SimAB: Simulating A/B Tests with Persona-Conditioned AI Agents for Rapid Design Evaluation
This addresses the need for faster, privacy-preserving design evaluation for experimentation practitioners, though it is an incremental improvement on simulation methods.
The paper tackles the problem of slow and impractical A/B testing by introducing SimAB, a system that simulates tests using persona-conditioned AI agents, achieving 67% overall accuracy and 83% for high-confidence cases against historical tests.
A/B testing is a standard method for validating design decisions, yet its reliance on real user traffic limits iteration speed and makes certain experiments impractical. We present SimAB, a system that reframes A/B testing as a fast, privacy-preserving simulation using persona-conditioned AI agents. Given design screenshots and a conversion goal, SimAB generates user personas, deploys them as agents that state their preference, aggregates results, and synthesizes rationales. Through a formative study with experimentation practitioners, we identified scenarios where traffic constraints hinder testing, including low-traffic pages, multi-variant comparisons, micro-optimizations, and privacy-sensitive contexts. Our design emphasizes speed, early feedback, actionable rationales, and audience specification. We evaluate SimAB against 47 historical A/B tests with known outcomes, achieving 67% overall accuracy, increasing to 83% for high-confidence cases. Additional experiments show robustness to naming and positional bias and demonstrate accuracy gains from personas. Practitioner feedback suggests that SimAB supports faster evaluation cycles and rapid screening of designs difficult to assess with traditional A/B tests.