Glass-Box AI: Showing Model Confidence So People Trust It
aiuxdesign-systemneon
The problem is not the model
People mistrust AI when they cannot check it. I built a glass-box UI where every answer shows its work.
Three primitives
Confidence Rails encode certainty in the border gradient. High is solid, low is dashed.
Undo Trails keep a ghost of every generative action. You scrub back in one click.
Intent Forks show 2 to 3 plausible next steps as cards when the model is unsure. You pick, it learns.
How I built it
I stream tokens via SSE from a Neon edge worker, score hallucinations with a critic model, and log corrections for nightly tuning. Trust went up because control stayed with the human.