AI real estate agent with listing search, mortgage calculation, neighborhood intelligence, and showing scheduler
The Real Estate Concierge AI Agent framework is the AI prompt system for real estate brokerages, PropTech platforms, and individual agents building AI that handles the high-volume, time-intensive work of buyer and seller engagement. Real estate agents spend 60% of their time on activities that don't require their expertise: answering basic listing questions, explaining mortgage math, scheduling showings, and providing neighborhood information. This framework automates all of it with an AI concierge that qualifies buyers, searches the MLS via natural language, calculates mortgage scenarios, delivers neighborhood intelligence, and schedules showings — freeing agents to focus on negotiation, relationships, and closing. The framework includes both buyer-side and seller-side agent modes.
Full Access Unlocked
All 56 prompts · All 6 modules
"The buyer qualification flow — gathering budget, pre-approval, timeline, and must-haves in a natural..."
Broker/Owner · Independent brokerage, 28 agents
Need expert implementation?
Hire an OrchestratorConnect with a certified Prompt.Doctor Orchestrator to deploy this framework for you.
No coding required. You will use ChatGPT or Claude as your AI tool. Follow these steps in order — do not skip ahead.
Purchase & download the framework
Click the buy button on this page. After checkout, go to the and hit Download .zip. Unzip it — you'll get a .md file (the full framework) and a .pdf (easy to read reference). Keep both open.
Open your project — new or existing
This dashboard is designed to integrate into any existing project or be built as a standalone app. If you already have a site in Airo (or Cursor, Bolt, etc.), open that project. If you're starting fresh, create a new project. The Orchestrator Prompt handles both cases — it scans what's already there and adds only what's missing.
Paste the Orchestrator Prompt into your builder's chat
Open the on this page. Copy the Orchestrator Prompt and paste it into your AI builder's chat. It will scaffold the full admin system — secure login, email marketing module, booking engine, and CMS — on top of your existing codebase. This takes 2–5 minutes.
Add your API keys as secrets
Critical — Novice UsersIn your builder, go to Settings → Secrets and add the keys your app needs. For this framework: STRIPE_SECRET_KEY (for booking payments — get it from your Stripe dashboard), ANTHROPIC_API_KEY (for AI-assisted content — get it from console.anthropic.com), and DATABASE_URL (your MySQL connection string). No key is needed for the admin login, CMS, or email modules — those run on your existing infrastructure.
Don't have a MySQL server?
You can purchase a shared hosting plan with cPanel and MySQL at host.esgwon.dev. Once your account is set up, follow the step-by-step guide to create your database and connect it to your AI website builder.
How to set up cPanel MySQL & connect to your AI website →Need help with Stripe?
Get your STRIPE_SECRET_KEY and STRIPE_PUBLISHABLE_KEY from your Stripe dashboard. The guide covers test keys, webhook setup, and going live.
Need help with Anthropic?
Get your ANTHROPIC_API_KEY from console.anthropic.com. The guide covers model selection, cost management, and troubleshooting.
Prompting Airo after setup — always name the file
When asking Airo to add tables, columns, or features to the admin dashboard, always include src/server/lib/admin-db.ts in your prompt. Without it, Airo may target the wrong database. Example: "Add a bookings table in the admin database (src/server/lib/admin-db.ts) — do not touch any other database connection in this project."
Run the framework prompts inside your live app
Your app is now running in the builder's preview panel. Open the on this page, copy each prompt one at a time, and paste it into your builder's chat. Replace every [BRACKET] with your real data before sending. Work through the stages in order — each stage output feeds the next.
Test end-to-end, then publish or hand off to your client
Walk through the admin as a real user: log in, create a booking, send a test email campaign, update a CMS image, and run the Safe-to-Publish gate. Once everything passes, click Publish in your builder. Because this is a white-label dashboard, your client accesses it at /admin on their own domain — no Prompt.Doctor branding, no third-party login required.
