Trusted Agents for
Energy and Utilities
From grid operations and asset maintenance to customers, trading and investment planning, Prometheux runs your knowledge as rules on the data you already have, across GIS, asset, meter, billing, market and operational systems. Teams and their AI agents get the same answer every time, with the rules and source rows behind it. No migration, no new data store.
Proven in production
The Business Is Connected.
Its Data Isn't.
Grid, assets, customers, markets and partners each run on their own systems, and the knowledge that connects them sits with a few experts. Every outage review, investment case, billing query and emissions or regulatory report starts by stitching data together again, by hand.
Where Energy and
Utility Teams Start
Use cases across delivery, assets, customers and markets, and planning, each run as rules on the data you already have. Pick one, prove it on your own data, then reuse the model for the next.
Grid & Network
Keep supply reliable by planning, operating and restoring the network from one picture of how it connects.
Assets & Field Operations
Spend maintenance and field effort where reliability and safety depend on it, from one view of every asset.
Customers & Markets
Bill correctly, serve customers consistently and see commercial exposure across books.
Planning & Reporting
Plan investment and connections, and report figures, from the same model, computed by your definitions and traced to source.
The Questions Other
Tools Can't Answer
Who Loses Supply
If this substation trips, which feeders, transformers and customers lose supply, which of them are critical sites or priority customers, and through which path? A recursive walk down the network at any depth, counted per asset.
Single Points of Failure
Which hospitals, water works and other critical sites are supplied by one path only, so a single open switch or failed transformer cuts them off?
Hierarchies That Roll Up
Which substations carry the most components past their inspection date, rolled up from component to bay to site to region, with each count traced to the records behind it?
One Asset, Many Records
Which entries in GIS, the asset register and maintenance history are the same physical asset? Every match cites its rule. See entity resolution.
One Model Across
Grid and Business
Typical industrial data platforms consolidate OT and IT data into their own store before anyone can use it. Prometheux sits between your grid, asset and customer data and the people, tools and agents that act on it, and runs the knowledge where the data already lives.
Analytics
Control-room dashboards, graph and BI
Integrations
Back into the databases behind GIS, asset, billing and work-order systems
Agents
Utility agents, deterministic answers
Models
Define the ontology, read answers, and power analytics, integrations and agents
Your grid, asset and customer data
Network connectivity, asset registers, operational, meter, billing and customer data, connected in place. Nothing to migrate.
-
Grid, Asset and Customer Operations
- Outage impact, asset roll-ups, tariff and billing checks and transition reporting on one model
- Agents call deterministic rules over MCP and API, with the derivation behind every answer
- Results written back to the databases behind GIS, asset, billing and work-order systems, on a schedule or when data changes
-
The Utility Knowledge Engine
- One network, asset and customer model across systems, instead of a separate copy per tool
- Recursion with aggregation and graph algorithms: customers per feeder, critical load per substation, assets per site
- Same input, same output, with lineage to the rules and source rows
-
Cloud Agnostic
- Run in your own data centre, any cloud or inside your data platform, under your own controls
- Scale horizontally on clusters as meter and network data grows, with optional GPU acceleration
- 1-click deployment anywhere: EKS, AKS, GKE, Databricks Clusters, Snowpark Containers
-
Utility-Data Agnostic
- Read and write connectivity, asset, meter, billing and operational data in any database, format and schema
- Connect data lakes, warehouses, object storage, files and APIs across clouds and on-premises
- No new data store or twin to migrate into and keep in sync
Same Layers.
Better Built.
Map a typical energy data or grid-twin platform to Prometheux and the difference is where the work happens: in place, in rules you own, with an answer you can check, for the grid and the business around it.
Your Grid.
Your Rules.
Network knowledge sits with a few engineers and inside tools that each cover part of the picture. Prometheux turns that knowledge into readable rules that run on your existing GIS, asset, meter and customer data, so outage reviews, investment cases and regulatory reporting all start from the same, checkable answers.
Owned, Not Vendor-Bound
The model spans GIS, asset, meter and customer systems and stays with you, in rules your engineers can read and version.
Deterministic and Explained
The same network state gives the same answer, with the rules and source rows behind it, which is what an outage review or a regulator asks for.
Built for Grid Scale
Rules run as distributed, parallel jobs, with optional GPU acceleration, on compute you already have. See high-performance engine.
Portable by Design
Run in Prometheux cloud, your cloud, or on your own servers on Docker or Kubernetes, inside your own security boundary. See on-premises.
Codify grid knowledge once. Reuse it for outages, assets and reporting. Give agents rules they can be trusted on.
One Use Case.
Then the Next.
Connect in Place
Point Prometheux at the data for one network area, one billing process or one report. The data is processed where it lives; nothing is copied.
Codify the Knowledge
Your engineers and analysts, our forward deployed engineers and the AI assistant turn network rules, asset hierarchies, tariff logic and reporting definitions into readable rules in days, not months.
Run One Use Case
Outage impact, an asset roll-up, a billing check or one transition figure, on live data, for people and agents alike.
Expand Across the Business
Each new network area, process or report reuses the rules already written, so the model grows without rebuilding context for every tool.
Questions,
Answered
Is this another data platform or digital twin?
No. Prometheux reads your GIS, asset, meter, billing, operational and customer data where it already lives, across clouds and on-premises, and runs the rules there. The model is logical: there's nothing new to migrate or keep in sync.
Do we have to replace our GIS, asset, billing or outage systems?
No. Keep them. Prometheux reads from them, adds the cross-system reasoning, and writes results back to the systems your teams already use, on a schedule, when data changes or on demand.
Does it replace power-flow or physics simulation?
No. Prometheux reasons over connectivity, assets, customers and business rules. Simulation results stored in your databases or files can be read as one more source, alongside everything else.
Does it come with emissions or ESG calculations built in?
No. Your reporting definitions and factors are codified as rules; Prometheux computes each figure from them on your data and shows the lineage to the source rows, so the same inputs always give the same figure.
Our operational data can't leave our environment. Can it run there?
Yes. Prometheux runs on your own servers on Docker or Kubernetes, or in your own cloud, so the data stays under your controls. It works within existing access controls such as Unity Catalog and Snowflake RBAC, and Prometheux is SOC 2 Type II certified.
What does it cost at our data volumes?
It depends on your data and use cases, so we measure it on yours rather than quote a generic figure. Most utilities start with one network area, one process or one report, prove the value, then expand.
Related Capabilities
Bring One Energy
Use Case.
Outage impact, an asset roll-up, a billing check or one transition figure, on your own data. Our forward deployed engineers will run it with you, in place, on your infrastructure.
