Import hours reported by clients
AI reads hours clients email as Excel files, PDFs, or scans and checks them against contracts. Approved hours go to the dispatch system for payroll and billing.
- 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)
Hours for 12 workers (253 working days) from 5 clients, sent as Excel files, PDFs, a fax, CSVs, and time-card photos, read in 127 seconds and checked against each contract. The 3 days that need the client (Saturday work outside the contract, a break too short, an end time left blank) shown with the report's own words. After the coordinator approved, 9 workers' hours went into payroll and billing and the 3 questions went to the clients. Kitewell built the workflow 17 minutes after the request.
A real run on November 1, 2026, sped up. The system it works with was built for the demo.
The problem today
Under Japan's worker dispatch rules, each client reports every dispatched worker's days worked, start and end times, and breaks to the agency at least once a month. The report may come on paper, by fax, or by email, and every client uses its own format. Before payroll and billing close, staff read the reports and type them into the dispatch management system again.
The workflow in Kitewell
- Receive clients' emails with hours and save the attachmentsEmail
- AI reads each worker's days, start and end times, and breaks from Excel files, PDFs, and scanned imagesAI judgment
- Get each contract's working days, hours, and breaks from the dispatch management systemWeb
- Extract work outside the contract, missing entries, and low-confidence readingsAutomatic
- Staff check the extracted items, ask the client where needed, and approveApproval
- Convert approved hours to an import CSV (Shift_JIS) and load it into the dispatch management systemWeb
What AI does
Reads each worker's days and times from reports whose format differs by client. Low-confidence readings are shown to staff together with the matching part of the original document.
Where people decide
Staff decide how to treat work outside the contract or missing entries after checking with the client, and approve the hours before they go to payroll and billing.
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
- How reliably each client's format can be read
- Whether the output fits your dispatch management system's import screen and CSV format
- Whether the way discrepancies are checked with clients fits how you work
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
- What about clients whose hours come through their attendance system or a timesheet product?
- Collecting hours from a client's attendance system is covered in the use case on totaling client timesheets and watching overtime caps. Some products let workers enter hours in a web timesheet the agency provides, for the client's staff to approve online. Where such a route collects a client's hours, use it. This use case covers hours that arrive in each client's own format.
- 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
Write job postings for each job board
From a client's job request, AI drafts postings in each job board's format. Staff check them, then publish through each board's official route.
Track placement retention and fee refunds
Confirm with employers at set points up to six months after hire that placed people stayed. For early leavers, draft the refund and log the six-month count.
Enter records into a desktop accounting app
For each row of an Excel list, AI enters the record in a desktop app. A person approves before it is saved, and the slip number goes back into the row.
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.