Docs

Default Standard Responses

Kore.ai Bot Builder tool provides a few default text responses. This section lists them and gives an explanation as to when these responses are triggered. For an overview on Standard Responses, refer here. Statements Message Definition When the user confirms to close the conversation in a language and switch to…

Traits

In natural conversations, it is very common that a user provides background/relevant information while describing a specific scenario. Traits are specific entities, attributes, or details that the users express in their conversations. The utterance may not directly convey any specific intent, but the traits present in the utterance are used…

User Intent Node

As a bot developer, you typically create a task to resolve one primary user intent. Yet, user conversations can branch into related intents (follow-up or sub-intents) as a part of the primary intent. Let us take a look into this sample conversation for a flight booking assistant: VA: Hi, how…

Virtual Assistants Overview

Introduction Communication has been the essence of life from the beginning of time. Traditionally, conversations were restricted to verbal and textual interaction between humans. These interactions were usually guided by emotions, context, and awareness of previous conversations. With the advent of computers, interactions have expanded to include machines i.e. human-machine…

Managing Dialogs

Your bot can have many dialog tasks with related components. You can use the Dialog Editor to create, review, and edit a single dialog task for a bot. However, to better visualize and understand relationships and settings for all dialog tasks in a bot, you must use the Manage Components…

Message (Bot Response) Nodes

The Message Node is used to deliver a message to the user. Message nodes commonly follow an API, web service call, or webhook event to define their results as a formatted response.You can format bot responses as below: Plain text: Type a message in plain text. You can use stored…

Conversation Testing

Conversation Testing enables you to simulate end-to-end conversational flows to evaluate the dialog task or perform regression. You can create Test Cases to capture various business scenarios and run them at a later point in time to validate the performance of the assistant. Test Cases Overview Test Cases consist of…

Talk to Bot

After you have defined your assistant and configured one or more tasks, you should test your settings before you publish your NLP-enabled assistant. Bot owners and developers can chat with the assistant in real-time to test recognition, performance, and flow as if it were a live session. Testing a Virtual…

Creating a Simple Virtual Assistant

After you have signed up with the Kore.ai Bots platform, the next step is to create a bot. Before you create a bot, it is recommended to go through the basics of bot-building from this link. You can follow the steps given in this document to build the bot at…

Adding the Mattermost Channel

You can connect Kore.ai assistants to your Mattermost account using either: Webhook based integration or WebSocket based integration. Before you begin, ensure that you have access to the administrative functions of your Mattermost account. WebHook based Integration Step 1: Setup Outgoing Webhook Login to your Mattermost account From the Main…