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.
- 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
Insurance claims arrive as paper documents in many formats, typed or handwritten: claim forms, medical certificates, and receipts. Staff read them, look up the policy, enter the claim in the claims assessment system, and check it. Entry and checking take up time that assessment itself needs.
The workflow in Kitewell
- AI reads admission dates, procedure names, amounts, and other items from the scanned claim form, certificate, and receiptsAI judgment
- Look up the policy the claim is for on the policy management screenWeb
- AI points out mismatches between documents and against the policyAI judgment
- Staff check low-confidence items and mismatchesHuman task
- Enter the claim in the claims assessment system and save the screenWeb
- An assessor decides on paymentApproval
What AI does
Reads items from documents in varied formats and shows where in the document each value came from. Points out mismatches such as hospital stays that differ from receipt dates.
Where people decide
An assessor decides whether to pay and how much. Medical questions go to doctors and others under your procedures. AI never decides on payment.
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
- How reliably each kind of document can be read
- Which AI model handles sensitive information such as medical history, and where it runs (in-house or in a closed network)
- Whether the policy management and claims assessment systems can be operated through their screens
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
- May the contents of medical certificates be sent to an outside AI?
- In Japan, sensitive information such as medical history may be handled only with the customer's consent and within what the work requires. Using an outside AI service means confirming, among other things, that the data entered is not used for training. Kitewell can also use AI models hosted in-house or in a closed network.
- 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.
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.
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.
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.