Research properties for disclosure statements
Get registry PDFs, check municipal zoning and hazard maps, and draft the disclosure statement with its sources kept. A licensed specialist checks and explains.
- 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
Before a sale in Japan, a licensed real estate specialist (takken-shi) must explain registered rights, restrictions under the City Planning Act, the Building Standards Act, and other laws, the property's location on flood hazard maps, and more. Registry records must be requested by lot or building number, and each municipality publishes zoning and hazard maps on its own site. For every property, staff search several sites, save the screens, and copy the results into the statement.
The workflow in Kitewell
- AI reads the address, lot number, and building number from the listing request or property registerAI judgment
- Staff confirm which registry records to request (each request is charged)Approval
- Sign in to the land registry information service and download full-record PDFs for the land and buildingWeb
- AI reads the owner, mortgages, and other rights from the registry PDFsAI judgment
- Look up zoning, building coverage and floor area ratios, flood zones, and more on municipal zoning and hazard maps, and save the screensWeb
- AI drafts the relevant sections of the disclosure statement from the findings and source screensAI judgment
- A licensed specialist checks the draft and looks into items that need confirming at the municipal officeHuman task
What AI does
Reads the address and lot number from the documents, and the owner, mortgages, and other rights from the registry PDFs. It drafts the relevant sections of the disclosure statement with the source screens attached. Items the sites alone cannot settle are left marked as unconfirmed.
Where people decide
Staff approve each registry request. A licensed specialist checks the draft, confirms details at the municipal office, and gives the explanation.
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 number and frequency of registry requests suit the service's terms
- Whether the needed items can be read from your target municipalities' zoning and hazard map screens
- Whether the type and content of rights are read correctly from registry PDFs
- Whether the draft fits the disclosure statement format you use
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 write the disclosure statement?
- No. Japan's Real Estate Brokerage Act requires a licensed real estate specialist to give the explanation of important matters. AI drafts a summary of what was researched online. The licensed specialist checks it, confirms details at the municipal office, and gives the explanation.
- Isn't the Real Estate Information Library's API enough?
- It is useful for broad checks such as zoning. Its terms, however, do not guarantee the content for procedures such as disclosure statements, and say it is meant as reference information. What goes into a disclosure statement is confirmed against municipal maps and records.
- May the land registry information service be used automatically?
- Its terms say it may restrict use, for example when lot or building number searches are excessive. Each request is made only after staff approve it, and the PoC checks that the number and frequency of requests are appropriate.
- 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 exclusive listing and REINS deadlines
Track REINS registration, certificate delivery, seller reports, and status-change deadlines for each exclusive listing. AI drafts reports; agents operate REINS.
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.
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.