Software and AI for the built environment
We apply AI in real estate across the life of a building: tenders and quality dossiers during construction, tenant requests and rent administration once it is let, and maintenance for decades after. We build the software, agents and integrations, and your housing consultants, site managers and asset managers stay in charge.
Industries in real estate
The work, and where software fits.
The built environment is document-heavy and long-lived. A building starts as a tender and a stack of specifications, gets a quality dossier at completion, and then produces repair requests, inspections, rent changes and energy measures for fifty years or more. The data moves between contractors, owners, managers and tenants, often by email and PDF.
Software fits where those handoffs slow things down. Search and summarisation help estimators and staff find what a contract or specification says, and intake agents and portals make sure repair requests and tenant questions arrive complete. Integrations between ERPs such as Viewpoint, Yardi or King, FMIS platforms such as Planon, and site apps keep one version of the truth about each building.
How we improve real estate.
Tenant and occupant service
Repair intake, tenant questions and portals connected to your ERP, with sensitive conversations handled by people.
Document search over contracts and specifications
Leases, tenders and specifications made searchable with answers linked to the source paragraph.
Quality and inspection evidence
Offline apps for site inspections, snags and condition assessments that feed Wkb dossiers and maintenance plans.
Contract and invoice checks
Subcontractor and supplier invoices compared with framework rates, contract scope and chain liability requirements.
Building and asset data
ERP, FMIS, BIM and sensor data joined into one model per building for planning, energy labels and reporting.
Further reading.
How to build a production RAG chatbot: a practical guide
What it takes to turn a promising RAG experiment into a chatbot people trust: ingestion, hybrid search, citations, permissions and evals.
5 min read
Human-in-the-loop AI agents: design patterns for production
The patterns we use to run AI agents safely in production: approval checkpoints, confidence thresholds, tool permissions, audit trails and fallbacks.
4 min read
How to evaluate RAG: retrieval metrics, faithfulness and golden sets
How to measure a RAG system properly: separate retrieval from answers, check faithfulness claim by claim and build a golden set you can trust.
4 min read
Common questions.
We regularly look at Viewpoint, Tobias AX, Yardi, MRI, King, Syntess, Planon, Ultimo, TOPdesk and Autodesk Construction Cloud. If a system has an API we use it; if it only exports files, we build around that.
Yes. Field apps store inspections, photos and signatures on the device and sync when a connection is available, so work continues in basements, on roofs and on remote sites.
No, though it helps to know where the gaps are. A first project usually includes cleaning the data it depends on, such as the asset register or repair catalogue, and shows what to fix next.
Yes. We build around the systems you have and coordinate with your suppliers on interfaces. You own what we build, including the integration code.