Settle move-out restoration costs
Compare move-out checklists and photos with move-in records and lease clauses, and propose each item's cost split under national guidelines. Staff decide.
- 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 National Consumer Affairs Center received 14,711 consultations about restoration disputes in rental housing in fiscal 2025. After the move-out inspection, staff compare the checklist and photos with the move-in record and the lease's special clauses, split each item between tenant and landlord, account for the item's age, and write the settlement. Tenants may also ask for a breakdown of the costs and the reasons behind them.
The workflow in Kitewell
- Get the lease's special clauses, move-in date, and move-in records and photos from the management systemWeb
- AI compares the move-out checklist and photos with the move-in record and lists the damageAI judgment
- AI proposes, item by item, who bears the cost and the tenant's share by age, following the guidelines and the lease's clausesAI judgment
- Staff review and approve the cost split and amountsApproval
- Enter the approved settlement in the management system's settlement screenWeb
- Staff send the settlement to the tenant and answer questionsHuman task
What AI does
Compares the checklist and photos with the move-in record and lists the damage. Following the national guidelines from the land ministry (MLIT) and the lease's special clauses, it proposes whether the tenant or the landlord bears each cost and the tenant's share by age, with its reasons. Items it is unsure of are marked and passed to staff.
Where people decide
Staff decide the cost split and amounts. For hard calls, such as how a special clause applies, staff consult the landlord.
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 lease's special clauses and move-in records can be retrieved from your management system
- Whether damage can be read from inspection photos and checklists
- Whether the proposed cost splits match your internal standards and agreements with landlords
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
- Does AI decide what the tenant pays?
- No. AI proposes a cost split and its reasons, following the guidelines and the lease's clauses. Staff decide the split and amounts, and each approval is recorded.
- What if there are no move-in records or photos?
- Where no move-in record exists, AI notes that it cannot compare and passes the item to staff. MLIT's guidelines recommend a checklist at both move-in and move-out, along with means such as photos.
- 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
Check property listings across portals
Your Excel property register is compared with each listing portal, and any difference in rent or availability goes into the row and to the person responsible.
Submit tenancy applications to rent guarantors
AI reads tenancy applications sent by email and enters them in the screens of rent guarantors your application system doesn't reach. Staff confirm first.
Reconcile rent payments
Match internet banking deposits against the tenant register. When the payer name differs from the tenant's, AI suggests the matching lease.
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.