01 Security engineering / agentic systems
Trust less.
Verify more.
Field notes and small tools for systems that act. Focused on real boundaries, observable controls, and what survives contact with reality.
02 Operating position
Capability is not authority.
Good systems make the difference enforceable. I write about security architecture, adversarial testing, agentic AI, and the gap between a control on paper and a control that actually constrains behavior.
- 01
- Assume compromise
- 02
- Constrain consequences
- 03
- Keep the evidence
03 Recent transmissions
Field notes
Expanding Your Coverage With Agents
Agent workflows can produce useful first-pass security documentation so teams are not starting from scratch.
AI and Accuracy
AI can create enormous leverage, but confident output and polished citations are not substitutes for verification.
Not Everything Should Use AI
Generative AI is useful when imperfect output is acceptable and constrained. Most software still needs deterministic control paths.
04 Useful distractions
Short links.
Long shadows.
A small link utility, isolated from the editorial site and explicit about its boundaries.
Open the toolguest@shady:~$ shorten https://example.org/too-long
↳ shady.link/7f3a
guest@shady:~$