I am exploring how AI can scale expert feedback in subjective domains with a hobby project.
After visiting art museums around the world, I kept coming back to a familiar challenge: how do you consistently evaluate something inherently subjective? After having created medical devices in pain, the idea was worth exploring. It’s a question that extends well beyond art—into areas like clinical assessment, training, and decision-making in healthcare.
To explore this, I built an AI-driven application that scores line drawings on a 1–10 scale across five criteria, paired with real-time, constructive feedback. I created a custom GPU server to keep it all secure, private and have unlimited tokens. I then queried that server from Miami, FL with each drawing and art, as it was being created live by hundreds of participants at a local gathering of makers.
At Maker Faire Miami (April 25–26), several hundred participants created drawings at the table, and received immediate evaluation and guidance.
What stood out:
- High engagement with structured, actionable feedback
- Rapid iteration and improvement within minutes (some kept modifying their art for higher scores)
- Interest from teachers and parents in using this to accelerate skill development in schools
It reinforced a broader idea: AI can help standardize and scale feedback in areas traditionally dependent on individual expertise.
In biotech and healthcare, the implications are significant—supporting training, improving consistency, and augmenting expert judgment in subjective evaluations.
Curious how others are thinking about applying AI to standardize decision-making without losing nuance?
