Bots

SDK Configuration

To enable your Kore.ai Bot to communicate between your application servers and Kore.ai servers, you need to create and register an app in Kore.ai Bot Builder that specifies the callback URL for your application, and generates the Client ID and Client Secret authentication tokens required for secure communications between your…

Bot Tasks

Kore.ai Bots platform supports the following types of tasks with different use cases: The following Bot tasks are available on the Kore.ai Bots Platform: Dialog Tasks Consists of multiple intents, sub-intents, and component nodes to conduct a complex conversational flow between a user and the bot. Know More Simple Tasks…

Analyzing Your Bot

Kore.ai provides various ways to aid in Analyzing your Bot performance: Dashboard: This page gives you - a bird’s eye view of all the bot configuration and capabilities, and view real-time and standard dashboards on your Bot’s performance Conversation Flows: This can be used to visualize the journey of various bot…

Adding the Skype Channel

To add the Skype channel to your bot, you need a developer Microsoft Bot Framework account to configure the connection between Skype and Kore.ai. Adding the Skype channel to your Kore.ai bot is a three-step process to allow end-users to interact with your bot. To add the Skype channel to…

Dialog Task

Kore.ai Dialog Tasks represent a full conversational flow between a user and a bot with a network of nodes that are connected using conditions. For example, if you create a banking bot, the tasks you want your bot to do for users is to: Retrieve and monitor account balances. Provide…

Adding the Twitter Channel

To set up Twitter as a channel, you must associate the bot with a Twitter account, define a Twitter app, and enable the integration. To add Twitter as a channel, follow the below steps: Create Twitter App - Log in to Twitter. In Twitter App Management Console, create an app…

Publishing your Bot

End users can interact with a bot only when it is published. When you publish a Bot task, the platform initiates a request to the Bots Admin to approve it. Depending on the Purpose defined for the bot during its initial set up, the following happens: For an Employee Bot: The Bots Admin needs to…

Adding the Cisco Webex Teams

To add the Cisco Webex Teams (formerly Cisco Spark) channel to your bot, the developer must create a bot app and an integration app in Cisco Webex Teams. Adding the Cisco Spark channel to your Kore.ai bot is a four-step process to allow end-users of your bot to interact with…

Utterance Testing

To make sure your bot responds to user utterances with related tasks, it is important that you test the bot with a variety of user inputs. Evaluating a bot with a large sample of expected user inputs not only provides insights into bot responses but also gives you a great…

Machine Learning

Developers need to provide sample utterances for each intent (task) the bot needs to identify to train the machine learning model. The platform ML engine will build a model that will try to map a user utterance to one of the bot intents. Kore.ai’s Bots Platform allows fully unsupervised machine…