Run everything inside your network.
Fully air-gappedThe knowledge graph, agents and models run locally. Updates arrive as signed offline packages and no data leaves the site.
- Local model serving
- Read-only connectors
- Your SSO, roles and audit
The same research, applied to each domain’s evidence, rules and owners.
A worked example: a capacity deviation in end-of-line cell testing, investigated across live plant events, genealogy, process data and specifications. Agents do the legwork. Engineers make the call.
The questionWhy did capacity drop on line B this week, and which packs are affected?
Find the affected cells, the batches they share and when the drop started.
Compare formation and ageing parameters for affected and unaffected batches.
Follow material lots through genealogy to every module and pack they reached.
Read the current specification and SOP revision for this cell type and step.
Propose hold, retest or release per pack, with the evidence attached.
The drop sits in batch B-77 on formation chamber 3, all from material lot M-114. 14 packs are affected; hold proposed for review.
The quality engineer confirms which packs are held before anything changes in the MES.
Process changes are proposed to the line owner, never applied directly.
New entities, relations and rules the agents suggest enter the plant graph only after an engineer accepts them.
Both are mapped to one plant model, so an alarm, a process step and the right procedure can be connected. Sources stay where they are; connectors are read-only.
Agent Hive
Agent HiveMachine states, values, alarms and counts, mapped to equipment and process steps.
SOPs, recipes, datasheets and specifications, read for equipment, limits and applicability.
Material, lot, cell, module and pack history from the MES and ERP.
The run fans out to process, material and specification agents, joins their findings and stops at the hold. Nothing changes in the MES until the quality engineer signs off.
Agents suggest new entities, relations and rules as they read the sources. Engineers review every change before it becomes part of the graph, and each answer stays tied to the graph version that produced it.
Agents read the sources and suggest entities, relations and rules.
Process engineers accept, edit or reject each proposed change.
Approved changes are versioned and linked to their sources.
Uncertain links and unanswered questions go back for review.
Ontology evolution. How the structure changed over 4 proposals: v1: baseline with Thing, Document, Report, Metric, Party, Vendor, Supplier. P-1 (add, from steward): Add class Definition ⊑ Metric, applied, giving v2. Diff: + Definition subClassOf Metric. P-2 (merge, from resolver): Merge Vendor into Supplier, applied, giving v3. Diff: − Vendor; + Supplier altLabel “Vendor”. P-3 (add, from extractor): Add class Misc ⊑ Document, rejected; v3 unchanged. Diff: + Misc subClassOf Document; ✗ rejected: no defining property. P-4 (deprecate, from steward): Deprecate Report, applied, giving v4. Diff: ~ Report owl:deprecated true; + replaced by Document. Selected: P-4 (deprecate, from steward): Deprecate Report, applied, giving v4. Diff: ~ Report owl:deprecated true; + replaced by Document.
Genealogy decides the hold scope: the material lot the evidence points to, traced through cells and modules to the packs it reached.
Return the right setpoint, limit or procedure for this product and process.
Link the events, documents, lots and timestamps behind it.
Compare causes across process areas and show the supporting evidence.
Find the affected specifications, procedures, limits and downstream steps.
A question set agreed with plant engineers checks that answers are correct, complete and backed by the right evidence. Each reviewed answer joins the set.
| Question | v1 | v2 | v3 | v4 |
|---|---|---|---|---|
| What is the formation voltage limit for cell type A?Find a fact | ✓ | ✓ | ✓ | ✓ |
| Which SOP revision applies to ageing on line B?Find a fact | ✗ | ✓ | ✓ | ✓ |
| Which material lots fed the failed cells?Show the evidence | ~ | ✓ | ✓ | ✓ |
| Which packs contain cells from lot M-114?Show the evidence | ✗ | ✗ | ✓ | ✓ |
| Why did capacity drop on line B in week 41?Investigate a cause | ✗ | ~ | ✗ | ✓ |
| Is the drop on one formation chamber or all?Investigate a cause | ~ | ✓ | ✓ | ✓ |
| If ageing time drops by 4 h, which limits change?Check a change | ✗ | ✗ | ~ | ✓ |
| Which downstream tests depend on the impedance limit?Check a change | ✓ | ~ | ✓ | ✓ |
Correct, partly right or wrong, with a note.
Reviewed answers become repeatable cases.
Prompts, tools and graph changes rerun the set.
A named owner approves the release.
Models can run inside the plant or through a controlled gateway. Plant context and access controls stay the same.
The knowledge graph, agents and models run locally. Updates arrive as signed offline packages and no data leaves the site.
A policy gateway controls what is sent, which model receives it and what comes back into the workflow.
Point at a part no egress · signed bundles in · data stays inside