6 modules · 56 prompts · 6 workflow stages
Buyer Qualification Engine
Budget range capture, pre-approval status, timeline (browsing/active/urgent), must-haves vs. nice-to-haves, deal-breakers, preferred neighborhoods, and buyer motivation scoring
10 promptsNatural Language Listing Search
Conversational query → MLS parameter extraction (beds, baths, price range, sqft, lot size, property type, features, school district), search result presentation, and "show me more like this" refinement
10 promptsMortgage Calculator Agent
Purchase price + down payment + rate + term → monthly P&I, PMI calculation (if <20% down), property tax estimate, insurance estimate, total PITI, amortization highlights, and refinance scenario comparison
9 promptsNeighborhood Intelligence
School rating lookup (GreatSchools integration prompt), commute time calculation, Walk Score / Transit Score explanation, neighborhood amenity summary, and crime index contextualization
9 promptsShowing Scheduler
Availability capture, agent calendar integration, showing confirmation message, 24-hour reminder, post-showing feedback request, and multi-property tour routing
9 promptsMarket Intelligence & Offer Strategy
Days on market analysis, price reduction history, comparable sales summary, list-to-sale ratio, offer strategy guidance (asking / above / below), and escalation clause explanation
9 promptsWrite a production-ready system prompt for a real estate buyer qualification AI agent for [BROKERAGE NAME]. The agent qualifies buyer leads and schedules showings. Requirements: 1) Role: a real estate concierge — knowledgeable, helpful, never pushy, 2) Qualification flow: collect budget range, pre-approval status, desired neighborhoods, must-have features, timeline to purchase, current living situation (renting/owning), 3) Lead scoring: classify as Hot (pre-approved, 0-3 month timeline), Warm (pre-approval in progress, 3-6 months), or Cold (just browsing, 6+ months), 4) Property matching: based on criteria, suggest 3 listings from the database with brief descriptions, 5) Showing scheduling: offer to schedule showings for interested properties, 6) Agent handoff: for Hot leads, immediately offer to connect with a licensed agent, 7) Prohibited: never quote specific mortgage rates, never guarantee property values, never pressure timeline. Include 3 few-shot examples: hot lead, warm lead, out-of-market inquiry.
You are a real estate AI assistant. Generate a Comparative Market Analysis (CMA) for the following property: Address: [ADDRESS]. Property details: [BEDS/BATHS/SQFT/YEAR BUILT/LOT SIZE]. Using the following comparable sales data: [PASTE COMP DATA]. Analysis: 1) Comp selection rationale: why each comp was selected (proximity, similarity, recency), 2) Adjustments: for each comp, apply adjustments for differences in beds, baths, sqft, condition, lot size, garage, pool (use standard adjustment values for [MARKET]), 3) Adjusted price per sqft: calculate for each comp after adjustments, 4) Value range: low / mid / high estimate with rationale, 5) Recommended list price: specific number with confidence level, 6) Market context: days on market trend, list-to-sale ratio, absorption rate for this price range and neighborhood. Format as a professional CMA report a seller would receive.
Build a conversational property showing scheduler for a real estate AI agent. The agent should: 1) Collect: buyer name, contact info, which property they want to see (by MLS# or address), preferred dates/times (offer 3 slots), 2) Availability check: call GET /api/showings/availability?propertyId=X&agentId=Y to get open slots, 3) Conflict detection: check if the property has an accepted offer or is off-market before scheduling, 4) Confirmation: send confirmation with: property address, showing date/time, agent name and contact, parking instructions, what to bring (ID, pre-approval letter), 5) Reminder: schedule automated reminder 2 hours before showing, 6) Post-showing follow-up: 24 hours after showing, ask for feedback and interest level, 7) Handle cancellations: allow rescheduling up to 2 hours before showing. Write as a TypeScript state machine. Include the database schema for showings and the email templates for confirmation and reminder.
system
19 prompts
prompts
10 prompts
workflow
18 prompts
templates
9 prompts
"The buyer qualification flow — gathering budget, pre-approval, timeline, and must-haves in a natural conversation — is what our top agents do intuitively. Now every lead gets that experience at 2am on a Sunday. Our lead-to-showing conversion went from 12% to 31%."
Broker/Owner
Independent brokerage, 28 agents
"The natural language MLS parameter extraction prompt is the foundation of our AI search product. "3-bedroom with a big yard near good schools under $600k" → structured search parameters in one call. It's the feature that made our search feel like talking to an agent."
VP of Product
PropTech listing portal, 2M monthly visitors
All 56 prompts across 6 modules are unlocked for your account.
Lifetime access