Reconcile freight invoices
Match carriers' freight invoice lines against shipment records, and send lines with weight, distance, or surcharge differences for approval.
- Runs on your own PCs and servers
- Use Azure OpenAI, Amazon Bedrock, Google Vertex AI, or an in-house model
- Its engine is Descarty's open-source Dagu (GPL-3.0)
30 October invoice lines taken from the carrier's portal and checked against shipment records and contract rates in 30 seconds; the 4 overcharges (+$23.70), on weight, zone, rate, and an accessorial, came with their reasons and evidence. Accounting approved, 26 lines were approved for payment, and the 4 went back to the carrier. Kitewell built the workflow 5 minutes after the request.
A real run on October 29, 2026, sped up. The system it works with was built for the demo.
The problem today
Every month, staff download invoice lines from several carriers and match them against shipment records one by one. A missed surcharge or weight difference means overpaying.
The workflow in Kitewell
- Download invoice lines from each carrier's billing portalWeb
- Match invoice lines against shipment recordsAutomatic
- AI estimates the reason for each line whose amount differsAI judgment
- Accounting reviews lines with differences and approves paymentApproval
- Export the results as CSV for the accounting systemAutomatic
What AI does
For lines whose amounts differ, estimates whether weight, distance, surcharges, or the contract rate explains it, and shows the evidence.
Where people decide
Accounting reviews only the lines with differences and decides whether to query the carrier or pay.
Done condition
Every carrier's invoice lines for the month are collected, their count matches each portal's own list, and every line either matches a shipment at the contract rate or is listed as an exception.
Exceptions it lists
- A carrier portal that needs sign-in again
- A line count that differs from the portal's list
- A line with no matching shipment
- An amount that differs on weight, zone, rate, or a surcharge
Prove Kitewell on your own systems
Try it free for 14 days on your own PC. To see it working first, ask for a 30-minute demo. There is also a one-month onboarding (¥500,000 before tax), where we build your first job together.
What to check when you try this work
- Whether invoice downloads from each carrier's portal run reliably
- Whether the matching rules for contract rates and surcharges fit your process
- Whether the estimated reasons help the review
How the onboarding runs
- Week 1Requirements and success criteria
- Weeks 2 to 3Build
- Week 4Verify on production screens
- Final dayReport
One-month onboarding
- Length
- One month
- Cost
- ¥500,000 (tax excluded). Your staff build, with the developer beside them
- If you go on to a license
- The onboarding fee is credited to the first year's contract
- Without the onboarding
- At Team scale, start on Team monthly (¥14,800 per computer a month, tax excluded), and cancel in any month
You can try it first on your own PC, in the free 14-day trial.
Frequently asked questions
- Do our documents and screens leave the company?
- Kitewell runs on your own PCs and servers, and Descarty never receives your business data. You choose the AI model: a cloud API, or an in-house or local model with an OpenAI-compatible API. With an in-house model, no data leaves the company. With a cloud model, what the AI reads is sent to the model's provider.
- What if the AI misreads something?
- A person checks what the AI produced before the work goes on. In a sheet, every value the AI reads shows the quote it came from, and rows below your confidence threshold go to a person. Reviewers can send work back with notes on what to fix, and who approved what is kept in the run history.
- What happens when a screen changes or a run stops?
- When a screen changes, the AI reads it again, relearns the step, and carries on. The relearned step is saved, and later runs repeat it. If a run still stops, ask the assistant right there, and it finds the cause and proposes a fix. A proposal is not saved until a person applies it.
- What happens to the RPA and systems we use today?
- Keep them. Kitewell operates screens the way a person does, so it works with systems that have no API. Move the robots that keep stopping and the work you gave up automating because it needs judgment, and leave fast, fixed processing in your current RPA.
- What does it cost?
- ¥14,800 per computer per month, or ¥148,000 per computer when paid yearly, before tax. A computer costs the same whether it builds or runs. You can try it free for 14 days. The one-month onboarding, where we build your first job together, is ¥500,000 before tax, credited to the first year if you go on.
Related use cases
Bill waiting time and loading charges per shipper
From driver logs, dispatch sheets, and tachograph records, pick out waiting and loading work per shipper that draft invoices miss. Staff decide what to bill.
Look up tracking numbers in bulk
For an Excel list of shipments, delivery status from each carrier's site goes into each row, and the shipments that need action are shown.
Book truck arrival slots in each shipper's system
For each trip on the dispatch sheet, enter the slot, truck, and driver in each shipper's or warehouse's booking system and write the booking number back.
See this work in a demo
A 30-minute demo shows this workflow running. The 14-day free trial lets you check it on your own systems.