Northfold Poultry — front-half deboning
Started on one deboning line in shadow mode, reached supervised autonomy in nine weeks and rolled the program to three sister lines.
Customers
The plants that stopped cutting the average carcass.
Design partners across four species, running Slicium from shadow mode to graduated autonomy on live production lines.
Design partners
Northfold PoultryMeridian PorkCascadia ProteinBaltic Fillet Co.Ardenne FoodsHarbour & Sons Seafood
Design-partner and pilot plants. Names shown are representative programme cohorts. [PLACEHOLDER]
Aggregate results
Across the design-partner cohort.
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
“We spent a decade buying machines that repeated a motion. This is the first system that understands what it is cutting.”
Customer stories
How each plant started.
Meridian Pork — fixed-weight retail packs
Attacked weight giveaway on retail belly and loin packs with predictive portion control tied to checkweigher feedback.
Baltic Fillet Co. — pin-bone detection
Fused X-ray and vision inspection to cut pin-bone escapes to zero while reducing false rejects that were destroying yield.
Cascadia Protein — grading consistency
Replaced shift-to-shift grader drift with consistent marbling and yield calls written back into pricing and MES.
Ardenne Foods — labour resilience
Used autonomy to hold output through a 22% cut-floor vacancy rate without overtime or line slowdowns.
Harbour & Sons — multi-site rollout
Standardised cut programs and evidence formats across four plants under one enterprise agreement.
By persona
Three people have to say yes.
Plant / Operations Director
Owns yield, throughput, labour and food safety. Wants autonomous production, not another report.
- Hard ROI in a paid pilot
- Output independent of staffing
- Fewer safety incidents
- Real-time visibility across lines
Processing / Yield Engineer
Owns cutting programs, yield, giveaway and portioning. Lives in the gap between spec and reality.
- Per-carcass adaptive cutting
- Twin testing before scrapping product
- Yield attribution by cell and program
- Rapid program rollout to sister lines
Food Safety / Quality Manager
Owns HACCP, foreign-material control, hygiene, grading and traceability. Carries the recall risk.
- Fused detection with fewer escapes
- Immutable evidence per decision
- HACCP control-point linkage
- Model change control they can audit
IT / OT and Security
Owns network segmentation, identity and the integrity of plant systems.
- On-prem and air-gapped options
- SSO, SAML and RBAC
- Signed OTA with change control
- No outbound data requirement
In their words
Operators, engineers, quality leads.
“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]
Adoption pattern
Every customer starts the same way.
One line, one number, eight weeks
Nobody signs a plant agreement on a slide. Every customer began with a single line, a single agreed metric and a shadow-mode baseline that made the comparison undeniable.
- Shadow baseline against current performance
- Advisory mode with operator corrections
- Supervised autonomy on the agreed envelope
- Measured result, then a decision
Then the expansion is obvious
Once the first line is proven, the second is a rollout, not a project. Programs, connectors and evidence formats are already validated — expansion is measured in weeks.
- Program reuse across sister lines
- Shared connectors and specs
- Cross-plant learning on rare events
- Target net revenue retention of 135%
What they see
The console customers live in.
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]
Their stacks
Equipment our customers already ran.
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
How they got approval
Security and food-safety sign-off.
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.
Customer FAQ
What new customers ask.
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.