Logistics automation: bookings, carrier ledgers, wait times
Truck bookings across shippers' systems, actual-carrier ledgers, waiting-time records, and billing: entry and records, automated with AI and human review.
- 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)

Common problems
Dispatchers enter the same trip again in each shipper's and warehouse's truck booking system
Since April 2025, written transport terms, actual-carrier ledgers, and waiting and handling records are required, adding records for every job
From April 2026, large shippers and warehouses measure driver waiting time and report it to the government, and ask carriers for the records
Use cases in this industry
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.
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.
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.
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.
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.
Trucking and warehouse paperwork grows with every shipper and subcontractor
Trucks carry 91.7% of Japan’s domestic freight by tonnage (fiscal 2023). Japan has 62,848 trucking companies (March 2024), and over 99% of general freight carriers are small or medium-sized businesses.
Since April 2024, truck drivers’ overtime has been capped at 960 hours a year, even under special circumstances. To keep drivers’ hours from being lost to waiting and loading, new duties for shippers and logistics companies took effect in April 2025 and April 2026.
Trucking and warehouse paperwork is made of exchanges with shippers, warehouses, and subcontractors. In a 2023 government survey, 70% of trucking companies said they use other trucking companies as subcontractors. Carriers that actually drive the loads said that even with a master contract, individual requests come by fax or email.
| Work | What stays manual | What already exists |
|---|---|---|
| Taking transport requests | Reading requests that arrive by fax or email and copying them into the dispatch sheet | Products that read delivery request forms with generative AI and turn them into CSV |
| Truck booking | Entering each trip in each shipper’s or warehouse’s booking system | Products that register bookings automatically from the same vendor’s dispatch system |
| Actual-carrier ledger | Collecting the actual carrier’s details from subcontractors and recording them for each job | A feature that collects actual-carrier details through a QR code on the request form, and apps that build the ledger |
| Waiting and handling records | Picking times out of driver logs and digital tachograph records and totaling them per shipper or site | Arrival and check-in records in truck booking systems |
| Shipping labels | Fitting order data to each carrier’s import format | Yamato Transport, Sagawa Express, and Japan Post label systems import CSV or Excel and print labels in bulk |
| Freight billing and payment | Matching invoices against actual jobs, including waiting and ancillary charges | Products that match invoices against payment data with AI |
Dedicated products are growing. In 2026, Hacobu launched MOVO Adapter, which reads delivery request forms with generative AI, and MOVO Billing, which matches invoices against planned payment data with AI. Yamato Transport’s B2 Cloud imports up to 1,000 labels at a time from Excel or CSV. What stays manual is the entry and matching that span systems and formats that differ by counterparty.
Each shipper and warehouse books trucks in a different system
The government lists truck booking systems (systems where carriers reserve an arrival slot at a loading dock) as one way to cut waiting time. Yet in its fiscal 2025 survey, only 17% of warehouse operators had a dock booking system, and 53% arranged arrival times by other means. The Ministry of Land, Infrastructure, Transport and Tourism (MLIT) notes that measures needing capital investment, such as dock booking systems, remain at a low rate of adoption.
The more these systems spread, the more work falls on carriers. Hacobell, which provides a truck booking system, names as a problem that carriers end up making bookings in several truck booking systems, and says each system’s input format differs, forcing tedious work on them.
In February 2025, Hacobell and TSUNAGUTE added links to each other’s booking systems. In July 2025, Hacobell also began registering trip requests made in its own dispatch system into its own booking system automatically. When a shipper’s or warehouse’s booking system comes from the same vendor as your dispatch system, links like these are enough. When it does not, someone still opens each booking system and enters each trip.
Since April 2025, every job leaves more records behind
Japan’s revised Motor Truck Transportation Business Act took effect on April 1, 2025. MLIT explains that layered subcontracting and transport contracts made by word of mouth had been major obstacles to carriers receiving fair fares and charges.
- Written transport terms: when a shipper and a trucking company make a transport contract, each gives the other a document stating the transport and its price, any loading or ancillary work and its price, and charges such as fuel surcharges. Email is allowed if the other party agrees, and copies are kept for one year. MLIT states that a transport request made only by phone violates the duty to provide written terms
- Actual-carrier ledger: a prime contractor that uses another company to carry a shipper’s load of 1.5 tons or more records, for each job, the actual carrier’s name, the goods and route, and its tier in the subcontracting chain, and keeps the record for one year. Subcontractors must notify the prime contractor of the actual carrier’s details
- Driver logs: the duty to record waiting of 30 minutes or more caused by the shipper, among other items, now covers all trucks, not just those of 8 tons gross weight and similar
From April 2026, freight forwarders that arrange trucking also must provide written terms, and keep the actual-carrier ledger when they act as prime contractor.
