Real estate automation: disclosures, applications, move-outs

Disclosure research, rent guarantor applications, move-out settlements, and listing checks: work between sites and papers, automated with AI and human 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)

Common problems

  1. Disclosure research means looking up the land registry, zoning maps, and hazard maps on separate sites and copying the results by hand

  2. Tenancy applications are typed again into the screens of rent guarantors that the application system does not connect to

  3. Leaving a let property in an ad counts as bait advertising, and can draw a penalty fee

Every property and lease adds screens and paperwork

Japan has 133,727 licensed real estate businesses (end of March 2026). Registrations under the Rental Housing Management Act number 9,987 (July 31, 2025), and 71.2% of rental owners hand management to a company (fiscal 2023). Members of the All Japan Real Estate Association that are registered for rental management have about 2.4 employees on average (end of October 2025).

The law sets documents and reports for each kind of work. The Rental Housing Management Act requires registered managers to report to owners, at intervals of no more than a year, on how management was carried out and on tenant complaints and how they were handled. For sales, since January 1, 2025, brokers must also register the transaction status of exclusively listed properties on REINS, the brokers’ shared listing network.

Much of the work already has dedicated systems. Listings sync from property management systems to each portal, and application systems send tenancy applications to rent guarantors. Since May 18, 2022, documents such as the disclosure statement may be delivered electronically with the other party’s consent. What stays manual is where one system does not connect to the next.

Work Screens and systems used What stays manual
Listing ads Property management system, each portal Checking the status of properties other companies handle, and taking down ads for let properties
Tenancy applications and screening Application system, each rent guarantor’s screens Entering applications for guarantors the application system doesn’t connect to, and applications that arrive on paper or by fax
Rent receipts Internet banking, management system Matching deposits whose payer name differs from the tenant’s
Move-out and restoration Management system, move-out checklist and photos Comparing with move-in records, splitting costs, and writing the settlement
Reports to owners Management system Summarizing tenant complaints and how they were handled
Research for sale disclosures Land registry information service, municipal zoning and hazard maps Looking things up site by site and copying them into the statement
Exclusive listings and REINS REINS, CRM Tracking registration and status deadlines, and writing seller reports

Disclosure research spans the land registry and municipal sites

Article 35 of the Real Estate Brokerage Act requires a licensed real estate specialist (takken-shi) to explain important matters in writing before a contract is concluded. These include the type and content of registered rights, and restrictions under the City Planning Act, the Building Standards Act, and other laws. For sales, Article 3(1) of the Act’s enforcement order lists the legal provisions behind these restrictions in 64 items.

The sources are scattered. Registry information can be obtained as a PDF from the land registry information service run by the Minji Homu Kyokai (Civil Affairs Association). A request must identify the property by its lot number or building number, not its street address.

Since August 28, 2020, the property’s location on flood hazard maps made under the Flood Control Act has also been part of the explanation. The Ministry of Land, Infrastructure, Transport and Tourism (MLIT) says to use the latest available map, either as printed by the municipality or printed from the municipality’s website.

MLIT’s Real Estate Information Library overlays zoning, fire prevention districts, flood inundation areas, and more on a map, and offers a free API. Its terms, however, do not guarantee the content for procedures such as disclosure statements, and say it is meant for use as reference information. What goes into a disclosure statement still has to be confirmed against municipal maps and records.

In MLIT’s fiscal 2025 figures, Article 35 (explanation of important matters) is listed among the main violations behind supervisory action: 9 business suspensions and 9 instructions. Faster research does not change who is responsible for checking and explaining: the licensed specialist.

Rental paperwork runs from screening to move-out

The rent guarantee council of the Japan Property Management Association, citing a fiscal 2020 survey, puts the share of private rentals that use a rent guarantor at 80%. MLIT’s register lists 125 rent guarantee companies (September 30, 2026).

