Cargo Overseas had always prided itself on being ahead of the curve.
From vegetation management along UK railways to utility infrastructure maintenance, they operated at a scale where data wasn’t just helpful—it was everywhere. Fleet GPS systems, job scheduling platforms, client portals, fuel cards, weather feeds, subcontractor reports, compliance systems. Every department had a dashboard. Every manager had reports. And yet, something was off.
It wasn’t obvious at first.
Mark, Head of Operations, noticed it as a “feeling” before he could point to numbers. Certain contracts were becoming less profitable. Response times were slipping in specific regions. Fuel costs were creeping up—but only for some teams. Nothing was breaking. But nothing was fully under control either.
Each system told a clean, logical story on its own.
The scheduling platform showed high job completion rates.
The GPS system showed vehicles moving efficiently.
The finance system showed stable margins—on paper.
But no one could answer a simple question without calling three people:
“What’s actually happening in the field right now?”
That changed when they piloted Intera.
They didn’t start big. Just one role: Regional Operations Controller – South England.
Intera wasn’t connected to “everything.” Only a few sources:
- Fleet GPS feed
- Job scheduling system
- Fuel card data
- Weather API
- Internal incident reports
Within a week, the first pattern appeared.
Not a dashboard. Not a KPI. A pattern.
“Fuel consumption anomaly linked to delayed vegetation jobs after rainfall.”
At first, it sounded too generic to be useful. But Intera drilled deeper automatically:
- Jobs delayed by rain were being rescheduled manually
- Rescheduled routes were not optimized in the GPS system
- Crews were driving longer distances between fragmented job clusters
- Engines were idling longer on wet terrain
Individually, each system was “correct.”
Together, they were hiding a compounding inefficiency.
Mark didn’t need to ask three teams anymore. He could see it.
Two weeks later, another pattern surfaced:
“Subcontractor overuse in high-density zones despite available internal crews.”
This one surprised everyone.
The scheduling system showed optimal allocation. But Intera combined:
- Crew availability logs
- Real-time vehicle positioning
- Subcontractor billing data
It turned out internal crews were technically “available,” but consistently just outside the planner’s manual visibility window. So subcontractors were being called in—quietly increasing costs.
Again, nothing was broken. But something was misaligned.
The real shift wasn’t in the data.
It was in behavior.
Before Intera, Mark’s day looked like this:
- Morning calls with regional managers
- Midday follow-ups on “issues”
- End-of-day reviews trying to understand what went wrong
After Intera, his day changed.
He opened one screen.
Not a dashboard full of charts—but a list of live operational signals:
- “Northwest region: rising fuel inefficiency linked to route fragmentation”
- “Rail contract: early-stage delay pattern forming due to equipment downtime clustering”
- “London zone: overperformance—replicable crew behavior detected”
Some were red. Some were yellow. Some were green.
For the first time, he wasn’t reacting to problems.
He was seeing them form.
Three months into the pilot, Cargo Overseas didn’t replace any systems.
They didn’t rebuild their stack.
They added something new: context across systems.
Finance started trusting operations data more.
Operations stopped relying on intuition alone.
Regional managers stopped “defending numbers” and started exploring patterns.
One unexpected outcome stood out.
A high-performing crew in the Midlands kept showing up as a green signal:
“Consistent overperformance under variable weather conditions.”
Intera broke it down:
- Route clustering behavior
- Start-time discipline
- Equipment usage patterns
It wasn’t luck. It was repeatable.
That “pattern” was turned into a new operational guideline and rolled out across two other regions.
Cargo Overseas didn’t suddenly become a different company.
They still had the same systems. The same people. The same complexity.
But they gained something they didn’t have before:
The ability to know what’s happening—without asking anyone.