The user testing lab that actually ships
We test products like scientists test hypotheses. 95% confidence intervals before claiming a finding is real. Evidence over opinions, numbers over vibes.
SERVICES
Synthetic User Testing
Multi-persona simulation at scale. 30-50 runs per test. 95% confidence intervals. Adversarial validation included.
UX Taxonomy
Evidence-based pattern libraries built from real user voices. Design decisions backed by data, not opinions.
Landing Page Optimization
Persona-level conversion analysis. A/B variant testing with segmented messaging recommendations.
Product Research (JTBD)
Jobs-to-be-Done interviews at scale. Outcome-driven innovation, validated needs, prioritized features.
RECENT WORK
UX TAXONOMYTinylab: Evidence-Based UI Patterns
Turned 30 simulated user sessions into a comprehensive UX taxonomy. Result: 3-type system with 72% consensus, zero assumptions.
LANDING PAGELMTY: Homepage Variant Testing
Tested two homepage variants across 10 B2B SaaS personas. Found V2 optimizes for C-level (+34 pts) but alienates PMM ICs (-41 pts).
METHODOLOGY
RESEARCH
Build personas from real human voices. No assumptions.
SIMULATE
Drop personas into your product. 30-50 runs per test.
VALIDATE
Adversarial review. 95% CI before claiming findings.
SHIP
Report results immediately. Numbers, not vibes.