If you want a home between $500k-$600k on Zillow, there are 100+ pages to scroll through. We automated that. Agent² takes a spoken request over a phone call, extracts structured search criteria, scrapes and ranks Zillow listings, and submits a contact form on the top match. End to end in under 90 seconds. Form automation hits 94% across 200+ test submissions. The judge at GenAI Genesis 2026 called it one of the most technically impressive projects he'd seen.
Stack
Telnyx——SIP trunk routing inbound phone calls to EC2. Provides the raw 8kHz telephony audio stream the noise pipeline processes
PersonaPlex——4-bit quantized LLM on EC2 GPU instance for real-time voice interaction and criteria extraction during the call
SpeexDSP + RNNoise——Two-stage noise suppression stack: SpeexDSP for adaptive echo cancellation and AGC, RNNoise for neural residual noise removal. Dropped WER from ~29% to 8.3%
ScraperAPI——Zillow scraping with residential proxy rotation. Also provides the proxy pool that feeds the Playwright anti-detection stack
Playwright——Automated form submission with randomized mouse trajectories, gaussian keystroke timing, and viewport-realistic scrolling to defeat behavioral heuristics
FastAPI——Orchestration backend coordinating the noise pipeline, criteria extraction, Zillow scraping, listing ranking, and Playwright automation