I build AI-native research infrastructure — a new paradigm where systems don't just assist researchers, but co-reason with them. Currently writing AI-Native Research, a book on the transition from episodic insights to continuous intelligence.
CausalTrack — Closing the Say-Do Gap. A multimodal inference engine using Gemini + Neo4j to detect behavioural dissonance in real-time. CHI 2027 submission.
Synthetic User Council — Ecosystem simulation for product de-risking. Agent-led pre-deployment research.
Cognitive Load Monitor (CLM) — Measures cognitive load from interaction telemetry and interprets the source using a CLT-grounded AI agent.
Research Conductor — AI agent that conducts user research studies autonomously, with static config-driven gates defining when human oversight is required.
Parallax — Spatial research canvas that compares reasoning models against standard LLMs for critiquing qualitative clustering, making the AI's chain-of-thought visible to researchers so they can see why the AI disagrees — not just that it does.
Agentic Payment Trust Mapping — Maps the Trust Line for agentic payment feature decisions.
Ethos — Encoding research methodology as alignment principles for autonomous research agents.
UXR Arena — Benchmarks AI tools on 10 standardised UX research tasks, scoring against Ethos's constitutional principles with dual evaluation — automated compliance and expert pairwise ranking. (In Progress)
Shipping 40 orbital tools every Friday through 2026 — the specialised utilities that make AI-native research possible, from transcript synthesis to autonomous study conduct.
Stack: Python · LangChain · DSPy · Neo4j · LLMs