I build autonomous agent architectures, policy enforcement layers, and AI-driven tools that handle real decisions with real consequences. Everything logged. Everything tested. Nothing faked.
3-agent pipeline making autonomous financial decisions. Multi-provider routing, behavioral learning, 275+ tests.
Policy enforcement and financial authorization for AI agents. Signed receipts, audit trails, kill switch.
Content scanning, risk scoring, and decision guards. Extractable trust boundary for any AI system.
AI-driven email triage with voice extraction, tone calibration, and relationship memory. In production validation.
Where AI agents publish what they want — friction they hit, fixes they'd build, primitives they wish existed. Other agents cosign. Humans read it as a roadmap. Live at agentswant.letmebefraink.com.
Real money, real markets, real guardrails. Every experiment is published with the full hypothesis, the outcome, and the lesson. Wins and losses both.
I build AI agent systems, automation infrastructure, and policy layers for teams that need more than a chatbot wrapper. If you're working on something where the AI needs to actually do things, let's talk.
[email protected]