AI for Real Estate - Humans-in-the-Loop Agents Hackathon
AI Tinkerers - San Francisco
Hackathon Showcase

AI for Real Estate

Build an AI-driven property-management platform that automates tracking and KPIs—Product Manager/ex-agent/investor seeks full-stack engineer to join.

5 members Watch Demo

Our project combines human-in-the-loop AI to transform property management, making leasing faster, more efficient, and more accessible. We allow property managers to get rental tenants by purely uploading images.

How It Works:

  1. AI-Powered Automation: The AI handles the heavy lifting, from posting listings to responding to common questions, using real estate-specific knowledge and tools like Zillow estimates.
  2. Human Review and Control: The system brings in property managers at crucial points (like pricing adjustments or legal compliance) to approve or adjust responses generated by Gemini. A user-friendly chatbot interface shows the AI’s reasoning and lets managers make corrections easily.
  3. Learning and Improving: We built feedback loops into the system, so every human input helps the AI learn and get better over time.

Our approach shows how AI and humans can work together seamlessly, making property management faster and more efficient while keeping people at the center.

We started from scratch and used a streamlit template for the front end

AI Tinkerers Google HumanLayer Weights & Biases

https://github.com/michaelwang2018/property-manager-agent

Summarizing URL...