Dynamic Conversation Flows

Building the next generation of real-time AI

Whether it’s a complex series of information-seeking questions or a complicated dialogue logic, Avaamo enables dynamic generation of new multi-turn conversations from scratch using ML domains and their associated intents and entities.

Technology – dynamic conversation generation

Not only does Avaamo understand what the user is asking and which system to get that information from, it is also able to dynamically generate a predictive natural language response to present that information.

nlu-diagram

Auto-generating multi-turn conversations

Avaamo bots provide the ability for multi-turn conversations. Once an intent has been identified, users will be prompted for information that is required for the intent to be fulfilled. Avaamo gives you an easy way to build multi-turn conversations for your bots. You simply list the intent utterances and the slots you want to collect from your users, and Avaamo takes care of orchestrating the dialogue by prompting for the appropriate slot.

Intent chaining

Avaamo can transfer control dynamically from one intent to another based on end user input.  For example, in a banking bot, after the user has reported a case of fraud, you can build your bot to subsequently ask if the user also wants to perform a credit check. The user response could result in other making the credit score check, or decline them. Avaamo will handle the flow accordingly.

Designed to scale

When you are designing a virtual assistant to handle 1000s of intents, creating responses through pre-defined conversational flows can require a lot of manpower and may also be error-prone. Instead letting the platform discern the top-level activity that a user is attempting to do, and then dynamically generating the appropriate conversation for that user can lead to a huge savings in effort and help your development and design teams scale rapidly.