Three lines, three numbers that moved
Each study follows the same structure: the baseline, the wedge workflow, the run, the approval behaviour and the measured result.
Leather yield from 79.1% to 87.4%
A 6,000-pair-a-day leather casual plant where scrap was the largest single cost and the two best pattern cutters were within three years of retirement.
Footeon deployed Cut & Nest on one leather line. Two weeks of baseline established yield per hide rather than per batch, which immediately revealed that scrap varied more by hide supplier than by cutter. Defect-aware nesting then solved layouts against the actual scanned hide, placing forgiving parts over marginal leather.
- Nest solve time fell from 41 manual minutes to 12.3 seconds
- Scrap fell from 20.9% to 12.6%
- Supplier scorecards renegotiated two hide contracts
- Zero out-of-tolerance parts across the pilot lot
Result
| Measure | Before | After |
|---|---|---|
| Leather yield | 79.1% | 87.4% |
| Scrap | 20.9% | 12.6% |
| Nest solve | 41 min | 12.3 s |
| Cutting rework | 2.4% | 0.3% |
- 10:31:07 bond.check_window(primer="PR-9", adhesive="AD-22", rh=0.71)
- 10:31:09 RH 71% pushes primer flash-off outside validated window
- 10:31:10 approval.request(param="activation_temp", from=64, to=66, reason="humidity drift")
- 10:34:14 approved by t.nguyen@[PLACEHOLDER] · change logged to audit trail A-88213
- 10:52:40 quality.inspect(scope="bond_line,fit,cosmetic", pairs=1200)
- 10:58:27 first-pass yield 98.2% · 21 rework (squeeze-out) · 0 bond-gap escapes
Delamination returns down 71%
A 22,000-pair-a-day athletic plant whose warranty analysis traced most claims to edge delamination on cemented construction during humid months.
Last & Bond was deployed with bond-line vision on every pair and act-with-approval autonomy on activation temperature, press pressure and cure. The agent recalculated the process window per adhesive lot and per shift, and paused for the quality engineer whenever it needed to move a validated parameter — which happened 34 times in the first quarter, each with sensor evidence attached.
- Bond-gap escapes to the brand QC gate fell to zero in the pilot lot
- Process window held in 96% of shifts, up from 71%
- 34 approval requests, median approval time 4 minutes
- Warranty reserve released after two quarters of sustained results
Changeover time cut 46% across four brands
A 38,000-pair-a-day contract manufacturer running 40 model changeovers a month for four different brands, each with its own specs and quality agreement.
Yield & Energy and the shoe-and-line twin were deployed first. Every changeover is now simulated before the line stops: the nest, the mould recipe, the lasting profile and the bond window are solved in the twin, and the changeover sequence itself is optimised against mould and last availability.
- Changeover time down 46% on average across four brands
- Per-brand tenant isolation satisfied all four quality agreements
- Energy per pair down 18% through press and oven scheduling
- First-good-pair time down from 90 minutes to 34
Changeover, before and after
- manual changeover · 3h 40m average
- twin-simulated changeover · 1h 58m average
- first good pair · 90 min → 34 min
- scrap during ramp · 640 → 180 pairs
- status · SUCCEEDED
Every study runs the same graph
The wedge differs; the loop does not. Each case study started at one node and expanded outward.
View as table
| # | Node | Agent | Depends on | Status |
|---|---|---|---|---|
| 01 | Twin simulate | Yield-and-Energy | — | SUCCEEDED |
| 02 | Cut and nest | Cut-and-Nest | Twin simulate | SUCCEEDED |
| 03 | Stitch upper | Stitch-and-Upper | Cut and nest | SUCCEEDED |
| 04 | Mould sole | Mold-and-Sole | Stitch upper | SUCCEEDED |
| 05 | Last upper | Last-and-Bond | Mould sole | SUCCEEDED |
| 06 | Bond sole | Last-and-Bond | Last upper | APPROVAL |
| 07 | Inspect pair | Quality-and-Fit | Bond sole | SUCCEEDED |
| 08 | Finish and pack | Robot-and-Assembly | Inspect pair | SUCCEEDED |
Across the three studies
Aggregate movement against each plant’s own baseline.
- +8.3 points of leather yield on defect-aware nesting
- −71% delamination-driven returns after bond-window control
- 98.2% first-pass yield across inspected pairs
- −46% changeover time between models and colourways
Scenarios are illustrative and modelled on design-partner pilots and published footwear benchmarks. [PLACEHOLDER] pending customer-approved publication.
The run behind the numbers
RUN-4417 is the representative shift used across these studies.
