Check damage claims for leased equipment
AI reads accident notices and repair estimates and lists missing documents and deadline risks. After staff approve, ask the customer for the rest and claim.
- 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
When leased equipment is damaged, accident notices, repair estimates, and photos arrive piecemeal from the customer by email and post. The documents required change with the kind of accident, such as fire, breakage, or theft, and with whether the item can be repaired, and if any one is missing, the insurance cannot be claimed. Staff look up the contract to check the insured period and whether it is a re-lease, then ask the customer for what is missing.
The workflow in Kitewell
- Pick up the accident report and attached documents from the customer's emailEmail
- AI reads the equipment, accident date, kind of accident, and whether it is repairable from the notice, repair estimate, and photosAI judgment
- Look up the contract period, whether it is a re-lease, and the insurance details in the core systemWeb
- AI lists the documents this kind of accident needs, what is missing, and the days since the accident, and drafts a requestAI judgment
- Staff review the list and the request, and approve asking for documents and claiming from the insurerApproval
- Email the customer asking for the missing documentsEmail
- For accidents with complete documents, enter and report the claim on the insurer's systemWeb
What AI does
Reads accident notices and repair estimates in varied formats, showing where in each document every value came from. Checks them against the documents required for the kind of accident and whether the item is repairable, and points out what is missing and anything that needs attention, such as a long time since the accident.
Where people decide
Staff decide whether the accident is covered and whether to claim from the insurer. Requests to customers and reports to the insurer go out only after staff approve them. Payment is decided by the insurer, as today.
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 document rules for each kind of accident can be set out for your main insurers
- How reliably repair estimates and accident notices can be read
- Whether accidents can be reported to the insurer through its 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
- Does AI decide whether the insurance pays?
- No. AI reads the documents, checks them against the contract period and the kind of accident, and shows what needs checking and what is missing. Staff decide whether to claim from the insurer, and the insurer decides on payment.
- 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
Read lease applications and prepare credit checks
AI reads lease applications from vendors into the core system, then gathers registry details and credit bureau scores into a memo for the credit reviewer.
Register leased equipment for property insurance
Each day, register newly accepted lease equipment on the insurer's agency system and record policy numbers. Staff hear only about items that failed.
Send lease expiry notices and collect replies
Find leases nearing expiry and draft notices asking each customer to re-lease or return. After sales approves, send them and arrange pickup and data erasure.
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.