Computational Product Researcher

Research, redefined for an
AI-native world.

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.

"CPR is the bridge from static insight to agentic intelligence. We are moving from studying users to building systems that co-evolve with them."
The AI-native stack

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.

Continuous intelligence

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

Loading repositories from GitHub...
2027
CausalTrack: Detecting the Say-Do Gap in User Research via Multimodal Behavioural Analysis
ACM CHI 2027 — Conference on Human Factors in Computing Systems
In progress
2027
Synthetic User Council: Agent-Led Ecosystem Simulation for Pre-Deployment Product Research
ACM CHI 2027 — Conference on Human Factors in Computing Systems
In progress
2027
When Should Research Agents Act Autonomously? Safety Boundaries for AI-Conducted Studies
ACM FAccT 2027 — Fairness, Accountability, and Transparency
In progress
2026
CausalTrack — Methodology Validation Study
github.com/kgkazakos/causaltrack · 50 synthetic interviews · 611-node knowledge graph
Live
Python LangChain DSPy Streamlit Gemini Claude (Anthropic) OpenAI Neo4j LangGraph Click CLI pytest GitHub Actions