Match erasure certificates to returned equipment
AI reads data erasure certificates from dealers and disposal contractors and matches them to returned units by serial number. Staff check only the exceptions.
- 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
Most returned PCs and servers are sold to used-equipment dealers. When a contractor erases the data, it sends a certificate or work report, in a format that differs by contractor. Staff compare the serial numbers on each certificate with the list of returned units one by one, and chase contractors for units with no certificate. Under government leases, the certificate may also have to be submitted to the customer.
The workflow in Kitewell
- Pick up certificates and work reports from contractors' emailEmail
- AI reads the serial number, date of work, and erasure method from each certificateAI judgment
- Register the list of returned units exported from the core system as a batch sheetAutomatic
- Match units and certificates by serial number, and list units with no certificate or a mismatched numberAutomatic
- Staff review the list and approve queries and requests for rework to contractorsApproval
- Attach matched certificates to the contracts in the core systemWeb
What AI does
Reads the serial number, date of work, and erasure method from certificates in each contractor's own format, showing where on the certificate each value came from. Where a number may have been misread, it shows units with similar numbers alongside.
Where people decide
Staff review the matching results and decide on queries and rework requests to contractors. Whether a certificate goes to the customer is decided by staff after checking the contract or specifications. Checking how contractors run their work stays with staff, 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 serial numbers are read correctly from each contractor's certificate format
- Whether serial numbers of returned units can be exported from the core system
- How to tell which contracts, such as government leases, require certificates to be submitted
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 matching certificates fulfil the responsibility for data erasure?
- No. Matching confirms only that contractors' reports correspond to the units. According to the Japan Leasing Association, under leases with companies the customer is responsible for erasing data, while government leases differ contract by contract. How contractors run their work is checked separately.
- 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.