Connections between application systems and guarantors are growing. ITANDI says its application system connects to 95 guarantors in Japan (end of March 2026), and that the 1.13 million applications it handled in fiscal 2025 were about 40% of an estimated 2.72 million nationwide. Ierabu GROUP also announced a new link between its broker network’s web applications and a guarantor in September 2026. These connections are made system by system and guarantor by guarantor. Applications to guarantors that aren’t connected, and applications that arrive on paper or by fax, are copied by staff into the guarantor’s application screen or form.

After a tenant moves out comes the restoration settlement. Japan’s National Consumer Affairs Center received 14,711 consultations about restoration disputes in rental housing in fiscal 2025. In one, the tenant was told at the move-out inspection that nothing needed restoring, then later billed for repairing scratches on the floor.

MLIT’s guidelines recommend a checklist at move-in and move-out, and say that visual means such as taking photos are also important. The tenant’s share falls with age: for carpet, for example, the share declines along a line until the carpet counts as fully depreciated at 6 years. Writing a settlement means comparing the inspection record and photos with the move-in record and the lease’s special clauses, then splitting and calculating the cost item by item.

Ads for let properties count as bait advertising

The portal advertising council of the Shutoken Real Estate Fair Trade Council brings together At Home, CHINTAI, LIFULL, LY Corporation, and Recruit. Its members share information on violating listings and remove them. In fiscal 2025 they shared 1,332 violating listings nationwide, 332 of them bait ads for properties already under contract.

Of the 206 cases (counting each ad) where the Shutoken council took action or gave guidance in fiscal 2025, 190 involved internet ads. Of the 14 cases where it imposed a penalty fee, 13 involved rentals. In its September 2026 actions, the council imposed a penalty fee on a company over portal ads for 8 rental apartments. Among the reasons, let properties stayed advertised for at least a month, the longest for three months or more.

The council notes that most violating listings are properties handled by other companies, and says brokers need to check transaction status regularly and avoid posting excessive numbers of ads. A company’s own listings can be taken down from its property management system. For other companies’ properties, the managing company’s status has to be checked again and again. Comparing listings with your own register is covered in “Check property listings across portals.”

What to check before automating

  • Each site’s rules: check whether REINS, listing portals, broker networks, and guarantors’ screens allow automated operation under their rules, terms, and contracts. The Chubu REINS guidelines state that the operator does not permit any tool that accesses REINS. “Check the terms before you automate a website” explains how to check
  • Registry requests: the land registry information service charges for each request. Its terms say it may restrict use, for example when lot or building number searches are excessive. Have staff approve each request before it is made
  • Where information comes from: data such as the Real Estate Information Library is reference information. Confirm what goes into a disclosure statement against municipal maps and records
  • Who decides: staff and licensed specialists decide which guarantor to apply to, what the disclosure statement says, and how restoration costs are split
  • Applicants’ personal data: decide first which AI models may see details such as employer and income
  • Whether a dedicated product is enough: work that portal syncing, application-to-guarantor connections, or electronic contracts already handle should stay there

What Kitewell does

Descarty’s Kitewell is integration and automation middleware that connects systems through APIs, files, databases, and screens.

  • Operates screens with no API: AI reads and operates web systems and desktop apps with no API, such as guarantors’ application screens, the land registry information service, and municipal zoning maps. Operations that worked are remembered and repeated the same way on later runs
  • Keeps going when screens change: when a remembered operation no longer fits the screen, AI reads the screen again, does the step, and remembers the new operation. If that fails, the run stops, and AI looks into the cause and suggests the fix
  • Reads documents and photos: AI reads application forms, registry PDFs, and move-out photos, and extracting fields or drafting becomes a step in the workflow. You choose the model for each step, including in-house and local models
  • Starts from applications sent by email: Gmail, Microsoft 365, or IMAP mailboxes are checked at set intervals, and attachments are saved to start the work
  • Passwords stay out of AI’s hands: passwords for guarantors’ screens and the registry service are referenced by name and typed in without showing the value to the AI. When a one-time password is required, the run pauses until staff enter it
  • People check where it matters: approval can be set on any step, such as before a registry request, before sending to a guarantor, or before a settlement is finalized. Requests reach Slack, Microsoft Teams, and email, and sending one back restarts the run from the step you choose
  • Every operation on record: each run keeps its logs, screenshots, and approval decisions, so you can later see what was looked up on which site and what was entered