-
01 twin.simulate_run SUCCEEDED 2m 40s
Simulated the whole lot in the shoe-and-line twin before a single hide was cut — nest layout, mould recipe and bonding process window for EVA midsole and rubber outsole at 71% relative humidity.
inputs · outputs
in: pattern velo-trainer-2, hide batch LH-2291, mould set M-14 · out: nest v7, recipe R-08, bond window 62–68 °C
-
02 cut.nest_optimize SUCCEEDED 4m 12s
Scanned 64 hides, marked 1,842 scars and brand marks, then solved a defect-aware nest across the EU 36–46 size curve. Leather yield came in at 87.4% against a 79.1% plant baseline.
inputs · outputs
in: 64 hides, 1,842 defects · out: yield 87.4%, 12.3 s solve, 22 nested part groups
-
03 stitch.tension_control SUCCEEDED 11m 08s
Held stitch tension inside ±4% across 14 stitching stations, caught three skipped stitches on the lateral overlay and re-ran those uppers before they reached lasting.
inputs · outputs
in: seam map v3, thread lot TL-77 · out: 3 skips corrected, 0 escapes
-
04 mold.density_control SUCCEEDED 9m 51s
Trimmed press temperature and dwell on P-3 as the EVA lot ran slightly high in blowing agent, holding midsole density at 0.24 g/cm³ within ±1.8% and cure at 214 seconds.
inputs · outputs
in: EVA lot EV-1180, recipe R-08 · out: density 0.24 g/cm³, cure 214 s
-
05 last.fit_control SUCCEEDED 6m 33s
Lasted the upper over last set L-42 under a heat and tension profile tuned to this leather lot. Toe-lasting deviation held at 0.6 mm; heel seat measured true on every pair sampled.
inputs · outputs
in: last set L-42, 78 °C, profile T-2 · out: deviation 0.6 mm
-
06 bond.window_control APPROVAL 3m 04s
Humidity climbed to 71% mid-shift, pushing the primer flash-off outside the validated window. The agent proposed +2 °C activation and +0.3 bar press pressure, and paused for the quality engineer to approve — the change touches a validated bonding parameter.
inputs · outputs
in: primer PR-9, adhesive AD-22, RH 71% · out: proposed activation 66 °C, awaiting sign-off
-
07 quality.inspect SUCCEEDED 5m 47s
Bond-line vision, 3D fit metrology and cosmetic scan on every pair. First-pass yield 98.2%; 21 pairs routed to rework for adhesive squeeze-out, none for bond gaps.
inputs · outputs
in: 1,200 pairs · out: FPY 98.2%, 21 rework, 0 bond-gap escapes
-
08 robot.finish_pack SUCCEEDED 18m 22s
Robotic cleaning, lacing, insole insertion and carton packing to spec C-4, with per-pair traceability written back to the MES and the brand’s quality portal.
inputs · outputs
in: carton spec C-4 · out: 1,179 pairs packed, 21 held
Read the run
One step paused for a human. That single approval is why the bond result held through a humid quarter.
- SUCCEEDED
- APPROVAL
How results are measured
A case study is only useful if the baseline is honest.
Baseline
- Two weeks of sensing before any writes
- Yield measured per hide, not per batch
- Defects measured on 100% of pairs, not samples
- Changeover timed from last good pair to first good pair
Attribution
- A/B by line or by shift wherever the plant allows
- Material-lot effects controlled for
- Results reported over at least twelve weeks
- Customer countersigns the published numbers
The people behind these studies
Each quote comes from the study above it.
“The nesting agent found yield our best pattern cutter could not — and then explained the layout hide by hide. We stopped arguing about scrap and started managing it.”
Leather yield 79.1% → 87.4%
“Bonding is where our warranty costs live. Having an agent watch humidity, primer flash-off and press pressure on every pair — and stop for a human when it wants to move a validated parameter — is the first thing that has actually moved delamination.”
Delamination returns −71%
“We run 40 model changeovers a month. Simulating the nest, the mould recipe and the bond window in the twin before the line starts took hours out of every launch.”
Changeover time −46%
Design-partner scenarios are illustrative and modelled on public footwear-manufacturing benchmarks — named references are [PLACEHOLDER] pending customer approval.
Questions about these results
-
A typical wedge deployment on one line runs six to ten weeks: two weeks of sensing and baseline capture, three to five weeks of shadow-mode model tuning against your material lots, then graduated autonomy. Whole-factory rollouts follow line by line.
-
Yes — and they are exactly where bond control earns its keep. Recycled EVA, bio-TPU and mono-material uppers shift adhesion behaviour and process windows; the twin simulates the new window and the bond agent holds it as lot chemistry drifts.
-
No. Footeon is a software and factory-edge autonomy layer that sits on top of the machines you already run. We connect over OPC UA, MQTT, Modbus TCP and vendor SDKs, read sensors and vision, and write setpoints back through the controls you already trust — with approval gates on any validated parameter.
-
Agents are bounded by guardrails and schema validation, they cite the datasheet or spec clause behind a decision, and they fail closed to the last known-good recipe. Continuous evaluation against golden datasets gates every model and prompt change in CI before it reaches a plant.
Get your own baseline
Two weeks of sensing produces the same numbers for your plant, at no cost and with no writes to your machines.