Define Sample Sentences

Introduction

Sample sentences are the example invocations that you add when you configure an action for your ConvoKraft bot. These sentences are conversational in nature, and can be configured based on how a user is likely to interact with your bot. You can add multiple sample sentences for a particular action.

When the user interacts with the bot, the Convokraft bot looks for similar sounding invocations in the sample sentences, and triggers the corresponding action associated with the invocation. If there are no matches found with any existing configured sample sentences, the bot would respond based on the configurations made in the fallback handler.

Sample sentences apply to all action executions, such as direct responses, as well as for business logic execution. In both cases of action executions, you will need to define sample sentences for the bot you create.

• If you have chosen to configure the response based on a direct answer, then you can define the sample sentences that are likely to be used by the user in a conversational way. ConvoKraft understands the intent of the configured sample sentences using its NLP ability and when a user poses a similar query, the bot responds with the direct configured answer.

• If you have chosen to configure the response to execute a business logic, then along with configuring sample sentences, any text typed in the sample sentence can be selected and marked as a param. The param with the value provided by the user will then be passed to the business logic for further processing.

You can learn more about the implementation and usage of sample sentences while creating an action.

Define a Sample sentence

In this section, we will discuss a few example scenarios to explain the usage of sample sentences in a ConvoKraft action :

Say, you are creating an action which will be invoked to respond to queries regarding the details of a particular model of a mobile phone. Based on the inputs, say a model name or number, the corresponding business logic will get executed to fetch the details of that particular model.

The user might probably any questions similar to this:

“I need to know the specs of Iphone 14”

“Iphone 13 specs”

“Tell me everything about Iphone 14 Pro Max”

“Tech specifications of Iphone 14”

“Iphone SE2 technical specs”

The response to the question will be fetched based on user inputs. Say the user enquires about Iphone 14, the answer would be something like the below.

Let’s consider another example where the action provides details about Zoho Corporation. In this case, the answer to the question related to Zoho will be directly configured in the action.

Imagine the questions the user might ask and the different variations of them and configure them as sample sentences. Some questions can be :

“What is Zoho?”

“What does the company Zoho Corporation do?”

“Tell me something about Zoho Corp”

The bot would reply with the configured answer :

“Zoho Corporation is an Indian multinational technology company that makes computer software and web-based business tools. It is best known for the online office suite offering Zoho Office Suite. The company was founded in 1996 by Sridhar Vembu and Tony Thomas and has a presence in seven locations with global headquarters in Chennai, Tamil Nadu, India.”

To get a more detailed understanding about the implementation and usage of sample sentences while creating an action for your ConvoKraft bot, please refer to this page.