You can start from one piece of work, such as taking a tenancy application through applying to the rent guarantor and passing on the result. A demo shows how it runs, a free connection test confirms Kitewell reaches your systems, and a one-month PoC measures the result against success criteria agreed up front, before you license it for production. See From evaluation to production for details.

Sources

Frequently asked questions

May a tool operate REINS, listing portals, or rent guarantors' screens?
It depends on each site's rules and terms, and on your contracts with the guarantors. The REINS usage guidelines published by the Chubu and Kinki operators do not allow tools to access REINS. The PoC checks each site and automates only what its rules allow.
Does AI write the disclosure statement?
No. Japan's Real Estate Brokerage Act requires a licensed real estate specialist (takken-shi) to give the explanation of important matters. AI drafts a summary of what was researched online. The licensed specialist checks the draft, confirms details at the municipal office, and gives the explanation.
How does this differ from property management systems and application platforms?
Dedicated products already sync listings to portals, connect application systems to rent guarantors, and handle electronic contracts. Work they cover should stay with them. Kitewell suits the work left between products, such as applications to guarantors that aren't connected, or research across the land registry and municipal sites, automated to follow your company's own steps.

Use cases for any industry

  • All industries
  • Accounting & finance

Read invoices into the accounting system

AI reads incoming invoices, checks them against purchase orders, and records them in the accounting system. Invoices whose amounts differ wait for approval.

  • All industries
  • Accounting & finance

Create invoices and send them by email

Invoices are filled into your template from an Excel billing list and emailed once a person approves. AI first points out amounts far from last month's.

  • All industries
  • Sales

Research a list of prospects

For an Excel list of hundreds of companies, each one's business, locations, and size are collected from its website into its row, with a priority for sales.

  • All industries
  • HR & payroll

Find missing clock-ins

Collect yesterday's clock-ins from the attendance system and, once HR approves, ask employees with missing entries to fix them in Teams.

  • All industries
  • Accounting & finance

Take in emailed invoices and draft the entries

Find unread email with an invoice attached, have AI read the amount, and record a draft ledger entry. Uncertain entries wait for accounting to confirm.

  • All industries
  • IT

Review SaaS accounts

A SaaS account review matches each service's users to current staff. Collect each console's users, match them, and disable leavers only after approval.

  • All industries
  • Accounting & finance

Partner registration that starts on approval

A kintone approval starts the workflow by webhook. It looks up the tax registration number, AI matches it to the request, and a match enters the sales system.

  • All industries
  • Planning & marketing

Collect KPIs from SaaS tools into a weekly report

Collect figures from advertising, sales, support, and other SaaS tools, and produce a weekly report with week-on-week comparisons and likely causes of change.

  • All industries
  • Accounting & finance

Check supplier invoice registration numbers

Check your supplier master's registration numbers monthly through the NTA's Web-API, and list suppliers that were revoked, lapsed, or differ in name.

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 the onboarding checks

  • Which method connects each target system: API, file, database, or screen
  • Whether Kitewell can work a system with no API through its screens, as a person would
  • Whether AI relearns a step and processing continues when a screen changes
  • Whether errors are handled as agreed: stop, notify, or retry
  • Whether it runs in your environment, with the AI model you choose
  • Whether processing time and AI usage cost fit daily operation

How the onboarding runs

  1. Week 1Requirements and success criteria
  2. Weeks 2 to 3Build
  3. Week 4Verify on production screens
  4. 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.

See how the onboarding runs and its terms