Charges written down become the basis for billing. In the 2023 survey, written contracts often left out ancillary work charges and fuel surcharges, and about half of companies said they had done ancillary work not in the contract. The standard freight rates revised in March 2024 set levels for loading and unloading charges on top of waiting charges, and add 50% when waiting and handling together exceed two hours. MLIT says recording waiting and handling times gives carriers the basis to collect waiting, loading, and unloading charges from shippers. Finding unbilled waiting and handling charges is covered in Bill waiting time and loading charges per shipper.
Tools for the actual-carrier ledger have appeared as well. In February 2025, Hacobu added a feature to MOVO Vista that registers the actual carrier’s name and tier through a QR code on the delivery request form. In February 2026, the Japanese company LOGITECH launched an app that builds ledger data from dispatch messages, replacing the truck number notices that used to go by phone or email. When subcontractors don’t use such tools, someone still matches details arriving by email or phone against the dispatch sheet.
Waiting and handling times are now measured and reported to the government
Under Japan’s revised Logistics Efficiency Act, all shippers and logistics companies have since April 2025 had a duty to make efforts to load trucks more efficiently and to cut drivers’ waiting and handling times. Since April 2026, companies above a certain size are designated as specified businesses and must submit medium- to long-term plans and periodic reports. Designated shippers must also appoint a chief logistics officer (CLO).
As of August 27, 2026, the designations covered 3,257 shippers and franchise chains (2,142 companies after removing duplicates), 877 trucking companies, and 56 warehouse operators. The first plans are due at the end of October 2026, and the first periodic reports at the end of July 2027.
Designated shippers and warehouse operators include measured waiting and handling times in their periodic reports. For warehouse operators, that means monthly averages for each site measured. If measuring everything is hard, they may sample at least five consecutive business days each quarter. The listed measurement methods include arrival display devices and other systems, reception logs, staff assigned to record times, and information from truck drivers.
Counterparties ask for the records too. MLIT’s guide for warehouse operators notes that shippers may ask them to measure and provide waiting and handling times broken out for that shipper. For carriers, MLIT expects that shippers who cannot track waiting and handling times will check with the trucking company.
In MLIT’s fiscal 2025 survey, a truck driver’s average working span per trip was 10 hours 13 minutes, of which waiting and handling took 2 hours 2 minutes, down 1 hour 16 minutes from the previous year. The government’s target is two hours or less of waiting and handling per trip. Even so, companies reported sites where drivers still wait more than five hours.
What to check before automating
- Each system’s terms of use: whether you may operate a shipper’s or warehouse’s truck booking system automatically depends on its terms and your agreements with them. Check the terms before you automate a website explains how
- Whether a dedicated product or link is enough: if your dispatch and booking systems come from the same vendor, they may link automatically. Dedicated products also exist for reading request forms, for the actual-carrier ledger, and for invoice matching. If they cover what you need, consider them first
- How time is counted: waiting time runs from arrival at the pickup or delivery site to the start of handling, counting only waiting caused by the shipper or site. Settle each shipper’s and site’s counting rules, such as how to exclude waiting the carrier caused, before automating
- Who decides: staff check and decide the charges in written terms, what goes in the ledger, the figures reported to the government, and what to bill shippers. People also judge whether the result meets the law
- Drivers’ personal information: decide how drivers’ names and phone numbers for bookings arrive from subcontractors, and where they may be entered
What Kitewell does
Descarty’s Kitewell is integration and automation middleware that connects systems through APIs, files, databases, and screens.
- Operates booking and shipper systems: AI reads and operates web systems and desktop apps that have no API. Operations that worked are remembered and repeated the same way on later runs
- Keeps going when screens change: when a remembered operation no longer fits the screen, AI reads the screen again, does the step, and remembers the new operation. If it still can’t proceed, the run stops, and AI looks into the cause and suggests the fix
- Runs trip by trip from the dispatch sheet: register an Excel list such as the dispatch sheet as a batch sheet, and it runs row by row and writes results such as booking numbers back to each row
- Reads notices that arrive by email: it checks Gmail, Microsoft 365, or IMAP mail at set intervals and saves attachments. AI steps read notices and request forms in PDFs and images
- Handles sign-in hurdles: passwords are referenced by name and typed in without showing the value to the AI. When a one-time password is required, the run pauses until staff enter it
- People check where it matters: approval can be set on any step, such as before booking or before a record is finalized. Requests reach Slack, Microsoft Teams, and email, and sending one back restarts the run from the step you choose
- Every operation on record: each run keeps its logs, screenshots of the screens it filled in, and approval decisions
- Alerts when it stops: failures are sent to Slack, Microsoft Teams, email, and more
You can start from one piece of work, such as taking a delivery request through booking trucks on shipper and warehouse sites and recording it in the dispatch sheet. A demo shows how it runs, a free connection test confirms Kitewell reaches your systems, and a one-month PoC measures the result against success criteria agreed up front, before you license it for production. See From evaluation to production for details.
