Prompt-Repair Framework

Research · Prompt-Repair Framework

UW-Madison People & Robots Lab · Jan 2025 – Sep 2025

Pipeline adapting user prompts based on prior interactions using a novel Q-learning algorithm. +20% accuracy, +50% user satisfaction.

Details

- Full-stack prototype: React, Python/FastAPI, MongoDB - Co-authored paper submitted to UIST '26 - Collaborated with Professor Bilge Mutlu and Christine Lee

System demo

entry_id=1_z06dcwx5 widget_id=1_s8n28d18 title=AIR draft 1

This is the plain-HTML mirror served to crawlers, LLMs, and curl. Humans with a JavaScript-enabled browser see the rich React/XP-themed SPA at the same URL.

All plain pages · Live site · sitemap.xml