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.
The problem today
Orders and purchases are kept in Excel and copied by hand into a desktop sales or accounting application. The application has no API, and RPA scenarios stop every time its screens are updated.
The workflow in Kitewell
- Open the order or purchase workbook and run each rowAutomatic
- Open the application and create the record from the row, without savingDesktop
- Read the entered screen and check that the values matchAI judgment
- A person checks the before-save screenshot and approvesApproval
- Save the record and confirm it appears in the listDesktop
- Write the slip number and result back into each row of the workbookAutomatic
What AI does
Reads the screen and works the application's menus and fields the way a person does. An operation that worked is remembered and repeated the same way for the next rows; only when the screen changes does it read the screen again.
Where people decide
Checks the screen before the save and approves. If something is wrong, sends it back and only that row is redone.
What a PoC checks
- Whether AI reads and operates the target application's screens correctly
- Whether the time and AI model cost per record are acceptable
- Whether it runs unattended on a dedicated machine, or alongside a person on theirs
Discuss a PoC for this work
We check whether this workflow runs on your own work and screens.
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.
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.
Send shipping notices and reconcile receipts
Send shipping notices through each retailer's Web-EDI, then reconcile next morning's receipt data. AI suggests causes of quantity differences; staff confirm.