User Guide
API DOCSVOICE GATEWAYHELPSECURITY
Current Version
Current Version
  • Welcome
  • What's New
  • 🚀GETTING STARTED
    • Login
    • Concepts and Glossary
    • Language Models
      • Syntphony NLP
      • Other NLP and LLM Connectors
      • FAQs
    • Build a Virtual Agent
      • Overview
      • From Scratch
      • By Importing
      • Pre-Built Templates
      • Training task
    • Testing
      • Automated Test
      • Advanced Request
      • Simulate Dialog
      • View Logs
    • Create and manage profiles
  • 💬BUILD DIALOGS
    • Flows
    • Dialog Cells
      • Intent
      • Entity
      • Answer
      • Input
      • Jump
      • End
      • Service
      • Rest Connector
      • Code
      • Rule
        • Variable answers using Code and Rule cells
        • Enable and disable flows using Rule Cells
    • Data Masking of Personal Identificable Information
    • Dynamic Content and Contexts
    • Voice Agent
    • Multilingual Agent (beta)
  • ✨GENERATIVE AI
    • AI features
    • Assist Answer (beta)
    • Examples Generator
    • Knowledge AI
    • Prompt cell
      • Prompt crafting
      • Practical examples
    • Rephrase Answer
    • Zero-Shot LLM
  • 🌐CHANNELS
    • Channels
      • WhatsApp (by Infobip)
      • Facebook Messenger
      • Microsoft Teams
      • Integrating Existing Channels
    • Webchat Plugin
  • ⚙️CONFIGURATIONS
    • Parameters
    • Advanced Resources
    • Other Options
      • Intent Navigator
  • 📊ANALYTICS & INSIGHTS
    • Dashboards
      • Overview
      • Funnel charts
      • User messages
      • Conversations
      • Reports
    • External Analytics Platforms
  • API DOCS
    • Overview
    • API Guidelines
      • Conversation API
      • Cloner API
      • EVG Connector
      • Management API
        • Admin API
          • Bot Admin
          • Environment
          • Organization
          • User
          • Notification
        • Instance API
          • Knowledge AI
          • Knowledge AI NLP
          • Answer
          • Automated Tests
          • Bot
          • Broker
          • Channel
          • Dashboard
          • Dialog Manager
          • Entity
          • Generative Service
          • Intent
          • Parameters
          • Tag
          • Technical Log
          • Training
          • Transactional Service
          • Rest Connector
          • Wait Input
          • Websnippet
      • Webhooks
    • Infrastructure Guidelines
      • Syntphony CAI server Installation guide
      • Maintenance Methods
      • Supported/verified third-party software
    • Data Structure
      • Admin Data Structure
      • Environment Data Structure
    • Voice Gateway
      • Genesys Cloud CX
Powered by GitBook
On this page
  • What is a Virtual Agent
  • What are Conversational Virtual Agents
  • What are Intents & Entities
  • How to Build Intelligent Virtual Assistants

Was this helpful?

  1. GETTING STARTED
  2. Build a Virtual Agent

Overview

PreviousBuild a Virtual AgentNextFrom Scratch

Last updated 10 months ago

Was this helpful?

What is a Virtual Agent

Communication has been a cognitive activity since the dawn of time. In the early days, conversations were limited to verbal and textual interactions between people.

All of these interactions were guided by emotion, context, and knowledge of previous conversations. With the introduction of computers, the interactions have now extended to machines, i.e., human-machine interactions.

Artificial intelligence is a branch of knowledge that deals with the development of intelligent computer systems, i.e., systems that exhibit characteristics that we associate with human behavioral intelligence: Language comprehension, learning, reasoning, problem solving, etc.

Natural Language Processing (NLP) is a subfield of Artificial Intelligence that deals with the application of methods that enable computers to learn, understand, and produce content in natural language.

Using artificial intelligence and NLP capabilities enabled virtual assistants to understand user utterances in natural language, infer the task from the user utterance, and extract the information needed to perform the task successfully.

AI and NLP-based chats and virtual voice assistants are the latest trend in technology and a must-have for all businesses in this generation.

What are Conversational Virtual Agents

A Virtual Agent acts as an intelligent assistant between people and digital systems. It replaces the traditional user interfaces of an application or website with a conversational user interface. This is a paradigm shift from a previous communication, which involved either typing syntax-specific commands or clicking icons.

Virtual agents are designed to converse with the user through a combination of natural language conversations. Responses can take the form of buttons, calendars, or other widgets that speed up the user's response time. AI-powered messaging solutions, or conversational virtual assistants, serve as a springboard to the future.

They communicate via intelligent virtual agents, corporate apps and websites, social media, and messenger platforms. Users can interact with such assistants via voice or text to retrieve information, complete tasks and conduct transactions. So what makes the Conversational Virtual Assistant so special? In a nutshell:

What are Intents & Entities

A conversational virtual agent is based on three concepts:

  1. Intents, is the intent of what the user wants to say to the bot, i.e., what the user expects the chatbot to say when it says something.

  2. Utterances: these are the sentences that the user says to the chatbot.

  3. Entities: these are keywords associated with the intentions that determine the response of the chatbot, as they are necessary for the execution of the action identified by

The Conversational virtual agent's job is to detect the intent and entities necessary to carry a conversation from the user utterance.

How to Build Intelligent Virtual Assistants

The intelligence of virtual agents is not innate, but must be trained with the help of machine learning, big data and NLP technologies.

A virtual agent is intelligent when it knows the user's needs, understands the context, and responds to the user based on the user's needs, mood, etc. This intelligence gives VA the ability to handle any scenario of a conversation with ease.

To design an intelligent VA it is necessary:

  1. Create a natural language model that allows understanding user queries by detecting intentions. The NLP model must be trained by defining intentions using example texts (utterances). Syntphony CAI allows you to create language models by using the custom NLP engine, creating intentions, defining utterances, and training entities. In addition, you can also use models trained in external engines such as Watson, Luis, or Dialogflow.

  2. Design dialog flows for the different use cases we want to cover with the virtual agent. A dialog flow is a specific conversation to solve a use case. The flow includes language understanding, internal logic, calls to external services, and response management. With Syntphony CAI, we will be able to design flows of great complexity using the dialog manager.

  3. Create the responses. Responses need to be written and customized to the tone and experience you want to deliver with the bot. Also, the responses can be customized to the experience that each conversational channel can provide. Syntphony CAI allows you to create responses for multiple channels so that you can make the most of each channel's experience.

🚀
intents and utterances