Project

AI-Powered Pet-Caregiver Matching

Production FastAPI backend combining multi-layer rule filtering with a structured 22-question rubric evaluated by an LLM agent for compatibility scoring. Powering 100+ monthly bookings.

Website

llmmatching-systemsproduction

Problem

Matching pet owners with qualified caregivers requires balancing hundreds of compatibility factors that humans can't efficiently evaluate at scale.

Solution

Multi-layer rule-based filtering with LLM-evaluated rubric scoring, integrating Redis, MySQL, and OpenAI for real-time compatibility recommendations.

Impact

100+ monthly bookings on the pawsome.vip concierge platform with measurably higher match quality.

Stack

FastAPIOpenAIRedisMySQLDockerSentry