factory

Factory

Describe a factory in one line. Claude builds it as a live 3D simulation you can run.

The page is a model factory on a table, seen through a tilt-shift lens: a cut-away hall with the line inside, machines that move while they work, product flowing on conveyors, people, forklifts, a truck yard. Under it runs a discrete event simulation. Every number on screen comes from that simulation, never from a script: the throughput, the utilization bars, the WIP, the pulsing red outline around the bottleneck. When someone adds a machine at the bottleneck, the simulation gets one more server, the conveyor in front of it drains, and the outline moves to the next constraint.

The one rule that matters

The simulation is the explanation, so it has to be true.

• Cycle times, batch sizes, dwell times, breakdown rates and yields come from how the real process works. Use the numbers a process engineer would recognise and say in note where they come from ("18 min at 180 C", "51 slots, 3 needle head"). When you have to estimate, say "typical".
• Machine counts come from the sizing rule, which the page prints in the inspector: machines = CEIL(rate_in x cycle / (batch x availability x target utilization)).
• Throughput, utilization and the bottleneck come out of the simulation. Never tune inputs to make a nicer result. If the first line misses its target, that is the finding: report it, show it, and let the user fix it with the slider.

Workflow

Run date at the start. A factory takes 10 to 25 minutes.

1. Read the line. Pull out the product, the volume and the time unit. Fill in what is missing with stated assumptions: shifts (2 x 8 h unless the process runs around the clock, like cells, chemicals or glass), the product variant ("250 W rear hub motor"), the scope ("the canning hall, from bright tanks to pallets"). Say them in one short paragraph before building.
2. Route. Write the real process route as 6 to 10 stations, in flow order, with branches where sub-assemblies are made in parallel and joined (stator + rotor + housing into motor assembly). Each station: what happens, the machine that does it, the cycle time per unit or per batch, the batch, MTBF/MTTR if it is a machine that breaks, yield if it is a test or inspection. references/process.md has typical numbers for common processes and how to pick them.
3. Pick the token. One token is one unit unless the line is fast. Choose perToken so one token leaves the line every 5 s to 2 h (a tray of 40 croissants, a case of 24 cans, a tray of 96 cells).
4. Write spec.js (schema below). Start from the closest example in examples/.
5. Check it headless. node scripts/check.mjs spec.js. It sizes the line and runs 5 production days of the same engine the page runs, and prints per station: machines, capacity per day, busy, down, blocked, starved, failures; then the forecast and the bottleneck. Read it like an engineer:
   • Does each machine count look like a real plant? 446 proofer slots is right (4 chambers of 120); 40 laminators is a wrong cycle time.
   • Is the bottleneck plausible? Long dwell steps and machines with poor availability usually are.
   • Fix mistakes in the inputs (a wrong unit, a batch you forgot). Do not fix the result.
6. Build. node scripts/build.mjs spec.js <out>.html writes one file of about 1 MB with three.js, the runtime and the spec inlined. It opens from disk with no server and no network.
7. Look at it. node scripts/capture.mjs <out>.html shot.png --query "assemble=0" (needs Playwright) and read the PNG. The line should fill the frame, every station should have its machines, product should be on the conveyors, the HUD should show a throughput. Zero console errors.
8. Answer with the file path, the forecast against the target, the bottleneck and why, the sizing of the bottleneck station, and one what-if to try ("add a third winder: the forecast goes from 1,943 to 2,0xx a day and the constraint moves to EOL test"). Run that what-if through check.mjs (edit servers on a copy) before you quote it.

