Skip to main content

9. Tonkean AI

Artificial intelligence (AI) is an integral part of the Tonkean platform. From the AI Front Door to the AI Concierge, Tonkean AI empowers requesters to engage with your process more easily and enables makers to create truly next-level experiences for their users.

The primary Tonkean AI feature is the AI Front Door, which is an LLM-powered service embedded in and integrated with various parts of the platform. The AI Front Door (or simply, "the Front Door") is perhaps the most common way to interact with Tonkean AI, but there are other areas where users can engage with Tonkean AI power as well, such as when working through an intake experience. Your workflows can also leverage Tonkean AI in the middle of your module workflow thanks to LLM actions from connected OpenAI, Anthropic, Gemini, or other generative AI data sources.

The AI Front Door

The AI Front Door is the go-to place for internal users to ask questions and submit requests from your shared services teams, without needing to understand complex processes or policies. The AI Front Door is powered by Microsoft Azure OpenAI. It leverages the forms and data sources in your solutions as context to answer questions, initiate processes, and perform other tasks configured in your modules.

The AI Front Door does not train the model on your data. Instead, it selectively and strategically accesses the data in your enabled forms and data sources to act as context and reference to serve requesters. For example, if a member of the sales team asks how long the opportunity with ACME Inc. has been open, the AI Front Door locates the record for ACME Inc. in your connected Salesforce data source, calculates the number of days it's been open, and returns that to the user.

There are various ways the AI Front Door searches for and uses data in your Tonkean instance and data sources:

  • Entity lookup - Tonkean searches for relevant records in connected and AI-enabled data sources in response to a user query.

  • Entity analysis - Tonkean asks questions about the data source records identified as related or relevant to the query.

  • Action lookup - Tonkean searches for relevant intake sequences and actions related to the query.

  • Intake prefill - Using information extracted from the conversation with the requester, Tonkean populates the first interface in an intake sequence.

Below is a simplified diagram of the AI Front Door workflow and the process by which the Front Door retrieves and returns information to the requester:

ai_front_door.png

Next Topic:

10. Maker Best Practices