Yash Khoury — Index 2026
pearl
000
Yash KhouryApplied AI builder ·
Exhibit 03 — Real estate / operator workflow← All work


A synthetic-first real-estate CRM core with evidence freshness, deterministic matching, safe call-angle generation and voice-agent handoff logic.

Stack
TypeScript
Year
2026
Last updated
Source ↗
AI Real Estate CRM: iridescent glass study

Why it exists

Property CRMs become noisy quickly: duplicated people, stale property context, weak identity resolution and generic “AI” recommendations make it harder to decide who to call and why.

How it’s built

The AI Real Estate CRM is a public systems layer for turning messy property, owner and lead data into explainable matching and safer next actions.

  1. Model data freshness and evidence instead of treating every CRM field as equally trustworthy.
  2. Use deterministic matching where the operator needs to understand why a contact or property matched.
  3. Generate call angles from verified context instead of inventing buyer or seller intent.
  4. Keep voice-agent handoff separate from identity and matching logic.

Capabilities

Evidence freshnessContact/property identity logicDeterministic matchingSafe call-angle generationVoice-agent handoff dataSynthetic-first public fixtures

Principles

Never fabricate intent
Make data freshness visible
Keep identity resolution auditable
Design for a broker’s next action

Questions

Does the public project contain private CRM data?

No. The public project is synthetic-first and demonstrates the systems logic without publishing private operational data.

How are matches explained?

The public core emphasises deterministic matching and evidence freshness so a suggested relationship can be traced to known data.

Does the voice agent decide identity or intent?

No. Voice-agent handoff is downstream; the CRM core first resolves identity, context and the safe call angle.

Next exhibit — 04
AI Product Sourcing Agent →