AIMQA

This work presents an LLM-based decision companion that supports domain experts in assessing AI model quality within Low-Code / No-Code (LCNC) environments. The artifact focuses on contextualized interpretability by translating technical evaluation metrics into domain-specific explanations. Through a structured conversational “what” and “why” approach, it helps users understand model behavior, particularly via confusion matrix analysis, and supports informed decision-making without requiring deep technical expertise.