A security gate you can poke
An interactive, deterministic intercept-gate — propose a command and watch a no-LLM ruleset allow, hold, or block it, with its reason.
// A personal blog — my own experiments and views, not my employer’s.
Experiments in AI, security, memory & more.
Agent M Dashboard online
System Status:Active
Memories:474
Connections:943
Words:420K
Sources:4.6K
Projects:10
Local Time:––:––:––
Illustrative only, based on a real example.
On the tools I build and what I have learned running them.
New here? Start with → A security gate you can poke · Why I started Agent M
A kill-switch you can’t override isn’t a kill-switch — it stopped my own agent cold today, which is exactly the point.
Why I started Agent M
Every agent I tried was brilliant for an hour and a stranger the next morning. So I stopped waiting for a smarter model and built the memory.
CSS color-mix() gives you a full light/dark token system with no preprocessor and no build step — derive every muted and hairline shade from two base colours.
A security person's case for boring, auditable AI tooling
Useful-enough-to-depend-on and safe turn out to be the same problem. The boring path -- deterministic gates, legible state -- is the one that scales trust.
Gating on deterministic checks before the LLM-judge cut my review noise roughly in half. Cheap, truthful checks first; the expensive, sycophantic one last.