A survey that took days of manual assessment now returns a quote in seconds, from a video the customer shoots themselves.
Quoting a house move means knowing exactly what is being moved. Traditionally that requires a surveyor to visit, walk every room, and write down the contents by hand — scheduling, travel and a report that lands days later, by which time the customer has often booked someone else.
Estimating from a phone call instead is worse. Customers underestimate what they own, forget the loft, and describe a wardrobe without mentioning it has to come apart to leave the bedroom. The quote is wrong before the van is booked.
And the cost is not in the object count. It is in labour: what has to be dismantled, what needs two people, what will not fit through a door, and how long each of those takes. A list of furniture is not an estimate.
The customer walks through their home filming on an ordinary phone. No appointment, no surveyor, no waiting — the input is something they can produce in ten minutes on the evening they decide to move.
Computer vision detects furniture, appliances and boxes across the walkthrough, classifies each by type and size, and — critically — deduplicates across frames so a sofa filmed from three angles is counted once rather than three times.
Each identified object carries dismantling, handling and reassembly times, adjusted for access — stairs, doorway widths, floor level. The model estimates the work the move actually requires rather than the volume it occupies.
Labour, transport time, vehicle size and distance resolve into a priced quote returned while the customer is still on the site — turning a multi-day sales cycle into a single session.
Every object counted once across the walkthrough, then costed on the work it takes — not the volume it occupies.
Customer-recorded video walkthrough as the survey input, on any ordinary phone.
Object detection and classification across furniture, appliances and packed boxes.
Cross-frame deduplication so each item is counted once across the whole walkthrough.
Per-object dismantling, handling and reassembly time estimation.
Access-aware adjustment for stairs, doorways and floor level.
Volume and vehicle-size calculation from the recovered inventory.
Instant priced quotation, replacing a manual on-site survey.
Itemised breakdown the customer and the operations team can both audit.
On-site surveys replaced by a video the customer records themselves
Quotes returned in seconds rather than days
Estimates built on labour and access, not object count alone
Each item counted once across the full walkthrough
An itemised breakdown both customer and operations can audit
Three modules that read a feasibility study, judge it, and write a new one from scratch
Three modules: one reads a feasibility and fills the whole Excel model, one benchmarks it against world standards and returns a gap analysis, and one generates an entirely new professional feasibility from historical data.
Construction takeoff and bidding from architectural PDFs, in minutes
Reads architectural PDFs, detects the scale on its own, measures only the trade you work in, and returns quantities, labour hours and a bid — then pushes the work into your CRM.
Three role modules — school, teacher and student — with computer-vision proctoring
A multi-tenant platform with three distinct role modules — school administrator, teacher and student — backed by computer-vision proctoring, a randomised question engine and automatic certification on pass. We also produced the entire curriculum that runs inside it.