The customer films their own home. Computer vision identifies and counts every object, estimates dismantling, handling and transport time, and returns a priced quote.
The resultA survey that took days of manual assessment now returns a quote in seconds, from a video the customer shoots themselves.
Surveys are slow, phone estimates are wrong, and neither gets at the thing the price actually depends on: the work the move takes.
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.
Try it: put the flat on the fourth floor with no lift, then narrow the doorways. The sofa and the fridge now have to come apart to leave; the carrying time climbs. The volume never changes.
Ground floor, standard doors. Now change the access: the volume will not move; the work will.
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 line says what will be done to what — so the customer can check the quote against their own home.
The walkthrough video is uploaded and sampled into frames, passed through detection and classification, deduplicated into a single inventory, then costed — each object contributing dismantling, handling and transport time before the pricing engine returns a quote.
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.