Check agreement wages against new benchmarks
Load the benchmark wages the labor ministry sets each year and compare them with agreement wages and each worker's pay by job, region, and experience.
- 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
Japan's equal pay rules let staffing agencies set dispatched workers' pay through a labor-management agreement, but agreement wages must be at or above the benchmark wage for the same kind of work in the same area. The ministry revises benchmark wages every year, and agreement wages must be checked against the new figures even while an agreement is still in force. Between the notice in late August and the start of the new figures in April, staff map each job and client region to the ministry's tables, work out the amount for each experience level, and compare it with each worker's hourly pay.
The workflow in Kitewell
- Check the ministry's page weekly and download the new benchmark wage tables (Excel) when they appearWeb
- AI compares the jobs in the agreement with the ministry's job categories and points out renamed or reclassified onesAI judgment
- Get each covered worker's job, client location, years of experience, and hourly pay from the dispatch management systemWeb
- Calculate the benchmark by job, region, and experience, and compare it with agreement wages and actual payAutomatic
- AI summarizes combinations below or close to the benchmark and drafts material for the labor-management talksAI judgment
- Staff check the results and bring a revised agreement or a confirmation note to the labor-management talksHuman task
What AI does
Checks how the agreement's jobs map to the ministry's categories and points out renamed or reclassified ones. From the comparison, it summarizes combinations that fall below or close to the benchmark and drafts material for the talks.
Where people decide
Staff confirm that job mapping, the regional index, and experience levels follow the agreement. Agreement wages are decided through talks between the employer and the union or worker representative.
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 each covered worker's job, client location, experience, and hourly pay can be retrieved from your dispatch management system
- Whether job mapping, the regional index (by prefecture or by public employment office area), and experience levels match your agreement
- Whether the results match those of the ministry's wage comparison tool
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
- How does this differ from the ministry's wage comparison tool?
- The wage comparison tool is an Excel tool the Ministry of Health, Labour and Welfare publishes for checking that covered workers' wages are at or above the benchmark. If you only need to check agreement wages, use it first. This approach suits gathering each worker's job, work location, and pay from your dispatch management system and checking them together with agreement wages in one pass. The PoC checks that the results match the tool's.
- If the benchmark falls, may agreement wages be lowered?
- The ministry says that even when benchmark wages fall, the employer and workers should discuss fair treatment fully, starting from the wages in the current agreement. Lowering pay can be an adverse change to working conditions, which in principle requires both sides to agree. This check only gathers the material for those talks.
- 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
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.
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.
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.
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.