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.

¥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.

Match subcontractor progress billing to orders

Progress billing charges for work as it is done. AI matches subcontractor invoices to orders and assessed progress; site managers check differences first.

Try free for 14 days Book a 30-minute demo

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)

20 progress invoices from 16 subcontractors, each in its own format, read and matched against the orders and assessed progress in 33 seconds; the 5 that differ (progress over the assessment, an amount off, a line not on the order) were shown with the invoice's own words, and the 15 that match went into the payment data once a person approved. Kitewell built the workflow 10 minutes after the request.

A real run on October 29, 2026, sped up. The system it works with was built for the demo.

The problem today

Every month, invoices in many different formats arrive from subcontractors, and accounting matches each against the order and the assessed progress for that project. Differences go to the site manager, but finding what differs takes time, and the work piles up at month end.

The workflow in Kitewell

Add invoices from subcontractors to a batch sheetAutomatic
AI reads project, amount, progress percentage, and line itemsAI judgment
Match against order amounts and assessed progress, and extract differencesAutomatic
The site manager reviews invoices with differences and approvesApproval
Export data for payment processingAutomatic

What AI does

Reads project, amount, progress, and line items from invoices in any format, quoting where each came from, and shows which item differs from the order or assessment.

Where people decide

Invoices with differences go to payment only after the site manager reviews them.

Features used

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 the needed fields are read correctly from your main subcontractors' invoice formats
Where order and progress assessment data come from
Whether difference rules match your payment procedure

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.

Book a 30-minute demo Ask about onboarding

See how the onboarding runs and its terms

Frequently asked questions

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.

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.