Beat 01
The panel model
Substrate, array, emitter stack and sub-pixels modelled together. Every signal is interpreted in the context of the layers around it.
Documentation
Everything needed to deploy, operate and audit the loop
Guides for connectors, agents, autonomy gates, the review console, model management and audit export.
- Getting started
- Connectors
- Agents
- Operations
Getting started
Start here
Deployment overview
What runs on site, what runs centrally, and what never leaves the fab
Commissioning a connector
Survey, read-only enablement, mapping and shadow scoring
Autonomy gates
Shadow, advisory and graduated autonomy — thresholds and evidence
Baseline measurement
How to measure the number the pilot will be judged on
Concepts
The four ideas everything else builds on
Beat 02
The loop
Perceive, plan, act, sense, optimise, log, retrain. The loop runs in every mode; only write-back and approval change.
Beat 03
Autonomy gates
Shadow observes, advisory recommends, graduated autonomy acts on low-risk paths. Gates are per-agent and evidence-based.
Beat 04
The audit record
The unit of trust: sensed evidence, decision, model version, approver and resulting change, signed and immutable.
# 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
Interface guides
SECS-GEM / HSMS
Message sets, event subscription and governed recipe write-back
OPC-UA
Bridging tools and handling systems that do not speak SECS-GEM
REST
Modern inspection and metrology systems
MES integration
Lot context, routing and disposition write-back
Historian import
Bulk historical data for baselining and training
Agents
Per-agent documentation
deposit-and-pattern
Holds emitter-stack and TFT layer uniformity across the whole mother glass by closing the loop between chamber telemetry, overlay metrology and recipe write-back.
tft-and-anneal
Stabilises threshold voltage and mobility across the panel so backplane variation never becomes visible non-uniformity at cell test.
mura-and-defect
Separates real large-area non-uniformity, sub-pixel opens and shorts, particles and stains from the nuisance signals that swamp inspection queues.
microled-transfer
Optimises mass transfer and repair — the yield ceiling on microLED — by learning placement, bonding and repair outcomes emitter by emitter.
panel-handling
Coordinates robotic panel and cassette movement so large, fragile substrates move without breakage, particles or queue stalls.
age-test-and-bin
Runs aging, test and binning decisions with the demand mix in view, so grade calls maximise value instead of defaulting to the safest bin.
yield-and-ramp
Turns every excursion into a shorter ramp for the next product, compressing the manual tuning cycle that eats new-model margin.
Operations
Check the runtime in one command
The edge CLI reports everything an on-call engineer needs: runtime health, autonomy state, queued writes and fail-safe status.
$ emiteon status
runtime running v3.8.2
agents 7 loaded · 6 healthy · 1 advisory-only
autonomy graduated (mura-and-defect: advisory)
queued-writes 0
audit durable last export 02:00
fail-safe armed
Operations guides
Running it day to day
Model management
Version pinning, staged rollout, canary and rollback.
Audit export
Signed export into your quality and yield systems.
Alerting and escalation
Routing calls into ticketing, alerting and shift handover.
Backup and retention
Retention aligned to warranty and reliability windows.
Upgrade path
Staged upgrades with rollback and no line downtime.
Air-gapped operation
Signed model bundles delivered through your own media process.
Reference
Autonomy gate thresholds
Thresholds are agreed per deployment; these are the defaults we propose.
| Gate | Requires | Can do |
|---|---|---|
| Shadow | Connector commissioned read-only | Observe, predict, log — no write-back |
| Advisory | Measured accuracy against your dispositions | Recommend actions for engineer approval |
| Graduated autonomy | Sustained accuracy plus twin validation | Execute low-risk actions automatically |
| Human-in-the-loop (always) | By policy | High-impact recipe, scrap and bin decisions |
Troubleshooting
When something is wrong
The runtime is designed so that the first question — what did it decide and why — is always answerable from the audit log, offline, without contacting us.
- Every call links to its evidence and model version
- Autonomy transitions are logged with the trigger
- Fail-safe activations record the state returned to
- Signed export lets your team investigate independently
# 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
Voices from the line
What the fab floor tells us
“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
What the loop is measured on
Emiteon is priced and evaluated on the numbers a fab already reports. These are design-partner targets for the first twelve months of deployment.
$26BDisplay-fab automation, process control, inspection, test and fab software market
~14%Annual growth in the segments Emiteon plays in
135%Net revenue retention target from land-and-expand
99.9%Uptime target for the fab edge runtime
Figures marked as targets are design-partner objectives, not audited results. Company operating status, customers and outcomes are [ASPIRATIONAL] until independently verified.
FAQ
Questions fabs ask first
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.
Need documentation we have not written yet?
Tell us which interface or workflow you need covered and we will get it to you.