Enter carrier bookings and shipping instructions
AI reads booking requests and shipping instructions from shippers' emails. Approved details are entered on the carrier's site, and AI drafts the shipper reply.
- 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
Booking requests and shipping instructions (S/I) arrive from shippers in email bodies, Excel files, and PDFs. Staff pick out the vessel, ports, container type and count, goods description, and weight, and type them again into each carrier's website. In a 2024 survey by Japan's transport ministry, 45.0% of export bookings went by email attachment. With carriers not connected through INTTRA or an API, entry and confirmation stay manual.
The workflow in Kitewell
- Receive the shipper's booking request or shipping instruction email and save the attachmentsEmail
- AI reads the vessel, loading and discharge ports, container type and count, goods, and weight, and lists what is missingAI judgment
- Staff check what was read and what is missing, and approve the entryApproval
- Enter the booking or shipping instruction on the carrier's site and save the confirmation screen and booking numberWeb
- Record the booking number and details in the shipment list, and AI drafts the reply to the shipperAI judgment
- Staff check the reply and send it to the shipperHuman task
What AI does
Organizes requests in any layout into the carrier site's input fields. Missing items, and items where the email body and attachment disagree, are shown with where they came from for staff to confirm.
Where people decide
Shipment details follow the shipper's instructions, and staff confirm them before entry. Staff also check the reply before it goes to the shipper.
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 your main carriers' terms of use allow automated operation of their sites
- Which trades connect through INTTRA, a carrier API, or Cyber Port, and which still need screen entry
- Whether the needed fields are read correctly from each shipper's request format
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
- Is this needed if we already use INTTRA or carrier APIs?
- For carriers and trades already connected that way, those are the quicker route. Kitewell takes on organizing the details from the shipper's email, and entry on sites of unconnected carriers whose terms allow automated operation.
- 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.