Check draft B/Ls against shipping instructions
AI reads the draft B/L from the carrier and checks it item by item against the S/I, invoice, and packing list. Staff confirm differences with the shipper first.
- 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
Staff compare each draft bill of lading (B/L) from the carrier with the shipper's shipping instructions, invoice, and packing list, checking the shipper, consignee, notify party, goods description, package count, weight, and marks. In a 2024 survey by Japan's transport ministry, 62.3% of B/L and waybill issuance went by email attachment. Changing a B/L after it is issued can cost a fee.
The workflow in Kitewell
- Receive the draft B/L email from the carrier and save the PDFEmail
- AI reads the shipper, consignee, notify party, goods, package count, weight, and marks from the draftAI judgment
- AI compares them with the shipping instructions, invoice, and packing list, and shows differences and a note to the shipperAI judgment
- Staff review the differences and confirm them with the shipperHuman task
- Based on the shipper's answer, staff decide whether to request corrections or approve the draftApproval
- Record the check and the shipper's answer for the shipmentAutomatic
What AI does
Reads drafts in any layout and compares them item by item with the shipping instructions and the shipper's documents. It separates differences in spelling or format from differences in substance, and drafts the note asking the shipper to confirm.
Where people decide
Staff confirm with the shipper whether a difference is an error. Requesting corrections from the carrier and approving the draft stay with staff.
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 fields are read correctly from your main carriers' draft layouts
- Which fields to compare, and what counts as a difference (spelling, units, abbreviations)
- Whether drafts arrive by email or are checked on the carrier's site
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 it approve the draft automatically?
- No. Deciding whether a difference is an error, requesting corrections, and approving the draft stay with staff. Kitewell takes on reading and cross-checking the documents and drafting the note to the shipper.
- 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
Track vessels and tell shippers about ETA changes
Poll carriers' tracking APIs for your B/Ls and containers and detect ETA changes. AI drafts what the change affects and the shipper notice; staff check it.
Manage free time, demurrage, and detention
Calculate each container's remaining free time from discharge, gate-out, and empty-return events, and alert staff as deadlines near. AI drafts pickup requests.
Read and cross-check import documents before filing
AI reads the invoice, packing list, and B/L and cross-checks goods, quantities, weights, and values. A customs specialist resolves mismatches before filing.
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.