Take in orders from retailers' Web-EDI
Each morning, sign in to each retailer's Web-EDI, download orders, and convert them for the core system. Staff check unusual quantities before import.
- 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)
Kitewell's browser signed in to 3 retailers' Web-EDI, collected 24 order lines, and checked them against past orders in 19 seconds. AI flagged the 3 unusual lines, ten times the usual quantity, a tenth of it, and an item the store had never ordered, with its reasons. A person approved; 21 lines were imported and 3 held to confirm with the retailer. Kitewell built the workflow 8 minutes after the request.
A real run on October 29, 2026, sped up. The system it works with was built for the demo.
The problem today
With retailers not connected by the industry EDI standard, orders come through each retailer's own Web-EDI. Every morning, order staff sign in to each Web-EDI, all built differently, download orders, convert them, and import them into the core system. RPA automated this, but robots stop whenever a Web-EDI screen changes, and some days orders miss the cut-off.
In depth: Collecting orders from each customer's Web-EDI in one list
The workflow in Kitewell
- Sign in to each retailer's Web-EDI and download ordersWeb
- Convert each retailer's format into the core system's import formatAutomatic
- AI flags orders whose quantities or items differ sharply from past ordersAI judgment
- Order staff confirm flagged orders with the retailer and approve the importApproval
- Import into the core system and post orders that failed to TeamsAutomatic
What AI does
Compares with past orders by retailer and item to find quantities with suspect digits or items never ordered before, and explains why.
Where people decide
Order staff confirm only unusual orders with the retailer before approving the import.
This work, run in Kitewell
On October 19, 2026, Kitewell ran the part that collects order CSVs from three stand-in ordering sites and merges them into one list. The sites were built for the test.
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 each Web-EDI handles sign-in security such as one-time passwords or client certificates
- Whether each Web-EDI's terms allow automated screen operation
- Whether conversion and import finish reliably before the order cut-off
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 it work with Web-EDI that uses one-time codes or client certificates?
- With a one-time code, the run stops and asks for it; once someone enters the code, the browser carries on from the page it left open. With a client certificate, it runs on a PC that holds the certificate. Sites that turn automation away with image challenges or similar are not automated.
- 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
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.
Read Excel purchase orders from email and enter them
AI reads Excel purchase orders in each customer's own layout, checks them against the product master, and enters them. A person checks orders that do not match.
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.