WorkWithPlus's AI intent-based navigation works by taking advantage of all the information we have from the KB (semantic model) to give the best possible context to GeneXus Enterprise AI (which will transfer it to the desired LLM). Based on what the LLM returns, the best screen is loaded that responds to the user's intentions.

A typical flow is:

1. Users will specify the expected output, for example, accounts with a balance of approximately $500,000 USD.
    
2. The system will process this request and send it, along with a set of metadata called the "semantic model," to GeneXus Enterprise AI (is a new product of GeneXus that allows us to interact with LLMs (Language Model Models) like Chat GPT, Bard, etc.). It will return the user's intention in response.
    
3. This response will be processed and will display the desired screen, with the filters or instantiated data as needed.

WorkWithPlus will automatically generate all of this behaviour.

The semantic model

When we talk about a "semantic model", we're referring to the information from the KB that we already have. This includes:

• entities names
• domains
• attribute names
• applied filters
• descriptions of those filters, etc.

This information is sent to GeneXus Enterprise AI, to provide context for the LLM and help ensure the response to the final user is as accurate as possible.

Important:

This feature is a part of WorkWithPlus for Web. Any WorkWithPlus user with an active license can use it.

The development team will only have to pay an extra amount for the using of GeneXus Enterprise AI.

GeneXus Enterprise AI + WorkWithPlus give our community a free amount of requests when they are in the development and testing process. At the moment of deploying an application to production, you should buy and use your own credentials of GeneXus Enterprise AI (contact hello@workwithplus.com for more details).