Check and track dispatch period limits
Site limits come from the client's notice; per-person limits run from the worker's start in the unit. As either nears, AI drafts a check that staff 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)
24 active contracts checked in 6 seconds: 6 exempt ones set aside, and for the 6 within three months of a limit or at a site with no notified limit date, a confirmation to the client and a notice to the worker drafted. A person approved and they were sent. Kitewell built the workflow 5 minutes after the request.
A real run on October 28, 2026, sped up. The system it works with was built for the demo.
The problem today
Under Japan's worker dispatch law, dispatch to the same client site is generally limited to 3 years, and the same worker to the same unit to 3 years as well. Some dispatches are exempt from the limits, such as workers on indefinite contracts, workers aged 60 or over, and cover for staff on parental leave. Deadlines and exemptions differ by client and by worker, and tracking them in spreadsheets lets some slip.
The workflow in Kitewell
- Get dispatch contracts and the limit dates clients notified from the core systemAutomatic
- Leave out exempt dispatches, calculate per-site and per-person deadlines, and extract contracts nearing themAutomatic
- AI drafts a confirmation to the client and a notice to the workerAI judgment
- Staff check the drafts and approve sendingApproval
- Record what was sent and replied, and alert staff months aheadAutomatic
What AI does
Drafts confirmations to clients and notices to workers that fit each contract's situation.
Where people decide
Staff decide how each deadline is handled and what clients and workers are told, and check before sending.
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 contracts and limit dates can be retrieved from your core system
- Whether deadline calculations match your practice and reading of the law
- Whether the messages and how they are sent fit 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
- Do the deadline calculations follow the law?
- The PoC checks that the calculations match your practice and your reading of the law. Staff decide how each deadline is handled and what clients and workers are told, and check before sending.
- 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 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.
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.
Total client timesheets and watch overtime caps
Collect dispatched workers' hours from each client's attendance system and find people near the overtime cap. AI drafts the note to the client; staff check it.
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.