Multi-sensor fusion
RGB, depth, hyperspectral, X-ray, scale, line-speed and robot-pose streams synchronised with deterministic timing.
Features
Everything the loop needs. Nothing it does not.
Slicium ships the capabilities a protein plant actually runs on — and refuses the ones that only look good in a demo.
Perception
See the carcass, not the frame.
Anatomy segmentation
Bone, seam, muscle, fat and defect segmentation per species, robust to condensation, occlusion and lighting drift.
Confidence bounds
Every prediction carries calibrated uncertainty, which drives escalation and autonomy gating.
Control
Act on the process, not on a report.
Adaptive cut control
Cut path, blade force, approach angle and seam-following updated per carcass inside the cell’s motion envelope.
Giveaway control
Predictive weight and batch composition that hold target weight instead of overshooting it.
Robotic handling
Grasp and place planning for deformable, wet product, sanitation-cycle aware and washdown rated.
Deterministic reject
Independent, fail-safe reject and line-stop paths that do not depend on the cloud or the model server.
Program management
Versioned cut programs and specs with staged rollout across sister lines and sites.
Line balancing
Sequence, route rework and manage flow so the constraint sits where the plan wants it.
Twin & simulation
Test on pixels before you test on product.
Simulate the cut, then make it
The protein twin renders carcass anatomy and cell kinematics so a new spec, a new species mix or a new program can be evaluated against thousands of virtual carcasses before it touches a real one.
- Synthetic rare-event generation for bone chips, metal, plastic, bruising and condensation
- Predicted yield with confidence bounds
- Cut-sequence optimisation
- CI gating on twin validation
Learning that compounds across plants
Supervised corrections from every site improve the shared model family without exposing plant recipes, supplier data or tenant images. Rare anatomy learned once protects every line running that species.
- Federated fleet learning
- Physics-informed cut-response models
- Closed-loop control corpus
- Per-tenant isolation guarantees
Feature matrix
What is included at each tier.
| Capability | Line | Plant | Enterprise |
|---|---|---|---|
| One workflow agent | Included | Included | Included |
| Full six-agent loop | — | Included | Included |
| Protein twin | — | Included | Included |
| Custom species & cut models | — | Add-on | Included |
| Multi-site fleet management | — | — | Included |
| On-prem / air-gapped | Optional | Optional | Included |
| Assurance audit trail | Included | Included | Included |
| Named SLA and support | Standard | Priority | Dedicated |
Operating model
Autonomy that earns its level.
-
1
Perceive
Fuse RGB, depth, hyperspectral, X-ray, scale, line-speed and robot-pose streams into one synchronised view of the carcass and the line.
-
2
Plan
Compute the cut path, blade force and seam, the grade call, the detection verdict and the portion batch — validated in the twin before the blade moves.
-
3
Act
Write back into the robotic cell, portioner, grader, rejector and MES with adaptive, per-carcass control at line speed.
-
4
Verify & learn
Measure realised yield, grade, weight and rejects, log the assurance trail, and feed supervised corrections back into training.
Console features
Built for the shift, not the boardroom.
Saleable yield82.4%+4.1% vs baseline
Giveaway0.7%−61% this week
FM rejects120 escapes
Line uptime99.4%+2.2 pts
Line 4 · Front-half deboning1,412 /hr83.1% yieldAutonomous
Line 2 · Breast portioning2,980 /hr0.6% giveawayAutonomous
Line 7 · X-ray screening3,140 /hr4 rejectsAdvisory
Line 1 · Primal fabrication640 /hr78.9% yieldShadow
Illustrative console data from a pilot deboning line. [PLACEHOLDER]
Numbers
What the features add up to.
4.1%
Average saleable-yield uplift on pilot deboning lines [PLACEHOLDER]
61%
Reduction in weight giveaway per fixed-weight pack
38 ms
Median foreign-material reject decision at the plant edge
99.9%
Plant-edge runtime uptime target with fail-safe line stop
Integration features
Read, decide, write back.
Cutting & deboning
- Robotic primal cutting cells
- Deboning and trimming lines
- Blade force and seam controllers
- Cell safety and E-stop interlocks
Grading & inspection
- Vision and hyperspectral graders
- Carcass grading cameras
- X-ray and metal detectors
- Checkweighers and rejectors
Portioning & packing
- Portioners and slicers
- Fixed-weight batching
- Packing and palletising robots
- Labelling and traceability
Plant systems
- MES and production monitoring
- OPC UA / Modbus / EtherNet-IP
- Historians and time-series stores
- ERP and order specs
Quality & food safety
- HACCP control points
- QMS and CAPA workflows
- Traceability and lot genealogy
- Sanitation and hygiene records
Identity & workflow
- SSO / SAML / SCIM
- Role-based approval gates
- Ticketing and on-call alerting
- Shift handover surfaces
Assurance features
Provable by construction.
SOC 2 Type II (in progress)HACCP-alignedUSDA-FSISEU 853/2004GDPRISO 27001 (planned)
Per-tenant isolation
Every plant gets isolated data, models and vector stores. Cut recipes and species models never cross a tenant boundary — federated learning shares patterns, never your product IP.
Assurance-grade audit trail
Immutable logs link sensor frames, model version, autonomy level, approvals, overrides and outcomes for every agent action — built for recall defence and model governance.
Fail-safe by design
Blade, robot and line stops are deterministic and independent of the cloud. Graceful degradation returns the cell to a safe state if perception confidence drops.
Feedback
The features that changed the shift.
“The line does not care that every bird is different — Slicium does. We stopped programming a machine and started supervising an operator that adapts to each carcass.”
“Giveaway was the quiet leak nobody could close. Watching the portioner hold target within a couple of grams, shift after shift, changed the economics of the whole pack line.”
“What sold my team was the audit trail. Every reject links back to the frame, the model version and who approved the autonomy level. That is what a recall investigation actually needs.”
Design-partner quotes are composite and pending publication approval. [PLACEHOLDER]
Feature FAQ
Details worth asking about.
No. The perception and control loop runs entirely on the plant edge. Cloud is used for training, fleet management and reporting, and can be disabled for on-prem or air-gapped deployments. Federated learning shares model improvements without exposing plant recipes, supplier data or tenant images.
A typical pilot runs one line for 8–12 weeks: two weeks of integration and shadow-mode baselining, four to six weeks of advisory operation, then graduated autonomy against the agreed success metric. Connectors for common cutting, grading, X-ray, portioning and MES systems are pre-built. [PLACEHOLDER]
Cells are specified for cold, wet, IP69K washdown environments with daily caustic sanitation. Perception enclosures, cabling and edge compute are selected for condensation, temperature swing and high-pressure cleaning, and validated with your sanitation crew during commissioning.
Three tiers: Line at $12,000 per processing line per month for one workflow, Plant at $80,000 per month for the whole loop including the twin, and Enterprise custom agreements for multi-site fleets. Annual prepay saves 15–20%, and outcome-based components can be tied to yield, giveaway, labour or safety.
Start with one line. Prove the yield.
Run a paid pilot on a single processing line with a defined yield, giveaway or labour success metric. Shadow mode first, autonomy only when the numbers earn it.