Correlation happens too slowly to prevent anything
Utilities struggle to connect AMI, SCADA and field events fast enough to avoid losses, outages or compliance failures.
Supply chain & industry ยท North America
AMI, SCADA and field events all know something. None of them know it together.
Which is why the operation stays reactive when the data to be proactive already exists.
~9 hrs
average power interruption from major events per customer in 2024, against about four hours a year in the decade before.
In North America
This is what it actually runs on here.
Platforms in this market
- AMI head-end systems
- SCADA
- OSI PI
- Esri GIS
- OMS
Rules that apply here
- NERC CIP
- FERC orders
- state PUC reporting
- IEEE 1547
We read the rule before the call. It is the cheapest way to prove we did the work.
What is happening
Three systems each saw the fault. None of them told the other.
Maintenance stays reactive
Proactive maintenance, predictive load management and demand forecasting are all possible with data you already collect. Very little of it gets used.
Specialised assets do not fit standard systems
Bucket trucks, digger derricks and line equipment carry certifications alongside normal maintenance. Spreadsheets do not scale to that, and generic fleet systems do not model it.
Ageing infrastructure without real-time visibility
Older assets raise both outage likelihood and operating cost, and lack the instrumentation for anomaly detection.
However hard, whatever it is
Fault signals are one example. Bring the one that costs most.
This page is about joining field notes to events. If yours is billing, connections or a crew scheduling problem, that is the same job.
-
01 We sit with you
Days where the work happens, not a workshop in a meeting room. We watch the job get done and write down the shortcuts nobody wrote down.
-
02 We read everything
Your data, your rules, your vendors and their documentation, and the published research on your sector. We report what is actually in there.
-
03 We break it to first principles
Not which tool fixes this. What is actually causing it, taken apart until we reach the piece that cannot be divided further.
-
04 Then we build
Weeks, not quarters. By this point we are not guessing what to build, and guessing is the thing that makes projects long.
Where we sit
SCADA stays where it is. We build the layer that joins it to the rest.
4
What you get
- Correlated Meter, grid and field data in one timeline
- Condition-based Maintenance driven by asset condition
- Faster restore Outage response with the full picture
3
Built new for you — none of this exists in your stack today
- A sensor we build when the meter cannot tell you enough
- A field tablet that logs a job with no signal
- One map showing meters, faults and crews together
2
The grid-event layer Reads your meters and historians. Sends no command to any device.
Connectors, one agreed meaning per field, and a model reading what no
field holds. Accuracy measured on your own records.
1
- AMI head-end systems
- SCADA
- OSI PI
- Esri GIS
- OMS
What you already run — unchanged, and still yours
If a device reports it, we can read it. If it does not, we build the device. Modbus, DNP3, a historian tag, a meter with no port at all. And when nothing measures it, a sensor we make.
-
No API -
No documentation -
A terminal from 1994 -
It arrives as paper -
The vendor said no -
It reports nothing
Not a list of limits. Name yours on the call.
And once we can reach it, a model can read it. Most of the value here is in the sources nobody ever structured — the note, the letter, the screen.
Intelligence, plumbed in
A field engineer's note is the earliest fault signal you have.
The build is a connector to the work-order system, one agreed fault vocabulary, and a test set of faults you already know.
How we make AI survive real data-
Connectors -
A semantic layer -
Evals you can check
What changes
Judge us on this, not on what we built.
Correlated Meter, grid and field data in one timeline
So an anomaly becomes an event with context rather than three unrelated alarms.
Condition-based Maintenance driven by asset condition
Including certification status for specialised equipment, tracked alongside mechanical condition.
Faster restore Outage response with the full picture
What the meters saw, what the grid saw and what the crew found, in one place while it is still happening.
Who this is for
The people who feel this first
-
Director of Operations -
Asset Management Head -
Field Services Manager -
Grid Operations Manager -
Compliance Lead
Straight answers
The questions you would ask on the call
-
Our OT network is isolated, and it needs to stay that way.
Agreed, and we design for that. We read through a data diode or a historian replica. We are never a part the control system depends on. Nothing we build can affect grid operations.
-
Can you work with our historian rather than live SCADA?
Usually that is the better option. Historians are built to be read from, they carry the history you need, and they keep us entirely out of the control path.
-
Do you have hardware capability?
Yes. We build the sensors and the firmware, as well as the software above them. That matters when the answer is to start measuring something that reports nothing today.
-
Is AI useful on SCADA and meter data?
The gain is usually in the field notes, not the telemetry. We read those, join them to the events, and test against faults you already know.
Do you know the rules that apply in the United States and Canada?
For energy & utilities that means NERC CIP, FERC orders, state PUC reporting and IEEE 1547. We read the rule before the call, so the first meeting is about your operation rather than about us catching up.
Whatever energy & utilities needs here, we can make it.
What you already run stays where it is. Around it we build software, hardware and the process itself. Here that means a sensor we build when the meter cannot tell you enough.
See everything we build-
Software -
Hardware -
Ways of working -
Whole ventures
Honest about the numbers
The figure above is from US Energy Information Administration, for energy & utilities.
We have not localised it, because a number nobody can check is worth less than a real one plus this sentence. The pattern travels. The size of it in your market is a question for the call.
Same industry, other markets