Build bots that can manage simple and complex dialog flows and that can learn from, contextualize, and remember conversation data to handle interruptions, execute transactions, and complete tasks – all without writing a single line of code.
Why businesses need highly conversational and context-aware chatbots
The best, most memorable bots have conversation flows that feel natural and human-like. Natural conversations, however, often tend to go beyond the predefined and linear intent resolution paths created by developers. To further complicate this, users often fail to follow a task to its logical conclusion before initiating another, which means that the bot must be able to guide the conversation in the new direction the user wants to go to achieve the desired result – without losing the original context of the conversation.
Dialog Turn Management
The Kore.ai Bots Platform empowers your bots to handle virtually all nuances related to human conversations, including interruptions, clarifications, and more. Plus, your developers get complete control in defining the dialog turn and context switching experience for users.
Hold and Resume
Human conversations are characterized by twists and turns, and no two directions are ever the same. Our bots account for this by allowing users to pause a task, start and complete another task, and then seamlessly return to the original task – all without losing important contextual data and conversation continuity.
Kore.ai provides developers with granular control over hold and resume functionality at the bot, task, and node levels, and allows businesses to control context switching rules and behaviors.
Developers can also select different options for how the bot behaves when resuming intents, including:
- Seeking confirmation from a user before taking action
- Notifying a user prior to fulfilling the request
- Automatically completing the task without alerting the user
End users can also, when allowed by your developers, select how and if they would like the original task to resume. Plus, the platform allows you to set conditional exceptions between tasks with the ability to pass contextual data when and if needed.
Sub-Intents and Follow-Up Intents
Chatbots have historically been limited to handling one intent and one entity at a time. Human conversations, however, are much more dynamic than that, in that they tend to switch between intents and entities, often combining multiple things into one.
Conversations can seamlessly branch into related intents as part of the primary intent, and work only within this context. An output context is added to the parent intent and an input context of the same name is added to the newly created child intent. This means that the child intent can only be matched when the parent intent was matched during a previous portion of the conversation.
Sub intents can be defined at the task level, and are the easiest way to shape dialog without having to manage context manually.
Our engine captures and stores all unattended interruptions from conversation flows. This means that bots can access intents that come up during the execution of a different task, but that were never acted upon.
Our bots can then ask users to select and perform tasks from a list of identified follow-up intents. Developers can also access this list to further train and refine their dialog flows.
Our intelligence engine breaks conversations down to their essence and can identify and follow-up on multiple action items, or intents, in a single message. The bot can then execute tasks in a sequential and logical manner.
The Kore.ai Bots Platform is the only platform in the market today that can handle multiple intents at the dialog management layer. This eliminates the need for users to carefully communicate one command, or intent, at a time – which in turn makes your bot sound less robotic and stale and more like a real person.
Our platform allows users to amend entity values at any point in a conversation. The bot understands the context of the request, identifies the entity to be amended, and then either clarifies the action to be taken or takes action directly – all without writing a single line of code.