Zillow builds a Fair Housing Guardrails system for LLM-powered real estate conversations
Out-of-the-box LLMs applied to real estate conversations could violate Fair Housing Act requirements by steering users based on legally protected characteristics, creating legal risk and inequitable service at scale.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · User submits real estate query
A user engages the conversational interface to discuss real estate topics such as understanding the process and identifying a desired location.
Tools used
BERTLLM
Outcome
Zillow designed and deployed internally a combined Fair Housing Guardrails system uniting prompt engineering, a stop list, and a fine-tuned BERT sequence classifier to detect FHA violations both pre- and post-LLM processing, with iterative improvement via human review and feedback.
What failed first
Prompt-based compliance instruction produced high recall but non-deterministic, low-precision behavior that over-flagged permissible queries. Stop-list matching lacked contextual awareness, misclassifying location names and accessibility-related queries as non-compliant.