Cut-and-Debone agent
Controls robotic primal cutting, deboning and trimming. Adapts cut path, blade force and seam-following to each animal’s anatomy to maximise saleable yield without bone chips or over-trim.
Physical AI for meat, poultry & seafood
Every cut,
Every cut,
maximum yield.
Slicium is the autonomous operations layer for protein processing — perceiving every carcass, planning every cut, and closing the loop from sensor to blade at line speed.
Runs on the plant edge. Shadow mode first — autonomy only when the numbers earn it.
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
Trusted on the cut floor
Northfold PoultryMeridian PorkCascadia ProteinBaltic Fillet Co.Ardenne FoodsHarbour & Sons Seafood
Design-partner and pilot plants. Names shown are representative programme cohorts. [PLACEHOLDER]
Measured outcomes
The margin is in the millimetre.
Yield, giveaway, contamination and labour are the four numbers that decide a protein plant’s year. Slicium moves all four.
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
The loop
Perception, planning and control — on one plant-edge platform.
Incumbents sell a machine, a camera, or a detector. Slicium unifies them into a system of action that adapts to every animal.
Cut & debone
A cut path for this carcass, not the average one.
Every animal is anatomically unique. The Cut-and-Debone agent maps bone, seam and fat/lean boundaries, then drives cut path, blade force and seam-following per carcass — recovering saleable meat that fixed automation leaves on the bone.
- Per-carcass anatomy segmentation and seam detection
- Adaptive blade force with bone-contact avoidance
- Over-trim and bone-chip suppression
- Encodes the master butcher’s craft from supervised corrections
Detect & protect
Catch the fragment before it becomes a recall.
X-ray, RGB and hyperspectral streams are fused at the edge so bone chips, metal, plastic and defects are identified and rejected in tens of milliseconds — with the evidence chain a recall investigation actually needs.
- Multi-sensor fusion at 30–120 FPS
- Sub-50 ms reject decisions [ASPIRATIONAL]
- Hygiene and pathogen-risk intelligence
- Immutable frame-to-verdict audit trail
Portion & pack
Stop paying for weight you give away.
Overshooting target weight bleeds margin on every single pack. The Portion-and-Pack agent predicts weight from geometry and controls the portioner and batcher to land on spec instead of above it.
- Predictive weight from 3D geometry
- Fixed-weight batching optimisation
- Real-time giveaway per pack, per shift, per SKU
- Scrap and rework routing
How it runs
Perceive → plan → act → learn.
The closed loop runs entirely at the plant edge, inside your safety and food-safety windows.
-
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.
Six agents, one orchestrator
The agents that run the plant.
Each agent owns a workflow. The plant orchestrator sequences them, holds the safety envelope and keeps the audit trail.
Grade-and-Yield agent
Senses and predicts grade, marbling, lean/fat ratio, weight and yield from vision and hyperspectral imaging — before and after the cut.
Detect-and-Safety agent
Fuses X-ray, RGB and hyperspectral streams for foreign-material, defect and contamination detection, plus hygiene and pathogen-risk intelligence.
Portion-and-Pack agent
Controls portioning, slicing, weight-giveaway and fixed-weight batching so every pack lands on target instead of above it.
Robot-and-Handling agent
Drives robotic loading, hanging, handling, packing and palletising in cold, wet, washdown environments rated for daily sanitation.
Yield-and-Throughput agent
Optimises line balance, scrap, giveaway and cold-chain flow across the plant, and flags off-spec risk before it reaches the pack.
Why Slicium wins
A system of action, not another dashboard.
Hit the yield before the cut
An Omniverse-based protein twin simulates carcass anatomy, cut sequences and yield, then auto-optimises the cut and portion plan to hit target yield and spec before the blade moves. No other vendor closes that loop.
Category growing fast
Protein-processing automation, robotic cutting, vision grading, X-ray inspection and plant MES exceed $25B and grow around 15% a year.
Compounding data
Rare anatomy, bone-chip and contamination patterns learned at one plant transfer, privacy-preserving, to every similar line.
Plant edge, GPU-accelerated
Jetson-class cells, TensorRT, DeepStream and Holoscan fuse sensors deterministically at line speed.
Assurance-grade by default
Product specs, HACCP controls, sensor frames, model versions, autonomy level, approvals and outcomes are linked in one graph for recall defence and model governance.
Plant console
Every line, every carcass, in real time.
Yield, grade, giveaway, foreign material and autonomy level per line — with the audit trail one click away.
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]
Design partners
What the cut floor says.
“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]
Integrations
Deep write-back into the systems you already run.
Read-only tools observe. Slicium acts — through pre-built connectors into cutting, grading, detection, portioning, packing and MES systems.
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
Trust
Built for regulated, high-consequence production.
Food safety and IP protection are not features bolted on later — they are the architecture.
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.
Enterprise
From one line to every plant you run.
Land on a single workflow with clear ROI, then expand across lines, modules and sites under one control plane.
Multi-site fleet management
One control plane for every plant, line and cell. Roll a validated cut program from one site to twenty with staged approval.
Custom species and cut models
Fine-tuned anatomy, grade and yield models for your species mix, specs and customer cut sheets — trained on your supervised corrections.
Dedicated SLAs and support
99.9% uptime target, named solutions engineers, on-site commissioning and 24/7 response aligned to your shift patterns.
Questions
What processors ask first.
That variability is the whole point. Fixed automation fails because it repeats one motion; Slicium perceives each animal’s anatomy — bone position, seam location, fat/lean boundary — and plans a cut path, blade force and seam-follow specific to that carcass. The cut is validated against a digital twin that predicts yield before the blade moves.
Slicium runs a graduated autonomy model: shadow, then advisory, then supervised autonomy, each gated by measured accuracy and twin validation. Below the confidence threshold the cell degrades to a safe state, escalates to a human, or routes the product to rework — it never guesses on a food-safety decision.
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]
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.