All projects

Confidential (real estate group) · Real estate

Multi-tenant AI platform automating real estate agency operations.

Private deployment, client project

Category

SaaS

Year

2025

Capabilities

AI, Cloud & Automation, Full-Stack

Industry

Real estate

Real Estate Operating System on a laptop
Real Estate Operating System on a phone

The problem

Real estate agencies managed CRM, compliance, marketing and document workflows across disconnected tools and manual processes. They had no unified system for client and property management or agreement generation.

Our approach

We built a multi-tenant AI system with specialised CRM, compliance and knowledge agents, then connected them to a marketing module and a complete document generation and e-signing pipeline.

Inside the product

More than one screen.

3 more screens from Real Estate Operating System, captured at device size.

Real Estate Operating System: Leasing pipeline on a laptop

Leasing pipeline

Leads scored by the CRM agent and moved through viewing, offer and contract.

Real Estate Operating System: Agreement generation on a laptop

Agreement generation

Tenancy agreements generated from templates and sent for e-signature.

Real Estate Operating System: AI agents on a laptop

AI agents

CRM, compliance and knowledge agents scoped to each agency’s own data.

On the phone

Real Estate Operating System: Home on a phone

Home

Real Estate Operating System: Leasing pipeline on a phone

Leasing pipeline

Real Estate Operating System: Agreement generation on a phone

Agreement generation

Real Estate Operating System: AI agents on a phone

AI agents

How it is built

Architecture

A React frontend talks to a Python and FastAPI backend, while LangGraph orchestrates specialised multi-agent workflows powered by OpenAI models. The multi-tenant architecture serves more than 30 agencies from one platform while supporting each agency’s own CRM and workflows.

Key features

CRM agent syncing with agency-specific CRMs
Compliance agent for regulatory workflows
Knowledge agent for pipeline and workflow Q&A
Marketing module for photography booking and brochure ordering
Vendor reporting
Automated document generation and e-signing

Challenges & solutions

Where it got hard.

Challenge

Each agency used its own CRM and operating workflow, so one fixed integration could not serve every tenant.

Solution

Put the differences behind agency-specific CRM integrations while keeping the agent workflow and product experience shared across tenants.

Challenge

CRM, compliance, knowledge and document tasks had to cooperate without turning one long workflow into a fragile chain.

Solution

Split the work into specialised agents and used LangGraph to coordinate their responsibilities and hand-offs.

Results

What shipping it changed.

30+agencies supported on one platform.
70%reduction in manual document and agreement processing time.

Stack

  • Frontend

    • React
  • Backend

    • Python
    • FastAPI
  • AI

    • LangGraph
    • OpenAI
  • Architecture

    • Multi-tenant Architecture

Let's talk

We can usually tell within one call whether the approach above transfers to your problem, and what would need to change.