At Anyone AI, I evaluate AI-generated websites and interactive applications for quality, functionality, responsiveness, and alignment with user requirements. I provide evidence-based feedback on model outputs, including visual inconsistencies, usability issues, and instruction-following failures.
At AfterQuery, I developed prompts, rubrics, and evaluation metrics for AI model assessment, and built challenging Terminal-Bench datasets. At Tinamart Business Group PLC, I built operational dashboards and led analytics projects that improved reporting accuracy by 25%.

