™Account for every mile.
See distance by vehicle and driver, with business, personal, commuting, and unclassified mileage kept visible.
Output: mileage coverage reportFleet mileage control center · Free beta
Bring fleet mileage and fuel into one clear report.
Give the owner, operations, and finance one traceable view of mileage coverage, fuel spend, supported MPG, and the exceptions that still need a decision.
Miles accounted forFuel spend explainedExceptions owned
Free beta for 25 US field-service fleets
No card. No subscription. One short feedback email.
Illustrative SFP digital avatarMeet your digital fleet specialist
An agent that turns fleet evidence into an owner conversation.
The skill gives your AI a focused operating role. It knows which files to ask for, how to connect them, what the evidence can support, and when a person must decide.
- Brings together
- Telematics, gas cards, dispatch, mileage logs, and finance.
- Works through
- Identity mapping, normalization, reconciliation, MPG, and exceptions.
- Hands back
- A management report, evidence trail, and owned review queue.
Business value
Turn disconnected fleet files into four useful decisions.
Instead of asking an owner to compare five exports by hand, the skill organizes the evidence around the questions that move a weekly fleet review forward.
Explain the fuel spend.
Match fuel-card activity to vehicles, trips, work events, and finance records without hiding reversals or unmatched items.
Output: fuel and finance reconciliationUse MPG you can support.
Keep full-to-full tank-cycle MPG separate from approximate period MPG so the number carries its evidence limits.
Output: supported MPG cycle registerWork the exceptions first.
Route missing tank boundaries, identity gaps, odometer issues, and unmatched purchases to a named human reviewer.
Output: prioritized review queueCoordinated agent power
One mileage skill. Four specialist roles working together.
Each role works from the same saved evidence and passes its result to the next. The owner gets one coordinated report instead of four disconnected analyses.
Illustrative SFP agent crewThe coverage specialist
Normalizes odometers, trip distance, vehicles, drivers, and proposed business-use classifications without hiding gaps.
Hands back: driver and vehicle mileage coverageThe reconciliation specialist
Connects gas-card purchases, reversals, units, vehicles, trips, and finance records while preserving unmatched activity.
Hands back: fuel reconciliation and supported MPGThe dispatch specialist
Uses jobs, work orders, timing, and dispatch context to help a reviewer understand why fleet movement occurred.
Hands back: work-event evidence and context gapsThe exception coordinator
Prioritizes missing tank boundaries, identity conflicts, odometer issues, and unsupported conclusions for a named person.
Hands back: an owned exception and decision queueSynthetic report preview
See the owner-ready outputs before you build the skill.
Every value below comes from the skill's bundled fixtures. Each panel is labeled synthetic and keeps the distinction between supported tank-cycle MPG and approximate period MPG.
15.000Fixture miles covered12.000Supported weighted MPG1Priority exception routed
Coverage outputDriver and vehicle mileage coverage
15.000 fixture miles, one matched driver and vehicle, and 100.000% proposed classification coverage—still unreviewed.
Fuel + MPG outputSupported tank-cycle MPG and fuel reconciliation
Two full-to-full fixture cycles support 12.000 weighted MPG. The separate period estimate is 1.500 MPG and is not presented as tank-cycle evidence.
Action outputPriority exceptions with reviewer routing
A missing closing full-tank boundary stays in review. The agent flags evidence gaps; a named person decides what they mean.
Built to save repeated work
Spend less time re-explaining the business to your agent.
This skill carries a reusable intelligence layer for manage fleet mileage and fuel: focused context, workflow-fit personalization, evidence-led research, expert acceptance checks, and a defensible record of the work it helped remove.
Bring the right facts once.
A local context tool turns scope, rules, sources, prior decisions, and conflicts into a compact brief the next run can reuse.
Less repeated prompting and source huntingResearch only when the job needs it.
Workflow-specific guidance defines strong sources, freshness, quality checks, expertise boundaries, and when research can stop.
More focused analysis with traceable evidenceShow what work changed.
A comparison tool records minutes, manual steps, tokens, source opens, rework, and completed outputs against a comparable baseline.
Measured or clearly labeled as estimatedFit the way your business actually runs.
Workflow-specific questions capture systems, terminology, policies, thresholds, owners, and operating constraints. Critical gaps hold only the outputs they affect.
Draft, review, and operational readinessBuilt for the questions a practitioner will ask.
Each output carries anticipated expert concerns, evidence requirements, pass conditions, hold conditions, and a controlled revision path.
