Review molds held at suppliers
Find the last order for each mold on your ledger, list long-idle molds, and have AI draft notices once buyers decide to return, scrap, or pay for storage.
- 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
After a part's mass production ends or its orders drop, the mold often stays at the supplier's plant. Which molds have gone unused, and for how long, only shows up by matching the mold ledger against purchase records one mold at a time. Under Japan's amended Subcontract Act, in force since January 2026, making a supplier store molds without paying for storage while no parts are ordered counts as an unjust request for economic benefits.
The workflow in Kitewell
- Register the mold ledger (Excel) as a batch sheet and confirm where each mold is stored and which part numbers it makesAutomatic
- Look up the last order date and planned orders for each part number on the purchasing system's screensWeb
- AI lists molds with no orders for a year or more, or none planned for the coming year, checked against the storage fee and disposal terms in your agreements with suppliersAI judgment
- Buyers decide for each mold whether to take it back, scrap it, or keep it stored and pay for storageHuman task
- AI drafts a notice to each supplier proposing to discuss the moldsAI judgment
- The purchasing manager reviews the list and drafts and approvesApproval
- Send the notices and write the date sent and the decision into each row of the mold ledgerEmail
What AI does
Reads each mold's storage fee and disposal terms from agreements and past correspondence, and lists the molds that need discussing, with reasons. Drafts each supplier's notice from the decisions made.
Where people decide
Buyers decide whether to take back, scrap, or keep each mold and pay for storage, and the purchasing manager approves. Buyers hold the discussions with suppliers.
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 molds on the ledger can be linked to part numbers in the purchasing system (old part numbers, one mold making several parts)
- Whether order records per part number can be read reliably from the purchasing system's screens
- Whether the criteria for molds that need discussing (time without orders, end of mass production) match your company's view
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
- How long without orders before a mold needs discussing?
- It depends on the case. The guide to the amended act by the Japan Fair Trade Commission and the SME Agency gives, as examples, no orders for products made with the mold for a year or more, and being unable to give a specific order date within the coming year. The purchasing manager sets the criteria, and the PoC tests them against your ledger.
- May we ask suppliers to take stock of our molds?
- Stocktaking costs suppliers money too. In July 2026, the Japan Fair Trade Commission issued a recommendation to a construction crane maker that had made suppliers store molds and take stock of them without bearing the costs. Whether to ask for stocktaking, and who pays for it, is for the purchasing manager to decide. This automation starts by matching your own ledger with your purchase records.
- 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
Answer customers' chemical content surveys
Read part numbers and due dates from chemSHERPA survey requests in customer portals, build answer files from your data, and submit them after QA approves.
Enter an Excel list into a web system
For each row of an Excel list of orders, AI enters it into a web system and writes the receipt number back into the row. Only failed rows are redone.
Enter records into a desktop accounting app
For each row of an Excel list, AI enters the record in a desktop app. A person approves before it is saved, and the slip number goes back into 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.