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.
- 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
About 80% of private rentals in Japan use a rent guarantor, so most tenancy applications go through a guarantor's screening. When the application system connects to the guarantor, nothing needs retyping, but those connections are made system by system and guarantor by guarantor. For guarantors that aren't connected, and for applications that arrive on paper, by fax, or as PDFs, staff read the form and type the applicant's name, employer, income, emergency contact, property, and rent into the guarantor's screen again.
The workflow in Kitewell
- Check for emails with application forms attached, and save the attachmentsEmail
- AI reads the applicant, employer, income, emergency contact, property, and rent from the formAI judgment
- Staff confirm which guarantor to apply to and what was readApproval
- Sign in to the guarantor's application screen, enter the application, and submit itWeb
- Record the reference number and the screens entered for each applicationAutomatic
- Staff check the screening result and tell the landlord and the leasing agentHuman task
What AI does
Reads the fields screening needs from forms and fax images in varied formats, and arranges them to match each guarantor's input fields. Fields it cannot read, or that conflict within the form, are shown to staff.
Where people decide
Staff confirm which guarantor to apply to and that what was read is right. The landlord and staff decide on the tenancy based on the screening result.
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 guarantor's terms and your contract allow automated operation of its application screen
- Whether the needed fields can be read from forms and fax images in varied formats
- Whether each guarantor's sign-in works, including IDs, passwords, and one-time passwords
- Which AI models may handle applicants' personal data, and what applicants have consented to
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
- Is this needed if our application system already connects to the guarantor?
- Applications to connected guarantors are best sent through the application system. ITANDI, for example, says its application system connects to 95 guarantors in Japan (end of March 2026). This covers applications to guarantors that aren't connected, and applications that arrive on paper, by fax, or as PDFs.
- May applicants' employer and income be passed to AI?
- It depends on your internal rules and what applicants have consented to. You choose the AI model for each reading step, including in-house and local models. The PoC settles which information each model may handle.
- 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.
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.
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.