AIBullisharXiv – CS AI · Mar 37/109
🧠
SimAB: Simulating A/B Tests with Persona-Conditioned AI Agents for Rapid Design Evaluation
SimAB is a new system that uses persona-conditioned AI agents to simulate A/B tests for rapid design evaluation without requiring real user traffic. The system achieved 67% overall accuracy against 47 historical A/B tests, rising to 83% for high-confidence cases, potentially transforming how companies validate design decisions.