Beat 01
Line
One tool or inspection line, one agent family, one success metric. The fastest path to a defensible internal result.
Products
Line for a single tool or inspection line, Fab for the full closed loop, Enterprise for multi-fab standardisation.
Deployed beside the tools that make panels
Product line
Beat 01
One tool or inspection line, one agent family, one success metric. The fastest path to a defensible internal result.
Beat 02
The full closed loop across deposition, anneal, inspection, transfer, handling, test and bin, with the panel-and-line twin included.
Beat 03
Multi-fab rollout, custom process and defect models, fleet management, on-prem or air-gapped deployment and formal SLAs.
Beat 04
The same fab-edge runtime, the same autonomy gates and the same immutable audit log. Governance is not an upgrade.
# closed loop, one panel
perceive substrate → tft → emitter stack → sub-pixel
plan deposition · anneal · transfer · test/bin
act recipe write-back (SECS-GEM)
sense mura ΔL* · sub-pixel opens · particles
optimise yield · ramp · scrap
log immutable audit entry ✓ signed
retrain engineer correction → model
Composition
Every deployment is assembled from the same components; the tier decides how many.
Step 1 of 6 · edge
Deterministic, offline-capable execution beside the tools.
Step 2 of 6 · agents
One family for Line; the full seven for Fab and Enterprise.
Step 3 of 6 · connectors
SECS-GEM/HSMS, OPC-UA, REST and MES integration.
Step 4 of 6 · console
Where engineers approve, override and correct.
Step 5 of 6 · twin
Included from the Fab tier; validates before the run.
Step 6 of 6 · audit
Immutable, signed decision records on every tier.
Plans
Land on one workflow with a hard success metric, then expand tool by tool, module by module, fab by fab.
$16,000
per tool or inspection line / month
Panel makers validating ROI on the wedge workflow.
$110,000
per fab / month
Scaling fabs adopting the full closed loop.
Custom
land $700k–$8M ACV
Panel makers and display groups standardising on Emiteon.
Comparison
Line proves the wedge. Fab runs the loop. Enterprise standardises it.
| Capability | Line | Fab | Enterprise |
|---|---|---|---|
| Fab edge runtime | Included | Included | Included |
| Agent families | One | All seven | All seven + custom |
| Panel-and-line digital twin | — | Included | Included |
| Immutable audit log | Included | Included | Included |
| Autonomy gates | Shadow, advisory | All three | All three |
| Multi-fab governance | — | — | Included |
| On-prem / air-gapped | — | Optional | Included |
| Custom models | — | — | Included |
| SLA and dedicated support | Standard | Standard | Dedicated |
Included everywhere
Every write-back path can stop and return tools and handling to a known-good state.
Recipes, panel designs and defect images stay scoped to your tenant.
Identity from your directory, roles matched to fab responsibilities.
Replays are safe; a lost acknowledgement never double-writes a recipe.
Every decision is reconstructable against the exact model that made it.
Weak signal or lost control plane drops autonomy instead of guessing.
Expansion
A Line deployment that hits its metric expands to adjacent tools; a Fab deployment that holds its numbers expands to adjacent fabs. Net revenue retention is the honest measure of whether the loop works.
# closed loop, one panel
perceive substrate → tft → emitter stack → sub-pixel
plan deposition · anneal · transfer · test/bin
act recipe write-back (SECS-GEM)
sense mura ΔL* · sub-pixel opens · particles
optimise yield · ramp · scrap
log immutable audit entry ✓ signed
retrain engineer correction → model
Connectors
Voices from the line
“We do not lose panels because nobody is watching. We lose them because the signal that mattered was buried under a thousand nuisance calls.”
“Ramp is the whole game. If a new product takes two quarters of manual tuning, that is two quarters of margin we never get back.”
“Transfer yield is our ceiling on microLED. Every dead emitter is a repair cycle or a scrapped backplane.”
Quotes are illustrative composites drawn from discovery interviews with process-integration, yield and quality engineers. Named references are [PLACEHOLDER] pending design-partner consent.
The economics
Emiteon is priced and evaluated on the numbers a fab already reports. These are design-partner targets for the first twelve months of deployment.
Figures marked as targets are design-partner objectives, not audited results. Company operating status, customers and outcomes are [ASPIRATIONAL] until independently verified.
FAQ
Through three gates. Shadow mode observes and predicts with no write-back; advisory mode recommends recipe, transfer and binning moves that a process-integration or yield engineer approves; graduated autonomy releases low-risk deposition, anneal and transfer control once measured accuracy and twin validation clear the bar. High-impact decisions stay human-in-the-loop.
Reducing false calls is the wedge, not a side effect. The mura-and-defect agent is trained on true-versus-false-call labels from your own inspection history, so it separates genuine large-area non-uniformity, sub-pixel opens and shorts, particles and stains from nuisance signals, and every call is traceable to the evidence behind it.
Per-tenant isolation with recipes, panel designs and defect images scoped to your tenant, encryption in transit and at rest, SSO/RBAC, an immutable yield/quality-grade audit log and an on-prem or air-gapped option. Fleet learning shares model improvements, never your recipes.
Deposition, photolithography, encapsulation and anneal tools, Mura/AOI inspection and metrology, array and cell test, mass-transfer and repair stations, robotic handling and MES — vendor-neutral via SECS-GEM/HSMS where the tool supports it, with REST and OPC-UA bridges elsewhere.
Every pixel, perfectly uniform.
We would rather win a Line pilot on evidence than sell a fab on a slide.