This research enhances COOK (Cognitive Orthosis for cOoKing) by introducing a fuzzy logic-based adaptive framework overcoming static rule-based limitations, enabling context-aware cooking assistance adapting to individual cognitive impairments. We developed a four-context fuzzy inference system integrating stove operations, environmental conditions, cooking methods, and user profiles to replace COOK’s static rules. Dynamic coefficient adaptation personalizes risk assessment based on user cognitive profiles, with weights auto-adjusted using incident history and temporal factors. Our proposal was validated through simulation across \(1.4 \times 10^6\) scenarios. The system demonstrated 76% variance explanation ( \(R^2 = 0.759\) ) with strong statistical significance (F-statistic \(= 175,000\) , \(p < 0.001\) ). Adaptive rule generation achieves an average confidence of 78% with successful pattern recognition in 82% of scenarios. This enhancement transforms COOK from static safety monitoring into adaptive, context-aware assistance providing personalized protection evolving with user behavior and cognitive patterns.