Spec

FactorySkill.define({
  id: 'ebike-motors',                        // file name
  prompt: 'a line that makes 2,000 e-bike motors a day',  // the user's line, typed into the page
  title: 'E-bike hub motor line',
  product: { name: 'motor', unit: 'motors', perToken: 1 },
  demand: { perDay: 2000 },                  // or perHour, or perWeek (5 days)
  calendar: { shifts: 2, hoursPerShift: 8, startHour: 6 },
  sizing: { targetUtil: 0.85 },              // planned utilization for the sizing rule
  release: 'capacity',                       // 'capacity': raw material always there (find the max), 'takt': released at demand
  seed: 11,
  stations: [
    { id: 'stamp', name: 'Lamination press', machine: 'press', ct: 22, cv: 0.04, buffer: 8,
      mtbf: 6 * 3600, mttr: 25 * 60, input: 'coil', stage: 'stack', note: '64 laminations at 180 strokes/min' },
    { id: 'wind', name: 'Needle winding', machine: 'winder', ct: 150, after: ['stamp'], stage: 'wound' },
    ...
  ],
  stages: { coil: { shape: 'coil', color: '#8d949b' }, stack: { shape: 'ring', color: '#6f7780' }, ... },
})

Station fields:

field	meaning
id, name	key and the name on the plate and in the HUD
machine	a kit machine (table below) or an alias such as lathe, proofer, pasteurizer, seamer
ct	seconds per cycle per machine; with batch it is the time for the whole batch
cv	coefficient of variation of the cycle (lognormal). Automatic 0.02 to 0.06, manual 0.1 to 0.2
batch	units taken and released together (a chamber oven, a mixer, a TVAC)
perMachine	units one physical machine holds at once in continuous flow (tunnel oven, spiral, proofer, formation rack). The DES gets that many servers per machine with ct = dwell time
servers	'auto' (default, sizing rule) or a number of machines (times perMachine)
buffer	capacity of the input buffer (each input of a join has its own)
mtbf, mttr	mean busy seconds between failures and mean repair seconds (exponential)
yield	fraction good; the rest is scrapped at this station
after	predecessor ids. Default: the previous station. A station with input starts a new branch
input	the raw material stage a branch starts from
stage	the product stage this station outputs (looks up stages)
note	where the numbers come from, shown in the inspector
variant, color, accent, length, radius, height, fill, web, glow	looks
operators, reserve, at: [col, row, dir]	people beside machines, spare floor slots, manual grid placement

The model is a tree into one last station (the sink): every station feeds exactly one next station.

Kit

Machines (real scale, metres) in runtime/kit.js:

machine	looks like	kind
cnc	machining centre, window, moving spindle, chip conveyor	side
press	press with ram and flywheel, coil feeder; variant: 'magnetizer'	side
winder	needle winder, spinning table, wire spools	side
robot	fenced 6 axis arm cell; variant: 'weld' adds arc and sparks	side
bench	assembly bench with an operator, bins, tool balancer	side
tester	test rack with screens and a clamp fixture	side
oven	chamber oven with racks (batch); variant: 'proofer'	side
mixer	spiral or planetary mixer with turning bowl	side
filler	rotary filler / seamer in a glass enclosure	side
formation	racks with blinking channels (formation, ageing, burn-in)	side
tank	stainless tank with agitator, ladder, piping	side
laser	laser cell with glowing window	side
turntable	calibration turntable with camera tripods	side
cage	flight / function test cage; the unit lifts while tested	side
bay	integration bay with gantry crane and technicians; variant: 'cleanroom'	side
chamber	thermal vacuum / autoclave vessel with a round door (batch)	side
kitting	shelving with bins and a picker	side
stacker	high speed stacking / winding head	side
cell	generic enclosed process cell (anything else)	side
tunnel	tunnel oven, dryer; `variant: 'pasteurizer'	'washer'`
spiral	spiral cooler / freezer / proofer tower	inline
rollers	sheeter, laminator, `variant: 'calender'	'slitter'`
coater	roll to roll coater with drying oven	inline
smt	printer + pick and place + reflow	inline
vision	inspection arch over a belt	inline
packer	case packer / flow wrapper	inline

Product shapes for stages: ring wound rotor hub disc coil box crate tote croissant tray dough sheet can sixpack bottle cell pouch roll module pack pcb frame drone satellite bus sneaker bag puck. Each takes color and scale; tray takes item: 'croissant' | 'dough'.

