AI Model to Map Converter FAQ

You can create your procedure using a BPMN Process Model as the input. When creating a new process, you can select from the existing Process Models you have access to and then further select if you want to use the full model or part of it. Then, using Generative AI, the model is converted to a procedure, creating the first draft of the process including activities, tasks, and role assignments where possible. You can then choose to discard the outcome, regenerate, modify their selection, or accept the procedure as the first draft of their process.

You must have Process Models functionality available and enabled in your tenant to use this feature. Additionally, you need to have at least one Process Model created to select as an input.

All the information that is available inside the Process Model (BPMN).

Yes. Once you select which model you want to use as a basis, you can select to either use all or some of the containing elements.

If the generated procedure does not meet the expected outcome, there are a few options:

• Regenerate: Simply regenerating might provide a different outcome due to the nature of Generative AI.
• Modify the selection: You can go back and select a different part of the model or another model as your input.
• Edit manually: You can save the draft and start working on it manually in the usual Process Editing environment.

No, this functionality only applies to new procedures that have no activities added to them.

By utilizing the power of OpenAI, the feature is designed to be versatile and can draft a wide range of business procedures, from standard operating procedures to business process workflows. The quality of the output depends heavily on the quality of the information in the Process Model.

You can submit functionality ideas through the Nintex Ideas portal or reach out to us via support@nintex.com.

Like any feature using AI, it has limitations. It may not fully understand complex or ambiguous requirements, and the quality of the draft depends on the input provided. Currently, only BPMN models available within Process Manager can be used, and there is no prompt history tracking.

No. This feature is currently only used to generate procedures, not process models.

The information from Process Model in a prompt, which is then passed to a private MS OpenAI instance hosted on the Nintex Azure Infrastructure. Using the prompt this service will generate a suggested procedure, which will be returned to Process Manager, where it will be interpreted and displayed for the user to review.

No, all the data is kept inside of Nintex controlled spaces and the same Process Manager trust boundaries will apply to this feature.

No prompt/process specific data is collected by Nintex. The only data collected as part of this feature is basic usage data to measure the quality of the interaction (e.g. has the user accepted or regenerated their draft).

To deliver our Generate Procedure from Prompt functionality, we utilize the Azure OpenAI Service, using the GPT-4o model. We decided to use the Azure OpenAI to utilize the security capabilities of Microsoft Azure, while running the same models as OpenAI, within our Nintex MS Azure hosted instance. All data remain within the same Process Manager trust boundaries that apply today.

The knowledge bank used is the one used to originally train the OpenAI GPT-4o model. You can find more about that here. No additional knowledge bank or real-time data is used.

No prompt/process specific data is being used to train the Large Language Model (LLM) used to enable this functionality.

The feature is available to customers on our Expert/Enterprise tier. This feature is not currently available in the AEN region (United Arab Emirates).

This functionality is only available to users with the right to create new Processes (i.e. Process Editors). Additionally, these users must be able to use Process Models.

No explicit limit of using the generative function. Only limit is around process entitlement, as each saved process will count towards the customer’s consumption limit.