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.

  • Manufacturing
  • Wholesale & consumer goods
  • Sales
  • Operations & orders
  • 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

Orders and applications are kept in an Excel list, entered one by one by hand into a customer's web ordering system or an internal web system, and each receipt number is copied back into the list. Even with RPA, a run that stops midway leaves nobody sure which rows went in, and checking for gaps and duplicates takes time.

The workflow in Kitewell

  1. Open the order list workbook and check which rows will run and which are left out (titles, subtotals, blank rows)Automatic
  2. For each row, fill in the unit price from the product master workbookAutomatic
  3. Sign in to the web system and enter the order from the rowWeb
  4. Read the receipt number from the confirmation screenWeb
  5. Write the receipt number and result back into each row of the workbookAutomatic
  6. A person checks the failed rows, fixes them, and reruns only those rowsHuman task

What AI does

Reads the web system's screen, enters the row, and submits it. An operation that worked is remembered and repeated the same way for the next rows; only when the screen changes does it relearn the operation.

Where people decide

Checks only the failed rows, fixes the cause, and reruns just those rows. A finished row never runs again.

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 entering orders and reading receipt numbers run reliably on the target web system
  • Whether the current Excel list is read as it is (title rows, merged headings, Japanese era dates)
  • Whether the time and AI model cost per row are acceptable
  • Whether processing only the rows added or changed each morning fits the work

How the onboarding runs

  1. Week 1Requirements and success criteria
  2. Weeks 2 to 3Build
  3. Week 4Verify on production screens
  4. 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.

See how the onboarding runs and its terms

Frequently asked questions

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.

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.