// writing
Posts tagged #security
A mix of technical deep-dives, career reflections, and dispatches from the road.
tag: #security
AINov 14, 2026· 4 min
Human-in-the-Loop Approvals: Pausing the Agent Is the Easy Part
Agent SDKs make approval gates a one-line flag. What decides whether they protect you is the approval screen, the policy behind it, and what happens on resume.
read more →
AIOct 24, 2026· 4 min
Prompt Injection Is an Architecture Problem, Not a Prompt Problem
Why system-prompt warnings don't stop prompt injection, and the lethal trifecta, taint tracking, and quarantined-LLM patterns that actually constrain an agent.
read more →
// the newsletter