Answer inquiries that arrive on paper
For inquiries on paper, AI reads the form, the workflow looks up accounts across systems, and AI drafts the answer. Staff identify the person and approve.
- 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
Inquiries from government agencies have largely moved online, but inquiries such as those from bar associations still arrive on paper. Staff search for accounts by the name and date of birth on the form, look up balances and transactions in separate systems, and write the answer. With many accounts to search and the same lookups repeated in several systems, it is heavy clerical work.
The workflow in Kitewell
- AI reads the sender, the subject's name, kana, date of birth, and address, and the questions from the scanned formAI judgment
- Search for the subject on the name-matching screen and get candidate accountsWeb
- Staff decide which candidate is the subject, including people with the same nameHuman task
- Get balances and transaction details for the questions askedWeb
- AI drafts the answer question by questionAI judgment
- Staff review what is disclosed and approve the answerApproval
What AI does
Reads the subject and questions from forms in varied formats, and drafts an answer to each question from what was collected.
Where people decide
Staff identify the subject and decide what to disclose and how much, including whether confidentiality means declining to answer.
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 subject and questions can be read from forms in varied formats
- Whether the name-matching, balance, and transaction screens can be operated from an internal computer
- Whether the identification rules and the record of each operation meet what audits require
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 this cover deposit inquiries from government agencies?
- Inquiries received through an online inquiry service are best answered through that service. This covers inquiries that arrive on paper, and the lookups across several systems that follow an inquiry.
- 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
Process customer due diligence replies
AI reads returned due diligence forms and shows where they differ from the customer record. Approved changes are entered, and follow-ups are listed.
Screen new business partners from public sources
For each new partner on an Excel list, AI searches news and public sources and flags anything to check. A person decides, and the result stays in the row.
Enter insurance claim documents
AI reads claim forms, certificates, and receipts, and the workflow looks up the policy and enters the claim. Staff see mismatches; an assessor decides payment.
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.