Sovereign AI for Transport
From maritime ports to rail networks, transport infrastructure is the lifeblood of the economy, and every asset in it produces data that must not leave the operator. The platform models the network, predicts what will fail, coordinates the response, and keeps OT data where it belongs.
One model of the network
Track, rolling stock, berths, runways, signalling and sensors modelled once from GIS, asset and control systems, so a question about a segment has one answer.
Predict before it fails
Sensor and inspection history turned into failure risk per asset, with maintenance windows recommended against the timetable.
Coordinate the incident
One picture for the control room and partner agencies during a disruption, and the NIS2 report drafted from the record.
A rail operator, a port authority or an airport runs thousands of assets, dozens of operational systems and a control room that stitches them together by radio and spreadsheet. Predictive maintenance, flow optimisation and incident response are all natural for AI, but signalling, control and passenger data are critical-infrastructure data under NIS2, and the OT network cannot host anything that phones home. The platform runs where the network is and keeps the decision with the operator.
Read this if you're leading operations, asset management, safety, security or IT at a rail infrastructure manager, a port or airport authority, a road operator or a public transport company, or accountable for its NIS2 obligations.
For transport, Scrydon is the sovereign AI and data platform that models the network's assets, systems and flows in one ontology, runs predictive maintenance, flow optimisation and incident-response agents on it inside the operator's own infrastructure, and produces the NIS2 incident and audit records the regulator expects.
It runs on-premises, in a national sovereign cloud or air-gapped for the control network, with open-weight models served locally, so the same platform serves the control room, the asset planners and the security team.
Thousands of assets, dozens of systems, one control room
From maritime ports to rail networks, transport infrastructure is the lifeblood of the economy, and it runs on thousands of assets and dozens of operational systems that were never designed to share. Track, rolling stock, berths, cranes, runways and signalling live in GIS, asset-management and control systems that do not agree on what an asset is, so a question about one segment takes three systems to answer. Maintenance runs on calendars rather than on the condition the sensors already report, and a disruption is coordinated by radio between the operator, emergency services, the municipality and the utilities, each with their own picture.
The boundary is set by the control network. Signalling and control systems are critical infrastructure under NIS2 and must never host software that reaches the internet, passenger and freight data are commercially and personally sensitive, and any AI that touches an asset has to stop at a person. So the AI that helps has to run where the network is, model the whole network rather than one vendor's slice, and leave the operational decision with the control room.
Assets in silos — Track, rolling stock, berths, cranes and signalling live in GIS, asset and control systems that do not agree on what an asset is.
Maintenance by calendar — Inspections and replacements run on schedules, not on the condition the sensors already report.
Disruption by radio — An incident involves the operator, emergency services, the municipality and the utilities, each with their own picture.
OT that cannot connect — Signalling and control networks are critical infrastructure under NIS2 and must never host software that reaches the internet.
Model the network, predict the failure, coordinate the response
The platform models the network in one ontology of segments, assets, vehicles, sensors, timetables and services, mapped from GIS, asset, control and scheduling systems without replacing any of them. Sensor telemetry, inspection reports, weather and traffic land on that model continuously, so the condition of an asset and the flow on a segment are live rather than reconstructed, and a digital twin of the network keeps planning and simulation against the current state.
On that model, failure risk per asset and congestion per segment are forecast, and decision intelligence recommends maintenance windows and flow changes against the timetable, with the expected effect and cost. During a disruption, agents draft the incident picture from fused feeds, release the relevant layer to emergency services and the municipality through a data space, and prepare the NIS2 notification from the record. The control room approves every operational action, and each approval, override and agent action is logged.
- 1
Model
An ontology of segments, assets, vehicles, sensors, timetables and services, mapped from GIS, asset, control and scheduling systems.
- 2
Fuse
Sensor telemetry, inspection reports, weather and traffic land on the model continuously, so condition and flow are live.
- 3
Predict and plan
Failure risk per asset and congestion per segment are forecast; maintenance windows and flow changes are recommended against the timetable.
- 4
Respond, with approval
Agents draft the incident picture, the partner release and the NIS2 notification; the control room approves, and everything is logged.
The control network sets the boundary
The control network sets the boundary, and the platform is built to respect it. It runs on the operator's own hardware, in a national sovereign cloud or fully air-gapped for signalling and control, with open-weight models served locally so no inference call, licence check or update path leaves the perimeter.
Agents are identities, not scripts. Each carries scoped permissions per system and per action, so an agent that reads telemetry cannot write to signalling or a controller unless a policy allows it and a person approves. Partners see what they are entitled to through data spaces rather than through access to the operator's systems. The audit log, the policy decisions and the approvals are the NIS2, Cyber Resilience Act and ISO 27001 evidence, produced by running the platform rather than assembled for the audit.
On-premises or air-gapped — The full platform runs on the operator's hardware, in a national sovereign cloud or disconnected for the control network.
Agents that cannot touch control — Scoped agent identity means an agent that reads telemetry cannot write to signalling or a controller unless a policy and a person allow it.
Share with partners on your terms — Data spaces release an incident layer to emergency services or the municipality without handing over the operator's systems.
Evidence by construction — Audit log, policy decisions and approvals are the NIS2 and ISO 27001 evidence, produced by running the platform.
Keep an eye on this space
What changed for your sector in European AI sovereignty, and what we learned in the field. A few times a year, no drip campaign.
Use cases for transport
Rail, ports, airports and roads on one sovereign platform.
