A WAF That Reads the Prompt: OWASP CRS for LLM and MCP
A conventional web application firewall reads a URL, some headers, and maybe a form body. For agent traffic that is the wrong layer. The interesting content is …
Read more →$
whoami --verbose
● always shipping
|
Portland, OR
|
agentic mesh · agent runtimes · ai gateways
MIKE MOORE
building the agentic future in public
I run LLMs, robots, and gateways into production walls so you don't have to. Deep dives on the agentic mesh, agent runtimes, AI gateways, and the Kubernetes substrate that keeps autonomous systems honest — every post ships with a repo you can clone and receipts you can check.
The Latest Drops
I Benchmarked Jev on Agent Tool-Call Risk. Calibration Held.
TypeSafe AI launched Jev on 2026-09-15 with the usual launch-day multipliers — 193.6x faster, 444.6x cheaper than frontier LLMs — plus “zero …
Read more →kagent v1.0 Can Run Claude Code as a Managed Kubernetes Agent
kagent shipped v1.0.0-alpha1 this morning, its first 1.0 line after nine months on 0.x. The tag says alpha; GitHub’s own release flag says otherwise; …
Read more →Two agentgateway CEL Gotchas: One Fails Open, One Fails Closed
I was writing a CEL authorization policy for an LLM route in Solo Enterprise for agentgateway : restrict which models a caller may reach, and refuse callers …
Read more →How I Use the Pocket AI Recorder for Meetings, Ideas, and Life
For about six weeks I’ve had a Pocket recorder stuck to the back of my phone, and it has quietly become the thing I reach for most after the phone itself. …
Read more →Agent Identity on Kubernetes: The Complete Series
An AI agent that calls a model, a tool, or another agent has to prove who it is. Almost every production failure I have written up this month traces back to …
Read more →Finding the MCP Servers Your Platform Team Doesn't Know About
An MCP server is a small HTTP service. Anyone on your team can start one in an afternoon, and the useful ones get built precisely because they reach something …
Read more →Securing AI Agents in Production: The Complete Series
Almost everything in this series started the same way: a control that everybody agrees is the right control, applied to an agent, quietly not doing the thing …
Read more →Conway's Law Is Coming for Your MCP Servers
I have some version of this conversation just about every week. A platform team is rolling out MCP across the company, and the plan looks the same every time: …
Read more →Your Agent's LLM Key Survives Every Kubernetes Secret Control
I gave an agent pod an LLM API key the normal way, as a Secret projected into its environment. Then I turned on every Kubernetes control that sounds like it …
Read more →