Virtual Assistants

Using Session and Context Variables in Tasks

When you define tasks, you can access session variables provided by the Bots Platform, or custom variables that you define, as well as the context that defines the scope of the variable. For example, some API requests may require you to set session variables before the request is executed, or a…

User Prompts

After creating an Entity, Confirmation, or Message node in the Dialog Builder, Kore.ai lets you do the following: Modify the default message or user prompt displayed to the end-user. Add new prompts or messages. Add channel-specific prompts or messages. Prompt Types Dialog Tasks support two types of user prompts: Standard:…

Context Object

The Context object is the container object that persists data for dialog execution and across all intents i.e. dialog tasks, action, alert & info tasks, and FAQs. Kore.ai’s natural language processing (NLP) engine populates the intent identified, entities extracted, and history into this object. Keys from the Context object are…

Redacting Personally Identifiable Information

Personally identifiable information (PII), or sensitive personal information (SPI), refers to information that can be used on its own or with other information to identify, contact, or locate a single person, or to identify an individual in context. Some examples of PII include Social Security Number, email address, credit card…

Customizing Error Messages

In Bot Builder, each Bot and task contains a set of predefined error messages along with actions for standard HTTP Status codes returned for an HTTP Request method. In most cases, the default response and action are sufficient for an end-user response, however, you may need to handle other HTTP…

Context Management

Effective context management is important because it allows bots to interact with users in a way that is easier, quicker, more helpful, and less robotic and scripted. Contextual data helps users complete tasks faster and allows you to create more natural, human-like back and forth conversations. For example, let us…

Custom Meta Tags

While analyzing your Bot performances, you might want to give preference to or discard a particular scenario. For example, you might want to track how many people are booking tickets to Chicago. Or you might want to track how a specific user, a premium customer, requests are being catered to.…

Sessions History API

This API retrieves the conversation sessions created. The API details are available in the Bot Builder and Bot Admin Console (BAC) app scopes. To use this API, app needs the Bot Builder API scope of Bot sessions.OR the Admin API Scope of Bot sessions under Bot Analytics. POST https://{{host}}/api/public/bot/{{BotID}}/getSessions?containmentType={{containmentType}}and https://{{host}}/api/public/getSessions?containmentType={{containmentType}} for…

Conversation History API

Fetches the conversational messages between the bot and user in reverse chronological order. This API supports pagination. You can provide offset/skip and limit to get a certain number of messages at a time. This is a newer version of the old API which will soon be deprecated. This revised API…

Model Validation

Once you have built your virtual assistant and trained it, the Kore.ai platform builds an ML model mapping user utterance with bot intents (click here for more info). Once created, it is recommended to validate the model to understand and estimate an unbiased generalization performance of the ML model. Kore.ai…