AI Tools User & Prompt Crafter | TELUS (AI evaluation and response quality analysis)
Tested and evaluated advanced AI models across factual, creative, conversational, and technical tasks. Designed evaluation prompts to measure reasoning depth, edge-case handling, and structured problem-solving quality. Flagged logical, formatting, and structural issues in model responses to support continuous improvement.• Assessed AI outputs across multiple task categories (factual, creative, conversational, technical).• Authored evaluation prompts targeting reasoning depth and edge cases.• Identified and reported logical, formatting, and structural defects in responses.• Supported iterative model improvement through quality findings.