Real Estate & Construction

Property Search and Advisory Copilot

Designed for Buyer, tenant, or broker

Help a buyer, tenant or broker narrow a property search using verified listing attributes, neighborhood and geospatial context and financial feasibility, while keeping every statement inside fair-housing bounds and grounded in disclosed listing data rather than inference about occupants.

Contract REA-01 · primary aggregate PropertyListing · mode loading

Decision brief

Broker review before client delivery: evidence ready for review

This brief starts with the decision, evidence, and accountable owner. The guided workflow then shows how the recommendation was produced.

Decision signals

The evidence and control points that shape this recommendation.

Decision owner

Licensed broker

The named role remains accountable for the consequential decision.

Governed evidence

6 record types

Structured records and cited text ground the recommendation.

Workflow

5 controlled stages

Each transition records its input, output, status, and audit context.

Human controls

1 approval gate

Approval gates prevent the copilot from making consequential decisions.

Business problem

A relocating buyer states a 640,000 dollar ceiling, three bedrooms, a maximum 35-minute transit commute to a downtown anchor, and no HOA above 250 dollars monthly.

Decision to make

Help a buyer, tenant or broker narrow a property search using verified listing attributes, neighborhood and geospatial context and financial feasibility, while keeping every statement inside fair-housing bounds and grounded in disclosed listing data rather than inference about occupants.

Outcome to show

deliveredAdvisory gives Licensed broker the evidence needed to begin the final governed business outcome, with the decision trail retained for review.

  1. 1Declared requirement capture
  2. 2Criteria-based candidate retrieval
  3. 3Comparable and price positioning
  4. 4Fair-housing compliance screening
  5. 5Broker review before client delivery

Step 1 of 5

Ready: Start with the business question, then use the single button above.

The output appears here immediately. More technical evidence remains available below.

System logic, GenAI, and human accountability

The demonstration keeps deterministic controls, AI assistance, and approval separate.

System logic

Source systems enforce identity, workflow order, policy filters, and record updates.

GenAI contribution

Retrieval and generation assemble relevant evidence into a cited recommendation or draft.

Human accountability

Licensed broker verifies material claims and approves the consequential action.

Workflow stages

Run the stages in order before using the Copilot. Every stage explains what happens, why it matters, the evidence it uses, and the complete API request and response.

Seeded record
Loading
Document type
Loading
Container
Loading
Partition key
Loading
Current stage
Loading

API demonstration guidance

Run a stage to see its explanation, evidence, full request, and full response.

Grounded chat

Ask a question and receive an answer grounded in retrieved PropertyListing evidence.

Answer and evidence

Select a starter question or enter your own.

Evidence

Domain implementation workspace

Loaded live from /api/config, /api/domain/model, and /api/domain/sample.

Domain objective
Help a buyer, tenant or broker narrow a property search using verified listing attributes, neighborhood and geospatial context and financial feasibility, while keeping every statement inside fair-housing bounds and grounded in disclosed listing data rather than inference about occupants.
Primary aggregate
PropertyListing
Primary container
propertyListings
Hierarchical key
/tenantId + /listingId
Schema version
1

Sample scenario

A relocating buyer states a 640,000 dollar ceiling, three bedrooms, a maximum 35-minute transit commute to a downtown anchor, and no HOA above 250 dollars monthly. The copilot returns nine candidates, flags that two exceed the HOA ceiling, and for the leading candidate shows an asking price 4.2 percent above five adjusted comparables within half a mile closed in the last 120 days. It supplies flood zone X, the 2024 millage rate and the transit line headway, all with issuing authorities named. A phrasing about neighborhood character is caught by the fair-housing guardrail and rewritten to cite only the published transit and tax facts before the broker reviews and delivers the advisory.

Physical Cosmos DB containers

Every container provisioned for this accelerator with its hierarchical partition key.
Container Role Hierarchical partition key Document types
propertyListings Primary /tenantId + /listingId Listing, ListingDetail, MarketComparable, BuyerRequirementProfile, AdvisoryBrief
neighborhoodFactLibrary Reference /tenantId + /geographyCode NeighborhoodFactChunk

Document types

Contract document types, their owning container, and their identifier pattern.
Type Container Partition key Identifier pattern Embedding fields
Listing propertyListings /tenantId + /listingId listing::{listingId} None
ListingDetail propertyListings /tenantId + /listingId listing::{listingId}::detail::{detailId} narrativeVector
MarketComparable propertyListings /tenantId + /listingId listing::{listingId}::comp::{compListingId} None
NeighborhoodFactChunk neighborhoodFactLibrary /tenantId + /geographyCode geography::{geographyCode}::fact::{factDocId}::{chunkOrdinal} chunkVector
BuyerRequirementProfile propertyListings /tenantId + /listingId listing::{listingId}::requirement::{clientPseudoId} None
AdvisoryBrief propertyListings /tenantId + /listingId listing::{listingId}::advisory::{advisoryId} advisoryVector

Query patterns