Sources
- Japan Trucking Association: Japan’s trucking industry: current state and issues 2025 (in Japanese)
- Ministry of Health, Labour and Welfare: Working-hour standards for truck drivers (in Japanese)
- METI, MLIT, and MAFF: Survey of layered subcontracting in truck transport (April 27, 2023; in Japanese)
- LOGISTICS TODAY: Hacobu launches MOVO Adapter, an AI OCR for logistics (February 20, 2026; in Japanese)
- LOGISTICS TODAY: Hacobu supports freight rate management and invoice matching with AI (September 8, 2026; in Japanese)
- Yamato Transport B2 Cloud: Creating external data (in Japanese)
- Sagawa Express: e-Hiden III FAQ (in Japanese)
- Japan Post: Yu-Pack Print R (in Japanese)
- MLIT: Briefing on medium- to long-term plans under the Logistics Efficiency Act (September 2026; in Japanese)
- Hacobell: Hacobell and TSUNAGUTE link their truck booking systems (February 17, 2025; in Japanese)
- LOGISTICS TODAY: Hacobell links its truck booking system with its dispatch management (July 15, 2025; in Japanese)
- MLIT: The revised Motor Truck Transportation Business Act, in force April 1, 2025 (in Japanese) and Q&A on the revised act (as of March 31, 2026; in Japanese)
- MLIT: Recording of waiting and handling times in driver logs extended to all trucks (in Japanese)
- MLIT: The two acts on proper trucking (in Japanese)
- MLIT: New standard freight rates for trucks announced (March 22, 2024; in Japanese) and attachment (in Japanese)
- LNEWS: Hacobu collects actual-carrier details from a QR code on request forms (February 20, 2025; in Japanese)
- LNEWS: LOGITECH launches an app that helps build the actual-carrier ledger (February 4, 2026; in Japanese)
- MLIT: The Logistics Efficiency Act, for shippers and logistics companies (in Japanese)
- MLIT: Guide for specified warehouse operators under the Logistics Efficiency Act (February 2026; in Japanese)
Frequently asked questions
- May a tool operate shippers' and warehouses' truck booking systems?
- It depends on each system's terms of use and your agreements with the shipper or warehouse. The PoC checks each booking system's terms and automates only what they allow.
- Does automating the actual-carrier ledger or written transport terms make us compliant?
- Automation alone does not. Kitewell reads the notices and requests that arrive, matches them against the dispatch sheet, points out missing items, and drafts the records. Staff check what goes on record and decide whether it meets the law.
- How does this differ from the links between dispatch and booking systems?
- If your dispatch system and the truck booking system come from the same vendor, products exist that register bookings from dispatch automatically. Dedicated products also exist for actual-carrier ledgers and for reading delivery request forms. If they cover what you need, they are the quicker route. Kitewell suits entry that spans different shippers' and warehouses' systems, screens outside those links, and notices that subcontractors send by email.
Use cases for any industry
Read invoices into the accounting system
AI reads incoming invoices, checks them against purchase orders, and records them in the accounting system. Invoices whose amounts differ wait for approval.
Create invoices and send them by email
Invoices are filled into your template from an Excel billing list and emailed once a person approves. AI first points out amounts far from last month's.
Research a list of prospects
For an Excel list of hundreds of companies, each one's business, locations, and size are collected from its website into its row, with a priority for sales.
Find missing clock-ins
Collect yesterday's clock-ins from the attendance system and, once HR approves, ask employees with missing entries to fix them in Teams.
Take in emailed invoices and draft the entries
Find unread email with an invoice attached, have AI read the amount, and record a draft ledger entry. Uncertain entries wait for accounting to confirm.
Review SaaS accounts
A SaaS account review matches each service's users to current staff. Collect each console's users, match them, and disable leavers only after approval.
Partner registration that starts on approval
A kintone approval starts the workflow by webhook. It looks up the tax registration number, AI matches it to the request, and a match enters the sales system.
Collect KPIs from SaaS tools into a weekly report
Collect figures from advertising, sales, support, and other SaaS tools, and produce a weekly report with week-on-week comparisons and likely causes of change.
Check supplier invoice registration numbers
Check your supplier master's registration numbers monthly through the NTA's Web-API, and list suppliers that were revoked, lapsed, or differ in name.
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 the onboarding checks
- Which method connects each target system: API, file, database, or screen
- Whether Kitewell can work a system with no API through its screens, as a person would
- Whether AI relearns a step and processing continues when a screen changes
- Whether errors are handled as agreed: stop, notify, or retry
- Whether it runs in your environment, with the AI model you choose
- Whether processing time and AI usage cost fit daily operation
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.