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.
- 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 2026, warehouse operators and shippers designated as specified businesses report measured driver waiting and handling times to the government every year. The records sit in different places at each site: truck booking systems, paper or Excel reception logs, and information from carriers. In every quarterly measurement period, staff gather the records and work out the times one delivery at a time.
The workflow in Kitewell
- Register the list of sites and periods to measure as a batch sheet and run each siteAutomatic
- Download arrival, check-in, and handling start and end records from the truck booking systemWeb
- Match reception logs and carriers' records to the booking records for each delivery and compute the timesAutomatic
- AI points out deliveries to exclude, such as missing records or waiting the carrier caused, with the reasoningAI judgment
- Logistics staff review the exclusions and results, and approveApproval
- Write each site's monthly averages back to its row in the listAutomatic
What AI does
Reads scanned reception logs and carriers' records and links them to the booking records delivery by delivery. Deliveries with no arrival record, or records suggesting the carrier caused the wait, are shown as candidates to exclude, with the reasoning.
Where people decide
Staff decide which deliveries to exclude and whether the figures to report are right. Staff also file the report with the government.
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 arrival and handling records can be pulled from each site's booking system and reception logs
- Whether each site's rules for counting waiting time and excluding waits can be settled
- Whether reception logs and carriers' records link to booking records delivery by delivery
- Whether the results can be checked against totals made by hand
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
- Can the totals go straight into the report to the government?
- Staff check and decide the figures to report. Kitewell collects the records, computes the times, and points out candidates to exclude. Staff also file the periodic report.
- Can't the truck booking system's records alone be totaled?
- If every delivery is recorded in one booking system and can be totaled there, that is the quicker route. Kitewell suits totaling across booking systems that differ by site, paper or Excel reception logs, and records from carriers.
- 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
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.
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.