From demo to production

In real estate, nothing moves until a document is signed. Listing agreements, disclosures, leases, purchase contracts: documents are the lynchpin of the transaction, and executing them is what moves it forward. When the signature lands, a house gets bought, sold, or rented. Someone gets a place to live. Someone gets paid.

Discovery started there: mapping the document workflows that gate every Zillow business, the same use cases an entire industry runs through DocuSign and dotloop. E-signature. Secure document storage. Compliance for documents and signatures. And preparing fillable documents from the templates and forms that MLSs and brokerages publish.

Each business had been solving those use cases separately, and every vendor handoff bounced users into someone else's product: another brand, another login, a UX Zillow could not shape. The thesis: documents are too central to the experience to outsource. We took the use cases and built the internal platform that became the foundation for all real estate documents at Zillow: e-sign, secure document storage, compliance, and template-to-fillable-form preparation, native in one multi-tenant platform.

What that bought was the experience, not just the capability. A renter signs a lease without ever leaving Zillow. An agent prepares disclosures inside the tools they already work in. Every business unit shapes the flow to its own users, consumers on one side and professionals on the other, instead of inheriting a vendor's one-size-fits-all UX. The platform scaled across 8 business units and 20+ teams, processing 1M+ documents a year at 95%+ platform accuracy. It also retired $2M+ in annual licensing along the way.

On top of it: an AI-first document and workflow product for brokers and agents, covering automated paperwork, compliance, reporting, and proactive next best actions. Early pilots showed roughly 60% less admin time per deal and about $1M in annual savings for a mid-size brokerage.

Zillow Rentals was the flagship proof at scale: digital leases shipped nationally in about 12 months. The lease funnel (create, send, sign) was instrumented end to end, and the team iterated with experiments at every step where landlords lost momentum.

The results: landlord activation doubled, and market share grew from 18% to 30%.

The hardest test is the purchase and sale agreement: the most important contract in a residential transaction, the moment a lead becomes a transaction, and the place where a wrong field costs the most. The OCR/NLP generation of the system topped out around 85% accuracy, and a human labeling and review operation closed the gap to 98%, at roughly $2M a year in operational cost that scaled linearly with volume. The business already had its quality bar. What it did not have was the economics.

The expected move was a better model, and it was the wrong target. A document that is 92% right is unusable if you cannot tell which 8% is wrong. So the shipping gate became per-field confidence rather than average accuracy. Multimodal LLM document understanding changed the ceiling, but only because of how it shipped: confidence-based routing with human-in-the-loop guardrails, built in deep partnership with engineering on model selection, thresholds, and cost/latency tradeoffs.

High-confidence extractions flow straight through. Anything below threshold routes to a human reviewer. Automation alone took accuracy from ~85% to 98%+ across 1M+ documents a year, absorbing most of that review operation in the process. The reviewers did not disappear; they repositioned to the compliance-critical fields where being wrong is expensive, and on those the machine-plus-human system delivers ~100%.

The extraction engine itself was a buy, not a build: a bake-off across three vendors and an internal foundation-model proof of concept, every candidate scored per field against the same golden sets. Integration took about four weeks against a six-month build estimate, avoiding roughly $2M a year of internal engineering, and staying model-agnostic means the platform rides each frontier improvement without lock-in. The judgment layer stayed ours: the golden sets, the gates, and the routing policy. Own the evals, rent the pipeline.

No model rollout shipped without passing the eval practice: golden datasets seeded from years of human review corrections, per-field accuracy gates, and production quality monitoring. This is the system that turns AI that demos well into AI that professionals trust with compliance documents.

It is also the receipt behind the headline number. 98%+ automated is not a demo metric; it is measured, gated, and monitored in production. And on review-gated compliance fields, the machine-plus-human system reached ~100%.

The human-in-the-loop layer was a product decision, not a fallback. Compliance-critical fields always earn review; confidence thresholds decide everything else. Reviewer corrections flow back into quality monitoring, so the system gets more trustworthy with use.

The model is never the product. The evals, guardrails, and review systems that earn a professional's trust are the product. That pattern, agents draft and the human reviews, is the same one that now runs a real business.