AI for real estate: software agents that answer leads, read leases and route maintenance requests
AI for real estate is used in practice to respond to and qualify inbound leads, write listing descriptions from property data, abstract leases, handle tenant and maintenance messages, and track transaction deadlines. Goldenroz builds AI agents for brokerages, property managers and proptech companies that work inside your CRM, MLS feed and property management system, with fair housing guardrails and human approval. Projects start at $25,000, fixed price per phase after a free one-hour scoping call.
From $25,000, fixed price per phase
Updated 2026-11-14. By Shai Goldenberg
What usually goes wrong
- Leads go cold in minutesPortal and website inquiries arrive evenings and weekends. By the time a person calls back, the buyer or renter has spoken with someone else.
- Spring volume overwhelms the teamListings and inquiries climb from early spring through summer, and leasing peaks in the same months. Hiring for the peak leaves idle seats in winter.
- Leases are long and all differentCommercial leases bury renewal options, escalations, CAM terms and notice dates in dozens of pages. Missed notice dates cost real money.
- Maintenance requests arrive as vague textsA tenant writes that the heat is broken. Someone must find out which unit, how urgent, whether it is covered, and which vendor to send.
- Data is split across systemsListing data sits in the MLS, contacts in a CRM such as Follow Up Boss, and units and ledgers in Yardi, AppFolio or Buildium. Nothing connects them without manual work.
What is included
- Scope of one workflowA written page naming the job, such as first response to rental inquiries for a portfolio, the systems involved and what the agent must hand to a licensed person.
- CRM, MLS and property system connectionsAccess to your CRM, MLS data under your feed license, and your property management platform through APIs or scheduled exports. See AI integration.
- Fair housing guardrailsFixed rules that keep the agent from describing neighborhoods by who lives there, steering, or treating inquiries differently. Screening criteria are applied by code, the same way for everyone.
- Channel complianceConsent records and opt-out handling for text messages, and quiet hours, built into the sending logic.
- Handoff to a personClear triggers for transfer: a pricing negotiation, a legal question, a complaint, or anything the agent cannot answer from approved content.
- Conversation and action logA record of every message, lookup and booking the agent made, tied to the contact and property record.
AI agents for real estate are software, and the license stays with people
The phrase AI agents for real estate causes confusion because the industry already has agents. Here it means software that takes actions: it reads an inquiry, checks availability, answers from listing data, books a showing and writes the result to the CRM. It does not hold a license and should not act as if it does.
State license law decides what an unlicensed assistant may do, and the same line applies to software. Quoting facts from a listing and scheduling are generally support tasks. Negotiating terms, advising on price and interpreting a contract belong to the licensee. We set that boundary in the scope and enforce it in the agent's rules, and your broker of record confirms where it sits in your state.
For conversation-heavy use across web chat and messaging, see AI chatbot development.
Fair housing, messaging rules and data licenses
The Fair Housing Act prohibits discrimination in the sale and rental of housing, including in the wording of listings and in how inquiries are answered. A model that improvises a description of a neighborhood can create a violation in one sentence. Real estate AI agents we build answer from approved property facts, and listing drafts pass a fixed check for prohibited language before a person reviews them.
Automated texts and calls fall under the Telephone Consumer Protection Act, which requires prior consent for many message types. MLS data comes with license terms on display and reuse. We build to the rules you give us and document how each is enforced. We are engineers, not lawyers, and your counsel sets the policy.
Tenant screening decisions stay with your existing screening provider and your written criteria. The agent can collect an application. It does not approve or decline one.
How the work runs
Scoping call
Before the projectWe map the process, the systems involved and the cost of a wrong action. You get a fixed price for the first phase.
Prototype
About 1 to 2 weeksA working agent on one narrow task, run against real examples in a test environment. You see where it fails before you pay for production.
Production build
Roughly 4 to 8 weeksIntegrations, permissions, fallbacks, approval steps, logging and the evaluation set. The range depends on how many systems the agent connects to.
Launch with limits
At launchThe agent starts on a share of the volume, or with every action approved by a person. Limits widen as the logs show it holds.
What it costs
Every phase has a fixed price agreed before work starts. Model usage is paid to the model provider from your own account.
- Focused agent or agentic workflowFixed price per phaseFrom $25,000
- Larger AI platformsSeveral agents, many integrations or a full product$100,000 and up
- Scoping callEnds with a written scope and a price$0
- Model usageBilled to your own accountPaid to the provider
Who it is not for
- Individual agents or small teams with budgets under $25,000. CRM vendors' built-in assistants fit better.
- Automated valuation, pricing prediction or tenant approval decisions.
- Agents that negotiate or give advice reserved for a licensed person.
Who does the work
Shai leads the technology side: business software, SaaS and mobile apps, payments and escrow systems, Postgres security, AI agents built with Claude Code and MCP, and IT and infrastructure projects with senior infrastructure engineers.
Questions buyers ask
What is AI for real estate used for right now?
Lead response and qualification, showing scheduling, listing description drafts, lease abstraction, tenant messaging and maintenance triage, and deadline tracking in transactions. Valuation models and price prediction are statistical products of a different kind, which we do not build.
How much do real estate AI agents cost?
Projects start at $25,000 at a fixed price per phase after a free one-hour scoping call. That budget suits brokerages, management companies and proptech products with real volume, not individual agents. The parent service is AI agent development.
Can the agent work with Yardi, AppFolio or our MLS?
It depends on the access each vendor grants your account. Some expose APIs, some only scheduled exports, and MLS feeds have their own license terms. We check the available route for each system during scoping, before a price is set.
Are your AI solutions for real estate able to send texts to leads?
Yes, where consent exists. The agent checks consent and opt-out status before every message, and respects quiet hours. Your counsel should confirm your consent language.
How long does a build take?
A prototype on one workflow typically takes one to two weeks, and production roughly four to eight weeks depending on integrations. Teams that want it live for the spring market should start scoping in the autumn or early winter.
Guides on this topic
- MCP is an open standard that connects AI applications to your tools and data. Learn how hosts, clients and MCP servers work, and what to secure first.
- An AI agent takes actions across your systems. A chatbot answers questions. Compare the two, see examples and use cases, and use the guide to pick one.
- Seven Claude Code practices from a production codebase: CLAUDE.md rules, guard hooks, worktrees, permission envelopes and CI review. Apply them to your team.
More for real estate
AI by industry
- AI agent development
- AI for accounting
- AI app and software development
- AI code review and AI coding training
- AI strategy and readiness
- Claude consulting and implementation
- AI for construction
- AI for education
- AI for enterprise
- AI for finance and banking
- Generative AI and LLM development
- AI for healthcare
- AI for insurance
- AI for law firms
- AI for logistics
- AI for manufacturing
- MCP and Claude integration
- AI for retail and ecommerce
- AI for small and mid-size business
- AI
Talk to the person who will do the work
One hour, no sales team. You talk to Shai Goldenberg, the CTO, about your systems or your product, and you leave with a clear next step and a price range.