For facility managers
You manage a building that keeps changing: a tenant asks for more meeting rooms, the café wants the unit next door, a floor is added, and the night-cleaning contract comes up for renewal. You need one model of the building that carries each change, its options and its history, and that reopens next year.
What Laydyne does for it
Keep the building as one editable model of every level, with the parts that do not change locked, and open the whole site, each level and its plan.
Read the feature page: Build a 2D plan and a 3D model from a drawing, photos or a briefMake each change with the AI you already use, give the café the adjacent unit, copy the top floor twice and extend the lifts and stairs, with every other part keeping its id.
Read the feature page: Change the model with the AI you already useShow the current layout and the proposal from the same viewpoint with areas and counts side by side, and keep the superseded draft saved.
Read the feature page: Put two layouts in the same view and read the difference in numbersRun the operation on the same model: a café with two or four baristas under the same morning demand, or a night-cleaning crew with and without robot vacuums; runs need Pro.
Read the feature page: Simulate how people, goods and robots move and waitReopen the project in another session with its layouts, comparisons, drawing issues and history intact.
Read the feature page: Keep the project as a file you own, and hand the model on
Open a recorded example
- Open Calder Yards after the café extension and the two added floors, without signing in
- Open the office comparison: layout A and the client’s revision R02, without signing in
- Open the three-storey office prepared for night cleaning
- Seat a whole office floor with your AI: teams on desk islands and a printable seat map
What the published records produced
In the fictional building, the café grows from 106.41 m² to 260.3 m². Six parts are added, two change and 2,418 stay unchanged. Two residential floors are copied with their lifts and stairs. The project reopens with A, B, the superseded C draft and C final. In the separate cleaning study, two cleaners with two robot vacuums finish the last job at 23:40. Two cleaners alone finish at 00:33. Calculated cleaner staff hours are 3.3 and 5.1 respectively. Paid hours and cleaning quality are not established by these results.
- Change, compare and reopen a building
- Calder Yards level 1 drawing, Rev S3 (PDF)
- Calder Yards project with A, B and C (JSON)
- A/B/C design report (HTML)
- Plan a night-cleaning shift: crew size, robot vacuums and finish time
These recorded projects use synthetic inputs. Photos and drawings show what was produced; site accuracy, business effects and photorealistic reconstruction are not established.
What it does not do
- Tasks take the minutes you enter. The model does not measure cleaning quality or coverage per square metre, and it leaves out moved chairs, spills, robot charging, battery ageing and people in the building. Laydyne’s separate one-floor cleaning-robot calculation, which traces reachable floor and coverage, is not used on this page.
- Results come from a simplified, deterministic model: robots are circles moving at constant speed, and the same input always gives the same result. It does not model collisions or avoidance between robots or people (only capacities and queues), crowd physics, optimised lift group control (lift cars follow simple fixed rules), turning, or cleaning quality. Batteries, when a scenario gives them, drain in a straight line and charge at a constant rate. Dimensions read from photos and drawings are assumptions to check against measurements. It is for exploring options, not a calibrated prediction of a real site.
- A seating row or a bench is one part, not its capacity, so the seat figure is a part count, not a headcount; the model records no room type, so meeting rooms and offices are not told apart in the table.
- The working project stays in this browser. The JSON you export is a file you keep yourself: in a folder, in Git or on your own drive. Cloud saving on Pro and Max is a separate, manual action. An MCP link relays tool requests and results through Laydyne’s server and stores them temporarily for delivery; it is not a project backup. WebMCP editing runs inside the tab without the relay. See how your data flows and the privacy policy.
Price
Building and editing the model with your own AI over MCP, route checks, saving in this browser and JSON import and export are free, with no count limit; a free account is needed only to create an MCP link (3 per account). Running simulations, the built-in AI and cloud saving need Pro ($29 a month or $278.40 a year) or Max ($89 a month or $854.40 a year). Prices are in US dollars before tax; your AI provider bills its own usage separately.
Common questions
- Does the building keep its history after a change?
- Reopen the project in another session with its layouts, comparisons, drawing issues and history intact.
- Can I compare the layout before and after?
- Show the current layout and the proposal from the same viewpoint with areas and counts side by side, and keep the superseded draft saved.
- Does it measure cleaning quality?
- Tasks take the minutes you enter. The model does not measure cleaning quality or coverage per square metre, and it leaves out moved chairs, spills, robot charging, battery ageing and people in the building. Laydyne’s separate one-floor cleaning-robot calculation, which traces reachable floor and coverage, is not used on this page.
- Where is my building model kept?
- The working project stays in this browser. The JSON you export is a file you keep yourself: in a folder, in Git or on your own drive. Cloud saving on Pro and Max is a separate, manual action. An MCP link relays tool requests and results through Laydyne’s server and stores them temporarily for delivery; it is not a project backup. WebMCP editing runs inside the tab without the relay. See how your data flows and the privacy policy.