Quick answer: Fuel and plant hire surcharges are usually applied as a fixed percentage or flat fee, buried inside a much larger invoice, and rarely questioned because checking them manually across hundreds of invoices isn't realistic. Once these lines are extracted and classified separately, they're consistently one of the fastest and most defensible savings a construction procurement audit finds.
Why surcharges go unchecked
A fuel surcharge might be 3% of a much bigger plant hire invoice. Checking whether that 3% is still justified, still matches the contract, and still tracks with actual fuel prices requires pulling it out of hundreds of invoices individually, which almost nobody has time to do.
Why they compound into real money
Applied consistently across a large plant hire spend for a full year, a small surcharge percentage becomes a meaningful line on its own, one that most finance teams have never seen isolated from the rest of the invoice.
What extraction and classification reveals
Once surcharges are pulled out and classified as their own category, you can check them against actual market fuel prices, compare suppliers fairly, and challenge specific charges with specific evidence instead of a general sense that something feels high.
Pearstop extracts fuel and plant hire surcharges from invoices automatically and classifies them as their own line, so you can check whether they're still justified without manually opening hundreds of PDFs.

Stephanie Wiechers
CEO & Co-founder, Pearstop
Stephanie leads Pearstop's go-to-market and strategic direction. She works directly with procurement and FM leaders across Europe to understand how data quality affects margins, contracts, and AI readiness.
LinkedIn →Further reading
A UNSPSC treemap exposes tail spend before it costs you
Pair a UNSPSC category treemap with an on-contract vs tail-spend bar chart to see where procurement spend hides, and negotiate with real leverage.
Read more →AI & DigitalWhy a general AI tool failed our classification problem
A general-purpose AI tool hallucinated categories at volume and lost consistency across thousands of lines. The tool was asked the wrong question.
Read more →


