for sensitive work.

Read on Substack
EP.2

Fear is Fake: Why You're Still Not Running Local AI

I waited 14 days to do a 20-minute task. Here's what I learned about overthinking the setup.

Read on Substack
EP.3

The Fifth Party Problem: Who Pays When AI Agents Go Rogue?

AI agents are making decisions in your name. The liability chain is longer than anyone admits.

Read on Substack
EP.4

Your Local AI Agent Is a Security Risk

Local does not mean safe. The Lethal Trifecta that makes local agents a problem nobody is talking about.

Read on Substack
EP.5

The Clean Room Method

Five steps to stop AI tools from leaking your information. Practical and repeatable.

Read on Substack
EP.6

Your Boss Just Saw What Goldman Did With AI. Here's What Happens Next.

Goldman automated back-office work with Claude. Your leadership team saw the headline. Here is what actually happened.

Read on Substack
EP.7

MCP 101: I Read the Documentation So You Don't Have To

Everyone is talking about MCP. Almost nobody has read the actual spec. I did. Here is what it says.

Read on Substack
EP.8

MCP 102: Claude Already Knows

MCP 101 was the spec. MCP 102 is the behavior. What actually happens when you flip the switch.

Read on Substack
EP.9

Your AI Vendor Just Became a Defense Contractor. Now What?

Anthropic refused five words in a Pentagon contract and got designated a supply chain risk. What that means for your enterprise stack.

Read on Substack
EP.10

Your AI Vendor Just Became a Defense Contractor

Anthropic refused five words in a Pentagon contract. Got treated like Huawei. OpenAI signed hours later. This is what it means when your AI vendor picks a side.

Read on Substack
EP.11

MCP 103: I Gave Claude Code Someone Else's Tools

Community MCP servers work perfectly. Claude chained three of them without being asked. Nobody approved any of it. That's the problem.

Read on Substack
Follow on Substack Notes for episode updates

Standalone Episodes

One-off deep dives that don't fit a series. Worth reading anyway.

EP.14

I Thought March Was Over. Then Anthropic Shipped Claude Computer.

Six products, a Pentagon lawsuit, and a self-graded safety plan. Everything Anthropic shipped in March and what it means for operators.

Follow on Substack Notes for episode updates