Predictive Infrastructure Maintenance
Public Works
Challenge
Reactive maintenance of roads, bridges, and utilities leads to costly emergency repairs and service disruptions.
Solution
Analytics models process data from IoT sensors and historical reports to predict failures before they happen, scheduling preventative maintenance.
Read more
40% reduction in emergency repair costs and extended lifespan of critical public infrastructure.
Autonomous Rail Logistics
Transportation
Challenge
Managing mixed freight and passenger traffic on ageing rail networks leads to delays and inefficient capacity usage.
Solution
Sovereign optimisation agents re-route trains in real-time based on weather, track conditions, and priority, ensuring optimal network throughput.
Read more
15% increase in network capacity and improved on-time performance.
AI-Ready Sensor & OT Data Foundation
Data Engineering
Challenge
Grid, water and transport operators sit on years of SCADA and sensor history, but it is too fragmented and poorly labelled for AI models to use reliably.
Solution
An AI-ready data pipeline cleans, contextualises and grounds OT and sensor data in the ontology before it reaches any model, so agents reason over trustworthy, well-described data rather than raw tag soup.
Read more
Predictive models and agents reach production readiness faster, built on a data foundation operators can actually trust.
Human-Agent Outage Response Coordination
Incident Response
Challenge
An outage response spans multiple teams and shift changes, and each handoff between an agent's triage and an operator's decision restarts the coordination from scratch, costing minutes that matter during an active incident.
Solution
The AI OS runs outage response as one coordinated process: agents triage telemetry and stage response actions, operators approve or override at defined checkpoints, and the full incident state carries across shift changes automatically.
Read more
Faster, better-coordinated outage response with a single continuous incident record instead of fragmented handoffs between teams and shifts.
Ontology-Based Asset & Network Model
Asset Management
Challenge
A single substation or pipeline segment is represented differently in the GIS, the asset management system and the SCADA historian, so answering "what do we know about this asset" means manually cross-referencing systems that were never built to agree.
Solution
An ontology models every asset and network connection as a single entity, mapped from GIS, EAM and historian data, so agents and operators reason over one consistent asset model.
Read more
A unified, queryable asset and network model that replaces manual cross-referencing across disconnected systems.
What Transport has to comply with
The regulations that decide whether AI can run on this data at all. Each page lists what the framework asks and which platform controls answer it — properties and refusals, not a checklist.
NIS2 · NIS2 Directive
Applies to: Essential and important entities across critical sectors — energy, transport, water, health, digital infrastructure, public administration, manufacturing and more — and their supply chains.
How the platform supports itCRA · Cyber Resilience Act
Applies to: Manufacturers, importers and distributors of products with digital elements — hardware and software — placed on the EU market, including software vendors and the organisations that build connected products on top of them.
How the platform supports itAI Act · EU AI Act
Applies to: Providers, deployers, importers and distributors placing AI systems on the EU market or whose AI output is used in the EU.
How the platform supports itISO 27001 · ISO/IEC 27001
Applies to: Any organisation that operates an information security management system — routinely required of software vendors, service providers and regulated enterprises by customers, regulators and procurement.
How the platform supports it
What these outcomes actually run on
A transport architect asks whether it runs on the control network, how the network is modelled and how agents are kept away from signalling. These are the pages that answer those questions.
Sovereign Foundations
The zero-trust foundation the whole platform sits on — the same stack from air-gapped to cloud.
Air-Gapped
The full platform running offline, on networks with no route to the internet.
AI OS
The runtime that maps a process to steps, routes each step to a system, an agent or a person, and gives it the context to act.
Digital Twin
A live model of a physical system you can query, simulate against and plan with.
Analytics
Self-service analytics over a governed semantic model, so numbers mean the same thing in every report.
Identity
Federated identity and zero-trust access — for people and for agents, under the same policy.
Frequently asked questions
Can the platform run on the signalling or control network?+
How does predictive maintenance work across GIS, asset and control systems?+
How does it help during a major disruption?+
How does the platform support NIS2 for a transport operator?+
Do we have to replace our asset-management or control systems?+
Do you partner on tenders and framework contracts?+
Prefer to write? Email hello [at] scrydon.com and we will get back to you.
Keep going
Three routes from here: the rules you will be measured against, the platform these outcomes run on, and the sessions where we walk through them.
The rules that apply
Each regulation, what it asks, and the controls the platform provides for it.
The platform behind it
The AI Operating System, Analytics and Sovereign Foundations, page by page.
Every use case
All of them in one place, grouped by the sector that knows them best.
How – Inside the AI OS: running governed agents on your own cluster, live
17 Sept 2026, 09:00
Part 2 of the Sovereign AI series, for engineers and architects. No slides after minute five: an agent gets an identity and scoped permissions, calls tools over governed MCP, retrieves from the ontology rather than raw tables, runs inside the sandbox and is stopped when it steps outside policy, and everything lands in the audit trail — then the same stack brought up on a disconnected network. Properties and refusals, shown rather than claimed.
Other parts of Critical Infrastructure
The other dedicated pages under Critical Infrastructure, and the sector overview they hang off.
Utilities
Energy, water and gas operators: feeder-level forecasting, NIS2 incident reporting and OT data that stays inside the perimeter.
Read the pageTelecommunications
Fixed, mobile and wholesale operators: alarm correlation, fault prediction, subscriber agents and NIS2 reporting with the data kept inside the operator.
Read the page
Partners
