Approval policy engine
Which parameters need a human, which role, and what happens when the SLA expires.
Standardise autonomy across a factory network
One autonomy policy, one audit standard and one model fleet across brand-owned plants and contract manufacturers in every geography you source from.
What ships with an enterprise agreement
Governance, identity, deployment and support built for a manufacturer with plants on three continents and brand agreements on all of them.
Identity and access
- SAML and OIDC single sign-on
- SCIM user provisioning
- Role-based access down to line and station
- Break-glass access with recorded justification
Governance
- Autonomy policy per plant, line and parameter
- Approval routing by role and SLA
- Spend and compute limits per site
- Immutable audit export to your GRC system
Deployment
- On-premises with zero telemetry egress
- Customer VPC or dedicated region
- Edge fleet management and OTA rollback
- Air-gapped model updates on request
One run standard across every plant
The same graph, the same statuses and the same approval semantics whether the line is in Ho Chi Minh City, León or Porto.
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 |
A multi-site programme
Enterprise deployments run plant by plant with a shared model fleet and a shared policy.
| Phase | Scope | Autonomy | Governance milestone |
|---|---|---|---|
| Q1 | Lighthouse plant, one wedge workflow | Observe → recommend | Autonomy policy ratified |
| Q2 | Lighthouse plant, full loop + twin | Act with approval | Audit export accepted by brand QC |
| Q3 | Two additional plants, wedge workflow | Recommend → act | Fleet model governance in place |
| Q4 | Network rollout, shared model families | Act with approval on bond and last | Quarterly model review cadence live |
Governance features enterprises ask for first
Every one of these exists because a plant, a brand auditor or an IT security team asked for it.
Tenant and brand isolation
A contract manufacturer can run several brands with no cross-brand data or model leakage.
Audit export
Signed, immutable export of every action and approval into your GRC or quality system.
Edge fleet management
Model versions, health and rollback across hundreds of edge units from one console.
Data residency
EU, US or in-country residency, or fully on-prem with no egress at all.
SLAs and support
Availability, response and model-regression SLAs with a named customer solutions engineer.
What enterprise deployments look like
Sized against a network of plants rather than a single line.
- 350k lower bound of enterprise ACV, in US dollars
- 12 plants supported per fleet management console
- 99.95% factory-edge runtime availability target
- 7yr default audit retention for the liability window
Commercial figures are indicative; contractual terms are set per agreement.
Posture and assurances
The controls that make autonomy acceptable to an enterprise risk committee.
Certifications and posture
- In progress SOC 2 Type II — audit window open [ASPIRATIONAL]
- In progress ISO 27001 — controls implemented, certification pending [ASPIRATIONAL]
- Supported GDPR — EU data residency and DPA available
- Supported Per-tenant isolation for patterns, lasts and construction IP
- Supported On-premises deployment with zero telemetry egress
Agent-specific assurances
- Graduated autonomy: observe → recommend → act-with-approval → act, set per agent and per parameter
- Human-in-the-loop approval gates on every validated bonding, lasting and moulding parameter
- Immutable, quality-grade audit log of every agent action, approval and setpoint write
- Guardrails and schema validation on tool calls; fail-closed to last known-good recipe
- Sandboxed factory-edge runtime with signed model artefacts and version rollback
- Scoped permissions per line, per station and per operator role
What your teams will need from us
The documents and evidence enterprise buyers request during diligence.
Security and risk
- Security whitepaper and architecture diagrams
- Penetration-test summary [ASPIRATIONAL]
- SOC 2 report when the audit window closes [ASPIRATIONAL]
- Subprocessor list and DPA
Quality and legal
- Model validation and evaluation methodology
- Audit-log schema and retention policy
- IP protection commitments for patterns and lasts
- Standard MSA, SLA and support matrix
Enterprise perspectives
Illustrative scenarios from multi-site design-partner conversations.
“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.
Fits your enterprise landscape
ERP, PLM, MES and historian integration is table stakes for a network rollout.
Cutting and nesting
- Atom cutting tables
- Comelz CZ series
- Zünd G3
- Lectra Versalis
- Generic CNC / G-code
Stitching and lasting
- Programmable stitchers
- Lasting machine PLCs
- Toe / side / heel lasters
- Conveyor MES signals
- Barcode and RFID pair tracking
Moulding and bonding
- Compression press controllers
- PU / EVA injection lines
- Primer and cement stations
- Activation ovens
- Press pressure and cure sensors
Plant systems
- SAP and Oracle ERP
- PLM (Centric, PTC)
- MES / MOM systems
- OPC UA, MQTT, Modbus TCP
- Historian (PI, Ignition)
Connectors ship as versioned adapters. Anything not listed is reachable through OPC UA, MQTT, Modbus TCP or the Footeon REST/gRPC API.
Enterprise questions
-
Only if you choose. Inference runs on factory-edge servers, and Enterprise deployments can run fully on-premises or in your VPC with no telemetry egress. Brand IP — patterns, lasts, construction specs — is tenant-isolated and never used to train models for another customer.
-
It stops and asks. Every agent runs at a configured autonomy level: observe, recommend, act-with-approval, or act. Bonding, lasting and any parameter under a brand or safety validation defaults to act-with-approval, and every approval is written to an immutable audit log with the sensor evidence that triggered it.
-
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.
-
Line at $8,000 per line per month for one workflow, Factory at $55,000 per month for the whole loop, and Enterprise from $350k to $4M ACV for multi-site networks with custom material, last and bond models. Outcome-based components are available on leather waste, rework and returns.
Standardise on Footeon
Bring your network map and your worst quality line. We will scope a lighthouse plant and a fleet plan.