1. Home
  2. Kore.ai Conversational Platform
  3. Bot Builder Tool
  4. Configuring Bot Types
  5. Defining a Universal Bot

Defining a Universal Bot

Kore.ai’s Universal Bots facilitate a scalable, modular approach to bot building by helping you link several standard bots into one. The universal bot executes the tasks and functions of the linked bots by routing relevant utterances to the corresponding linked bots. Once you publish a universal bot, changes made in the linked bots automatically reflect in the universal bot. As a creator or developer of a bot, you can add any bots (published and configured) to a universal bot and access their underlying tasks and functions. When you publish a universal bot, the end users can only access the tasks that are published in the linked bots.

Let’s consider the example of a bank to understand how universal bots help you incorporate scalability and modularity into your chatbot strategy. From the scalability perspective, you may want to start building the first version of the bot to solve the credit card issues of the customers. As you optimize the bot, you can add more use cases from the other domains. Likewise, you can also build separate bots for credit card and loan-related issues – both deriving expertise from the respective functional areas. You can later integrate and optimize the bots to interoperate, thus making the design modular.

Note: A universal bot doesn’t own the linked bots, but it interprets the user utterances and maps them to the correct linked bots. The changes that you make to a linked bot task from inside the universal bot, such as training the task, are saved directly to the linked bot. Also, you cannot create any task for the universal bots except for customizing a default dialog task that gets created automatically with every universal bot.

How the Universal Bot Responses Work

Universal bot responses vary with the number of bots and tasks that match the user intent along with their relevance (exact matches or suggestions). The Natural Language Processing (NLP) engine processes the utterances sent to the linked bots, detects the user intents, and ranks them based on relevance. As a developer, you can test and train the bot responses as explained in Test and Train the Universal Bot article. Follow the table below to understand how the universal bot responses operate in various possible NLP outcomes:

NLP Outcome Bot Response
Only one exact match found from any of the linked bots Executes the task with the exact match
Exact matches found in more than one bots Shows the names of the bots to the user and prompts them to select one
Exact matches found with two or more tasks of a single bot Shows all the matching tasks to the user and prompts them to select one
Suggestions found in more than one bot Shows the names of the matching bots to the user and prompts them to select one
Suggestions found with two or more tasks of a single bot Shows all the suggestions to the user and prompts them to select one
Only one suggestion found Shows the suggestion to the user asking if they would like to select it
No exact match or suggestion found Executes the universal bot’s default dialog in the specified language.

Articles in this Section



Was this article helpful to you? Yes No