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.

  • Wholesale & consumer goods
  • Manufacturing
  • 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

Customers send purchase orders as Excel attachments, each in its own layout. Staff open them one by one, read the part numbers and quantities, and type them into the sales system. RPA needs a scenario per layout, rebuilt every time a customer is added.

The workflow in Kitewell

  1. Find emails with purchase orders in the inbox and save the attached workbooksEmail
  2. AI reads the customer, part numbers, quantities, and delivery dates from each layoutAI judgment
  3. Check part numbers and prices against the product master workbook and flag orders that do not matchAutomatic
  4. A person checks the orders that do not match and decides whether to enter themApproval
  5. Enter the order on the sales system's screenWeb
  6. Reply to the customer with the order number and move the email to processedEmail

What AI does

Finds which cell holds each part number and quantity even when cell positions and headings differ by customer, and keeps each value with the cell it came from.

Where people decide

Checks only the orders that do not match the master and decides whether to ask the customer or enter the order.

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 part numbers, quantities, and delivery dates are read correctly from your main customers' layouts
  • Whether the matching rules against the product master (old part numbers, different units) fit the work
  • Whether the reply's wording and sender follow your company's rules

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.