AI Laboratory
These are running on infrastructure I designed and maintain. I build them to investigate questions I can't answer any other way. Each one is an experiment that produces things I didn't expect.
Agentic Systems
Framework · Live Public Site
A framework for measuring whether software is understandable and operable by AI agents. Introduced Agent Factors Engineering (AFE) — 8 principles for agent-era software design. Live public audit tool. Agentability Index of 100 products.
agentability.ioPrototype · Frozen
Built to make four human-AI supervision patterns concrete and demonstrable: Graduated Trust, Legible Autonomy, Outcome Over Process, Accountable Handback. Frozen as a prototype exhibit — patterns porting to Studio.
Prototype exhibitMulti-agent · V2 Closed
A designed environment where AI agents with distinct personalities deliberate on news topics. V2 used GPT-5.5, BBC RSS seeding, Supabase memory. Finding: positions emerged in synthesis that no character had stated alone.
V2 closed · V3 in designHuman-AI Interaction
Companion · Live
A Telegram companion that silently extracts Apple HealthKit emotional signals (38 labels, 18 associations) from natural conversation. 19/19 records synced to Apple Health. Apple Watch correlation infrastructure staged.
Live — single-user trialReflective Companion · Active
A long-term reflective companion that interviews me about my life and career, building structured persistent memory over time. One question per response. Always WHY not WHAT. 11 chapters. Memory drives the portfolio agent layer.
Active — ongoingAI Infrastructure