Intent Detector Node

An intent detector is a key component for designing flows. Its primary function is to analyze user input and determine the user's intent or purpose behind that input. By recognizing the intent, the system can then take appropriate actions or provide relevant responses. These categories could represent actions, queries, requests for information, or any other meaningful user goals.

Through continuous learning and refinement, intent detectors enable more accurate and efficient interactions between users and AI systems, contributing to enhanced user experiences and improved task automation.

The Intent Node has the following properties:

Intents: The intents drop-down is a valuable property if they are re-used in the flows many times. Select a predefined intent from the drop-down that already contains phrases or entities or both.
Entities: Entities are specific pieces of information or data points extracted from a user's input, such as dates, names, locations, or product names. They provide context and detail that help the MEVA understand and respond accurately to the user's needs. Entities enhance the precision and relevance of the AI's interactions. You can add more than one entity to a node, by clicking on the plus symbol.
Phrases: Phrases are sample expressions or sentences that users might say to convey a particular intent. They help train the AI to recognize different ways users can express the same intent. By giving simple phrases, MEVA automatically detects other phrases that are similar.
Rule: A rule is a predefined condition or set of conditions that guide MEVA's behavior and responses in specific situations. Rules help automate decision-making processes, ensuring consistent and accurate handling of user inputs. They are critical for maintaining logical and effective conversation flows. The rule can be set based on AND and OR conditions. We simply instruct the MEVA to proceed further if the specified rule is true.
Pre Prompt: A Pre Prompt is an initial instruction or context provided to MEVA before processing a user's input. It sets the stage for the interaction, helping MEVA understand how to respond appropriately. Pre prompts are used to define the tone, scope, and objectives of the conversation.
For example: For an AI Tech Support, pre prompt can be,
```
"You are an AI assistant designed to provide technical support.
When a user asks about setting up their email on a smartphone, respond 
with a clear and friendly guide. Make sure to cover the basic steps
and offer to provide further assistance if needed. Tailor the 
instructions for both Android and iPhone users."
```
Post-Prompt: Post-prompt refers to the actions and responses that occur after the user inputs a prompt. Once the prompt is received, the MEVA analyzes the text, understands the context, and generates a relevant and coherent response based on its training data. This process involves interpreting the input, considering various possibilities, and selecting the most appropriate reply.
For example:
```
"After receiving the user's query about setting up
their email on their smartphone, retrieve the relevant documents and
guides from the knowledge base and present it clearly. Ensure your
tone remains helpful and informative."
```