Retail & ecommerce · Databricks
Pilot Company: Fueling efficiency from pump to profit
Public case study · not a Metric Oak engagement
- Reduction in manual processing via automation of the handling of fuel bills of lading (BOLs)
- 99%
- Decrease in overall processing costs
- 90%
- Accuracy in document processing of BOLs, accelerating revenue recognition
- 98.6%
What happened
The story in brief
A North American fuel supplier delivering fuel around the clock processed handwritten delivery forms by hand. Automating document processing with AI on Databricks removed most manual entry and achieved high accuracy, speeding up revenue recognition.
How it compares
- 90% decrease in overall processing costs, against a median reported cost reduction of 50% across 16 retail & ecommerce results.
Planning something similar?
AI-ready data
Governed, retrievable data for GenAI, RAG and agents. Senior engineers, fixed scope, measured results.
Related case studies
Retail & ecommerce · Databricks
84.5162M
Households served
Retail & ecommerce · Databricks
Ahold Delhaize50%
Cost reduction
Retail & ecommerce · Databricks
Air Miles80TB
Of retail consumer data ingested to support the AIR MILES Reward Program
Related insights
Frequently asked questions
What results did Pilot Company report?
Pilot Company reported 99% reduction in manual processing via automation of the handling of fuel bills of lading (BOLs); 90% decrease in overall processing costs; 98.6% accuracy in document processing of BOLs, accelerating revenue recognition, according to its customer story published by Databricks.
Which platform and technologies did Pilot Company use?
Pilot Company used Databricks, including Unity Catalog, Delta Lake, MLflow, Large language models.
How do these results compare with other retail & ecommerce programs?
90% decrease in overall processing costs, against a median reported cost reduction of 50% across 16 retail & ecommerce results.
Source
Customer story published by Databricks: Fueling efficiency from pump to profit (opens databricks.com in a new tab) on databricks.com. Figures as published, retrieved 27 October 2026. The summary above is Metric Oak's own. This is not a Metric Oak engagement.
Have 30 minutes? Get a senior architect’s view of your data platform.
No sales deck. You talk to the engineer who would lead the work.
Book an architecture review