I spent more than 15 years at the bedside as a Registered Nurse. Now I use that clinical judgment to evaluate AI. I review AI responses for accuracy, helpfulness, tone and safety, rank and rate outputs against rubrics, and explain every judgment in clear written English. I put accuracy ahead of speed.
Clinical background
Psychiatric nursing, substance use treatment, hemodialysis, medical-surgical, cardiac telemetry, veterans healthcare, hospice, home health and case management. Day to day that meant assessment and triage, medication safety, reading labs and telemetry, escalating changes in condition, and teaching patients and families in plain language.
AI evaluation
- Designed and ran a benchmark suite comparing 5 frontier AI models across research, voice, editing and logic.
- Built a clinical safety benchmark: 5 fictional patient scenarios, each with a hidden safety trap, 25 responses scored.
- Spotted that a visible scoring rubric was inflating results, reran under clean conditions, and caught risky advice the first run hid.
- Side-by-side ranking with a written justification for every call; claims checked against primary sources.
Business
- MixedBagPublications LLC: author and publisher on Amazon KDP.
- MixedBags.Store: an AI-assisted Shopify store where I review AI-generated images and product copy before anything goes live.
Education
- Master of Science (MS), Health Sciences, Excelsior University
- Master of Arts in Liberal Studies (MALS), Excelsior University
- Bachelor of Science (BS), Psychology and Health Professions, Excelsior University
- Associate of Science (AS), Nursing, The Academy for Nursing and Health Occupations
Get in touch
Open to AI evaluator, RLHF and healthcare SME roles. Contact details coming soon.