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.
- 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
Electronics and automotive customers send surveys on the chemical substances in each part. Most use chemSHERPA, Japan's common format for passing chemical content information along the supply chain, but some customers send requests by email and others through their procurement portals, and some also ask for a compliance guarantee or their own forms. Staff collect the requests, find each part's data, load the customer's request data to build an answer file, and submit it the way each customer asks. Each time substances are added to the regulated lists, surveys on the same parts come again.
The workflow in Kitewell
- Open new survey requests in the customer portal and download the request letter and request data (.shai file)Web
- AI reads the part numbers, due date, and documents required (chemSHERPA, guarantee, the customer's own forms) from the request letterAI judgment
- Look up each part's answer data in your internal list (Excel) and flag parts with noneAutomatic
- For parts with no data, staff survey suppliers or confirm the compositionHuman task
- Load the customer's request data into the chemSHERPA data creation tool and output the answer fileDesktop
- QA staff review the answer files and guarantees and approveApproval
- Attach each part's file in the customer portal, submit, and save the confirmation screenWeb
What AI does
Reads part numbers, due dates, and required documents from request letters that each customer writes differently. Before submission, it checks that no file is attached to the wrong line or mixed up with another type of document, and shows staff anything that looks wrong.
Where people decide
Staff decide what each part contains and what to answer, based on composition data. QA staff check documents the company stands behind, such as guarantees, before they are submitted.
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 getting requests and attaching answers run reliably in your main customers' portals
- Whether each customer portal's terms of use allow automated operation
- Whether loading request data and outputting answer files in the data creation tool run reliably
- Whether your answer data can be found reliably by part number (storage locations and file naming)
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
- Will CMP make this unnecessary?
- Once a customer and its suppliers move to CMP, the industry's new platform for chemical information, that trade can pass information as data to the parties each company designates. The CMP Consortium says CMP and chemSHERPA will run side by side, complementing each other, for the time being. This automation is for requests that still come through customer portals or email.
- Does it work for customers who send requests by email?
- Yes. The workflow starts with a step that checks the inbox at set intervals and saves attachments, and answers go back by email. The reply text and sender follow your company's rules.
- 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
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.
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.