With GAPTEQ Assist, defined data can be read from tables and analyzed by the AI for trends, peak values, etc. An interpretation can be provided directly on request.
Note! A demo example “Product management furniture store Müller” is used to describe how table contents can be read and analyzed.
Initial situation
In this GAPTEQ application of a furniture store, all product information (name, short description, detailed product description, dimensions, supplier, ...) is recorded in a form. Each product belongs to a product group and is initially recorded with a product name and a brief description.
Aim
Now, with the help of GAPTEQ Assist, the table (or a data record of a product group) “Sales per product group” is to be read out according to the desired content and at the same time analyzed according to specific questions.
1. Place AI chat component & define triggering event
- Drag the AI chat component onto the page (see screenshot below right).
Tip! The AI chat component can be replaced by the “invisible” AI Processor component.
By clicking on a button (“Sales analysis”), a selected data record from the “Sales per product group” table should now be analyzed.
- At the “clicked” event of the button - referenced to the AI chat component - store the action “ask(question, showQuestion)”.
- A string expression with the corresponding prompt to the AI is stored for the “question” parameter. (“In which three months were the highest sales achieved for the product category, and which month had the lowest sales”)
- The command “navigation.messageBox(message)” can be used to output the result in a message box. The content is the last response from the AI.
2. Define data sources for prompt
- The “selected.row” commands on the respective revenue form fields give the AI the corresponding data source, which in this case is to be analyzed or compared with each other.
