Now that you've learned how your AI Agent works, explore the extensions available to enhance its capabilities.
Extensions allow you to enhance a dataset by running code before or after your AI agent replies to a chat request. Modules can be assigned to a dataset, but can be excluded from running when using predefined questions, or when specific criteria is true.
You can add any module to any dataset using the "Add Extension to Dataset" endpoint of the API. To do this, you'll need to know the module "key". You can find that key from the module's page in the marketplace below.
Any module denoted as an "MODULE" module type can be used with a dataset.
Once added to a dataset, unless the module is skipped by a question, it will always be executed either before or after (look for the module runtime in the extension marketplace for details) the AI prompt reaches the AI agent. This allows you to enhance the dataset with additional context or processing.
Some extensions are "actions", meaning that they perform a specific task when a question is clicked during a chat.
Any module denoted as an "ACTION" module type can be used with a question.
Data forwarding allows you to pass data from one module to another. This is particularly useful when you want to use the output of one module as the input for another.
Common examples of this include using a questionnaire or contact module and forwarding that data to the EMAIL or API modules, allowing that data to be sent to a 3rd party platform.
Look for the "Data Intake" and "Data Output" flags in the marketplace for information on how a module or action can handle data forwarding.
Browse the various extensions available for use on our marketplace.
Marketplace