A process with no fitting machine: use cell with a glow colour, or define one in the spec file before define (guarded, so check.mjs can run the file without a browser):

if (FactorySkill.Kit) FactorySkill.Kit.def('kiln', (o) => {
  const K = FactorySkill.Kit, { g, M, body, acc } = K.sideBase(o, 3, 2.4)
  K.box(g, 3, 2.2, 2.2, body, 0, 0, 0)                 // K.box(parent, w, h, d, material, x, yBottom, z)
  const door = K.live(K.group(g, 0, 0, -1.1))          // parts that move live in K.live groups
  K.box(door, 1.4, 1.6, 0.08, acc, 0, 0.3, 0)
  return K.finish({ g, kind: 'side', w: 3, d: 2.4, h: 2.4, entry: K.V(0, 0.9, -1.3),
    work: K.workFixed(0, 0.9, 0), anim(s) { door.position.y = s.state === 'busy' ? 0 : 1.4 } }, o, [1.2, 2.2, -0.9])
})

references/kit.md has the whole API (materials, parts, people, vehicles, work(i, p) for units that move through a machine).

The page

• Opens on the assembled factory, already 3 production hours in (more for slow lines) so buffers hold WIP. ?intro=1 types the prompt and assembles the factory station by station first.
• HUD: throughput per day over the last 4 h against the target, a sparkline per production hour, takt, WIP, lead time, the bottleneck card, one bar per station split into busy, blocked, starved and down. The bottleneck station gets a pulsing red outline on the floor; nothing else is labelled.
• Click a station (or its row) for the inspector: machines with minus and plus (spare floor is reserved), cycle time and buffer sliders, the sizing formula with its numbers, MTBF/MTTR, failures, scrap, and a 3 day forecast of the changed line from the same engine.
• Speed buttons scale production time; the clock shows day, time and shift.
• ?film=1 stops the clock: window.__film.step(dt) renders one frame. window.factory exposes select(id), setMachines(id, n), setCT(id, s), setBuffer(id, n), camTo({az, el, dist, target}, s), stationCenter(id), forecast(), sim, world.
• Other URL options: speed, seed, release=takt, select=<id>, ui=0, assemble=0, ao=0.

Look

Tilt-shift miniature photography, not a CAD view: warm sun with soft shadows, ambient occlusion, a narrow band of focus with heavy blur above and below, saturated warm grade, vignette, grain. The factory sits on a diorama base on a table: cut-away hall (back and left walls full height, front and right cut low with the section face coloured), racking along the back wall, clutter on free floor, truck yard, parking, trees, a sign. Machines are cream with one accent colour per station. references/look.md explains each choice and what to keep when you extend it.

Verify like a critic

• check.mjs numbers match the HUD after a few hours (the HUD window is 4 h, so it is noisier).
• Every station shows its machines; nothing floats; tokens sit on belts or in machines.
• At the bottleneck the input buffer is full and machines upstream show amber (blocked); downstream rows show grey (starved). If not, the bottleneck is downtime driven: say so.
• Add a machine at the bottleneck in the page: the forecast line updates and the outline moves within about an hour of production time.

Files

path	what
runtime/des.js	the simulation engine and the sizing rule (pure, runs in Node and the browser)
runtime/kit.js	machines, products, people, vehicles
runtime/world.js	layout, hall, conveyors, token placement from simulation state
runtime/look.js	renderer, light, AO, bloom, tilt-shift, grade
runtime/app.js, runtime/hud.css	page, HUD, inspector, film hooks
vendor/three.bundle.js	three.js r185 and the addons used (MIT)
scripts/check.mjs, scripts/build.mjs, scripts/capture.mjs	headless run, build, screenshot
examples/*/spec.js	six factories made with this skill, each with its built page