Keep the actual-carrier ledger
AI reads the actual-carrier notices subcontractors email, links each to a job on the dispatch sheet, and fills in the ledger. Staff check gaps and mismatches.
- 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)
The problem today
Since April 2025, a prime contractor that subcontracts a load of 1.5 tons or more must record, for each job, the actual carrier's name, the goods and route, and its tier in the subcontracting chain. Subcontractors' notices arrive by email, fax, and phone, and dispatchers copy them into the ledger after comparing them with the dispatch sheet. When no notice comes, they chase the subcontractor.
The workflow in Kitewell
- Pick subcontracted jobs of 1.5 tons or more from the dispatch sheet and register them as a batch sheetAutomatic
- Take in the notices and attachments subcontractors send by emailEmail
- AI reads the actual carrier's name, route, goods, and tier from each notice and links it to a job on the dispatch sheetAI judgment
- Dispatchers review jobs with no notice or with details that differ from the dispatch sheet, and ask the subcontractorHuman task
- Write the confirmed details into each row of the ledger and keep the notice they came fromAutomatic
What AI does
Reads notices that each subcontractor words differently, extracts the actual carrier's name, route, goods, and tier, and links each notice to its job on the dispatch sheet. Links it is unsure of are shown with the reasoning.
Where people decide
Dispatchers check that each notice is right and decide what goes in the ledger. Staff also contact subcontractors whose notices have not arrived.
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 the needed details can be read from notices that each subcontractor words differently
- Whether notices link correctly to jobs on the dispatch sheet
- Whether notices that now arrive by fax or phone can be moved to email
- Whether the ledger is kept in a form you can produce promptly for audits or a shipper's request to see it
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
- Does automating the actual-carrier ledger make us compliant?
- Automation alone does not. Kitewell reads the notices, matches them against the dispatch sheet, and drafts the records. Staff check what goes on record and decide whether it meets the law.
- How does this differ from dedicated ledger apps?
- There is a feature that collects actual-carrier details through a QR code on the request form, and apps that build ledger data from dispatch messages. If your subcontractors can use them, they are the quicker route. Kitewell suits subcontractors who send notices their own way, by email or as PDFs.
- 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
Total driver waiting and handling times
Collect each site's arrival, check-in, and handling records, compute waiting and handling time per delivery, and total monthly averages. Staff set exclusions.
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.
Reconcile freight invoices
Match carriers' freight invoice lines against shipment records, and send lines with weight, distance, or surcharge differences for approval.
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.