Multi-site deployment
One control plane across plants, with per-site isolation, per-site envelopes and group-level rollout control for models and policies.
Enterprise
For extruders and aluminium groups running multiple plants, Extruon becomes the system of action: one autonomy standard, one quality audit trail, one set of models that improve everywhere as each site learns.
Land $600k–$7M ACV · Multi-year agreements with usage ramps · On-prem option available.
Built for groups running 3 to 40 presses
Design-partner names are illustrative pending public reference approval. [PLACEHOLDER]
What enterprise adds
One control plane across plants, with per-site isolation, per-site envelopes and group-level rollout control for models and policies.
Models fine-tuned to your alloy portfolio, die families, profile catalogue and temper targets rather than a generic baseline.
Fleet management for edge runtimes: versioning, staged OTA rollout, health monitoring and safe rollback across every press.
99.9% uptime target with graceful degradation, defined escalation paths and named support engineers who know your lines.
Recovery, defect, die-trial and energy benchmarks across your own sites — the internal league table that drives standardisation.
Group-level policy on which setpoints are writable, which sites may run bounded autonomy and who signs each envelope widening.
Rollout
Enterprise rollouts fail when they start big. Ours start on a single wedge workflow with an audited baseline and expand only on proven numbers.
01Baseline
We baseline recovery, reject rate, die trials, scrap, butt loss and kWh per tonne across your presses so every later claim has something to be measured against.
02Wedge
Deploy the highest-ROI module on the highest-pain press. Shadow, then assist, then bounded autonomy, gated on measured accuracy.
03Prove
The pilot ends with an audited delta against the baseline, not a demo. That number becomes the business case for the next expansion.
04Expand
Add presses on the proven module, then adjacent modules on the proven press, then the second site. Expansion is the growth engine — target NRR 135%.
05Standardise
One autonomy standard, one audit trail, one model fleet. Site-level craft is captured once and raises the floor everywhere.
Commercials
| Element | Structure | Why |
|---|---|---|
| Base platform | Multi-site subscription, land $600k–$7M ACV | Predictable spend for the group; scales with presses and modules |
| Annual prepay | ~15–20% discount | Improves cash and retention on both sides |
| Multi-year | Term agreements with usage ramps | Ramps match deployment reality rather than optimistic day-one usage |
| Outcome component | Tied to recovery, scrap, energy or throughput | The highest-value workflows are priced on the value they create |
| Discount policy | Floor protected; discounts traded for term and case studies | Price integrity across the group and the market |
Assurance-grade by default
Extruon never asks for control it has not earned. Shadow mode proves accuracy against your operators and gauges; advisory mode proves ROI; bounded autonomy only follows once the gates are met.
Data, models, retrieval indexes and memory are scoped per tenant and per entity. On-prem deployment is available for sensitive producers.
Die designs, customer drawings and recipes never leave your boundary. Fleet learning shares defect signatures and process priors, never geometry.
Every perception, recommendation, approval and setpoint write is recorded with its evidence, ready for quality and customer audits.
SSO and role-based access, encryption in transit and at rest, SOC 2 programme in progress, and fail-safe interlocks on every write path.
One standard
Group standardisation is not a policy document. It is the same perception stack, the same envelopes and the same audit trail on every press, with local models tuned to local dies.
Fleet learning raises the floor: a defect signature learned in one plant protects the others.
Enterprise readiness
SAML/OIDC single sign-on with role-based access down to setpoint-write permission per press.
Per-tenant data and model scoping, on-prem option for sensitive producers, and defined data-residency boundaries.
Immutable log of every perception, recommendation, approval and write, exportable for customer and regulatory audits.
Idempotent agent steps, graceful degradation and fail-safe press, quench, saw and robot stop behaviour.
OpenTelemetry tracing, twin and evaluation gating in CI, runtime guardrails and per-model observability.
EN 755 and ASTM B221 profile, alloy and temper traceability, surface and anodising quality records, SOC 2 programme in progress.
Measured on the press
Every Extruon engagement starts with a baseline and ends with an audited delta. These are the target bands we underwrite in a paid pilot.
+4.2 pts
Press recovery uplift, saleable vs charged metal
−38%
Surface-defect and dimensional rejects
−61%
Die-trial pushes before a die is signed off
−12%
kWh per tonne across heating, quench and aging
Target outcome bands modelled from design-partner baselines. [ASPIRATIONAL — to be replaced with audited pilot results.]
Group perspective
Our best plant and our worst plant ran the same alloys on similar presses with six recovery points between them. Nobody could explain it. Now we can.
The audit trail was what got it through our automotive customer's quality review. Per-rack traceability was non-negotiable for them.
We wanted one standard across eleven presses, not eleven pilots. The fleet control plane is the reason this was buyable.
Design-partner quotes are illustrative of the target outcome. [PLACEHOLDER — to be replaced with named references at GA.]
Seven agents, one orchestrator
Each agent owns a physical stage of the line, senses it directly, and acts inside an approved envelope. A plant orchestrator arbitrates between them so nobody optimises recovery at the expense of temper.
Controls billet temperature taper, ram speed, breakthrough pressure, container and die temperature, and exit temperature to keep metal flow balanced and the profile on dimension.
Senses and predicts cross-section dimensions, wall thickness, straightness and surface defects — die lines, pickup, scoring, blisters — from fused vision and laser gauge.
Optimises die temperature, correction and flow balance to cut die trials and the twist and bow that send profiles back to the stretcher.
Controls press-quench cooling rate and stretch-straightening so temper and flatness land inside spec on the first pass.
Controls cut-to-length, batching and aging ovens to reach T5 and T6 mechanical properties without over-soaking the oven.
Drives robotic pulling, stacking, racking and packing of long, hot, delicate profiles — the handling nobody wants to staff at 3am.
Optimises press recovery, scrap, butt and offcut loss, and energy per tonne across the whole line rather than one station at a time.
Answers metallurgy and die-design questions with citations into your die books, profile drawings, press recipes and alloy specs.
Simulates billet heating, metal flow through the die, quench and profile properties — hitting the target profile and yield before the push, not after the scrap.
Enterprise
Bring us your fleet baseline and we will propose the wedge, the rollout sequence and the audited metric each stage is judged on.
Land on one press. Expand press by press, module by module, site by site.