AI-powered marketplace for U.S. commercial real estate
A modern map-first platform for searching, shortlisting, and inquiring on office space and business centers across the United States.
About the Project
The platform helps prospective tenants and buyers find and screen office space and business centers across the United States. The product covers the full journey: search → shortlist → property evaluation → inquiry. The main working screen pairs a map with a card listing, so location and core property metrics stay visible side by side. The product funnel is built around four stages: filter-driven screening, shortlist for return-and-compare, property page as the decision point, and a request flow as a clean handoff into broker contact. An AI ranking layer assists during selection — narrowing options based on user behavior and stated criteria, with short explanations that keep the final decision transparent.
About Customer
Alan is a young founder with a software engineering background and a family business in U.S. commercial real estate. He understands the criteria buyers and tenants use to evaluate office space, why decisions stall, and where users drop off before ever reaching out to a broker.
Trustworthy AI suggestions
Embed AI as a practical screening assistant users can rely on, not an opaque system.
Pre-request drop-off
Remove the conversion gap before "Submit inquiry," where users stalled because metrics were unclear and they doubted the choice.
Readable metrics
Make the key parameters work as a one-glance answer for compare-and-decide.
Filtering without overload
Keep filters concise to avoid overwhelming users with options or accidentally exclude relevant listings.
Shortlist as a real workflow
Tet users collect, return, compare, prepare for discussion, and convert to inquiry.
Iteration-ready foundation
The platform must allow changes to selection logic, metrics, and fields without a rebuild.
Proposed Solution
We built a modular architecture: a Next.js frontend as a fast client surface for the map, filters, cards, shortlist, and request form; a custom backend on Directus with a separate Node.js API layer for search, property details, shortlist, and inquiries. PostgreSQL is used as the data core, with metrics stored as normalized fields so filtering, sorting, and aggregation stay fast and predictable.
Next.js as the product shell
We built the frontend as a Next.js application split into UI components and service modules — map, listing, filters, shortlist, property page, request form. We designed the search state as controlled and shareable: filter parameters, sort order, map viewport, and selected property all sync into the URL so users can navigate back, share a view, or refresh without losing progress.
Directus + Node.js
We chose Directus as the managed backend core for collections, roles, access rights, editorial and operational workflows, and the admin panel. On top of Directus, we added a Node.js API layer for dedicated search endpoints, metric aggregation, shortlist handling, request creation, and integrations (notifications, maps, AI). This split responsibilities cleanly: Directus handles data and administration; Node.js handles product logic and integration flows.
PostgreSQL schema
We designed the data model around metrics as first-class structured fields, enabling fast filter/sort/compare/aggregate. We also built in flexibility — adding new metrics and selection rules should not break cards, filters, or the property page.
AI as a ranking service
We integrated AI as a separate service that receives a base candidate list and returns a ranked result with short relevance explanations. The principle: AI stays a secondary assistant that narrows options faster, while the decision remains transparent through visible metrics and explanations.
Map–listing synchronization
We built the Maps API integration so the map and list operate in lockstep — selecting a marker highlights its card, hovering or clicking a card highlights the marker, and viewport changes preserving the active selection. This is critical for commercial real estate, where location is a primary decision factor.
Request workflow and notifications
We implemented the request as a full record with context: selected property, shortlist, key metrics, active filters, and user comment captured at the moment of submission. This reduces context loss between the interface and the next step in sales operations (broker contact, qualification, tour). Notifications are connected through a dedicated provider and adapter so each request reaches the right role immediately.
Alan brought listing examples, screenshots, comparison spreadsheets, typical metric sets, and a sketch of how users move between map, cards, and notes. We mapped the journey into repeatable steps — quick screening, several returns to candidate properties, shortlist build-up, and only then contact — and defined the core MVP decision: the minimum metric set that must always be visible.
+2 Resource
Results
Pilot-ready MVP delivered
live AI-assisted marketplace with a managed admin layer and a stable technical foundation, ready to put in front of partners and early clients within ~3 months from kickoff
Faster property screening inside the interface
key metrics surfaced on cards and property pages, supporting ~2× faster shortlist creation vs. the founder's original spreadsheet workflow
AI-assisted search
ranking and short explanations help users identify relevant options faster and understand the recommendation logic
Shortlist as a path to contact
saved properties become a working selection process: users return, compare, and convert into an inquiry rather than abandoning
Higher-quality leads
every request preserves selection context (property, shortlist, filters, key metrics), so the broker team receives concrete inquiries and can move users to the next step faster
Faster and more cost-efficient iteration cycles
Directus lets the operations team update content and reference data without engineering involvement; the modular architecture absorbs new metrics, selection rules, and integrations without rewrites
Get in Touch
Or send us a message and we'll get back to you within 15 minutes during business hours