Business Analyst – AI Evaluation (Freelance, concurrent with Tenon role)
Performed side-by-side evaluations of AI model outputs, assessing quality, accuracy, and relevance against predefined evaluation guidelines. Conducted fact-checking to validate information and detect inconsistencies or inaccuracies in generated responses. Delivered consistent, well-structured written justifications supporting evaluation decisions while following established quality standards. • Compared GHD model outputs using evaluation rubrics • Identified and flagged incorrect or inconsistent claims via fact-checking • Wrote rationales to explain ratings/decisions clearly • Documented findings for communication with stakeholders