Actual reviewer feedback stays separately attributedWhat the skill delivers
Seven practical outputs for the people running your fleet.
The local work pack gives the owner a management summary while preserving the detailed evidence fleet, operations, and finance need to review it.
7Practical outputs5Source categories4Evidence checks15Local Python tools
A fleet review built around action, not another data dump.
Use when a service or fleet company needs mileage reporting, gas-card reconciliation, business-purpose review, fuel-economy analysis, or a management-ready audit trail.
- Measure mileage coverage before relying on the report
- Reconcile gas-card, trip, work-event, and finance evidence
- Separate supported MPG from approximate screening metrics
- Assign evidence gaps and exceptions to a human reviewer
From activation check to management report.
- 01Activation assessment
- 02Normalized mileage, fuel, finance, and work-event evidence
- 03Driver and vehicle mileage summaries
- 04Fuel-card-to-trip and finance reconciliation
- 05Business, personal, commuting, and unclassified mileage coverage
- 06Supported full-to-full MPG cycles when evidence permits
- 07Exception queue and mileage management report
Coverage, supported MPG, fuel reconciliation, and open exceptions in one management view.
Seventeen standard-library Python entry points help intake, normalize, reconcile, verify, analyze, report, personalize, manage expert review, check research, and measure work.
Normalized rows retain source lineage while unsupported conclusions stay visibly blocked.
Classification, driver-conduct, tax, accounting, and operating decisions remain with your reviewers.
How the work runs
Saved exports in. A controlled fleet review out.
The skill works from copies of the files you already control. It does not log into, change, or send data back to provider systems.
Export saved files
Bring read-only copies from telematics, gas cards, dispatch, mileage logs, and finance.
Reconcile locally
The agent maps identities, normalizes units, joins evidence, calculates supported metrics, and preserves gaps.
Review the decisions
Owner, fleet, operations, or finance reviews exceptions before the report is relied on.
Start with the exports you already control.
- Mileage logs or saved telematics exports
- Fuel-card, dispatch, and finance exports
- Vehicle and driver mappings, reporting period, mileage policy, and reviewers
4 evidence rules protect the report.
- Every normalized row retains source lineage and hashes.
- Supported MPG requires complete full-to-full tank boundaries and odometers.
- Synthetic adapters remain pilot-only until customer-sample contracts pass.
- Classification and downstream decisions remain human-reviewed.
Simple first request
“I want one mileage and fuel report from my trip, gas-card, job, and money files.”
The skill will ask for the next fact or file. You do not need to know a special command.
When one skill proves useful
Build an agent skill pack for your business.
Choose up to 20 business jobs. We make each skill fit the same business. Your team can use the pack again and again.
- Free during beta · $49 planned after beta
- Up to 20 agent skills
- Made for the same business
Questions
Know what happens before you begin.
Is Manage Fleet Mileage and Fuel really free?
Yes. You can make and download one beta skill per email. No card or plan is needed. We ask to send one feedback email after you try it.
What should I have ready?
Start with mileage logs or saved telematics exports, fuel-card, dispatch, and finance exports, vehicle and driver mappings, reporting period, mileage policy, and reviewers. Use copies of your files and remove private information you do not need for the job.
Will the skill take action by itself?
The skill works from local copies and saved read-only exports. It never changes Samsara, gas-card, dispatch, payroll, or accounting systems. A qualified person reviews business purpose, reimbursement, tax, payroll, privacy, fraud, safety, and driver decisions.
How does the skill reduce repeated work and AI context?
It builds a reusable context brief, loads detailed evidence only when a stage needs it, checks the operating context for this workflow, audits research sources, and compares a like-for-like baseline with the assisted run. Token counts are planning estimates unless provider usage is supplied, and no savings are guaranteed.
How is the skill personalized and expert-reviewed?
Each skill has workflow-specific questions for systems, policies, owners, thresholds, terminology, and operating constraints. It reports which outputs are ready, partial, or blocked, then provides anticipated practitioner concerns and acceptance tests. Those concerns are a review rubric—not customer feedback or an endorsement—and actual reviewer comments stay separately attributed.
What is the ZIP file?
A ZIP is a way to send the agent skill in one file. Opening it does not install or run anything. An optional helper tool runs only when you choose to run it.
What if I need more than one agent skill?
The Personalized AI Skill Pack gives you up to 20 agent skills for the same business. It is free during beta, with a planned $49 price after beta.