Born Digital - Documentation
  • Welcome
    • Welcome to Digital Studio
  • Digital Agent
    • Introduction
    • Workspace
      • List of Projects
      • Project Details
      • Deploy Project
    • Conversation Flow
      • User Interface Basics
      • Nodes Explained
        • MESSAGE node
        • ANSWER node
        • DECISION node
        • FUNCTION node
        • AI node
        • TRANSFER node
        • REDIRECT node
        • START / END nodes
      • Training set
        • Overview
        • Best practices for writing training set
      • Launching project
      • Setting tab
    • Building new projects
      • Knowledge base project
        • Step 1. - Initializing Your Project
        • Step 2. - Integrating AI Node
        • Step 3. - Finalizing with Testing and Training
        • (Optional) - Integrating a Knowledge Base Index
      • Advanced project
        • Step 1. - Establishing Functions
        • Step 2. - Crafting Greetings
        • Step 3. - Adding the AI node
        • Step 4. - Managing Flow Scenarios
        • Step 5. - Finalizing the Project
        • Step 6. - Training and Execution
    • Advanced functions
      • Knowledge base
      • New AI node property variables
      • Recordings
      • Statistics
      • Code editor
      • Widgets
  • For advanced users
    • Conversation design tips
      • Customizing speech synthesis
      • Customizing text output
      • Customizing smart functions output
      • Randomizing message content
      • Alternative messages based on variable values
      • Setting time-based greetings
      • Personalised URL links
      • Custom business statuses with variables
      • String slicing
      • Implementing chat buttons
    • Intent recognition tips
      • Fine-Tuning Intent Recognition using Generative AI
      • Multi-step intent recognition
      • Recognition based on named entity extraction
    • Prompting cookbook
      • Basics
      • Prompting techniques
  • Product changelog
    • Product changelog
  • Initial setup
    • Starting up
    • My settings
  • Contacts
    • Contacts for you
Powered by GitBook
On this page

Was this helpful?

  1. Digital Agent
  2. Building new projects
  3. Knowledge base project

Step 2. - Integrating AI Node

This part is about integraton a Generative AI node for dynamic interactions and establishing an ongoing dialogue loop, preparing for further project refinement.

PreviousStep 1. - Initializing Your ProjectNextStep 3. - Finalizing with Testing and Training

Last updated 1 year ago

Was this helpful?

With the initial setup complete, the next stride involves incorporating a Generative AI intent recognition. This addition enriches customer interactions by enabling recognition of greetings or conversation conclusions, thus enhancing user experience with responsive engagement.

Defining Fallbacks

A fallback mechanism is crucial when specific intents are unrecognizable. In such cases, the interaction defaults to a 'AI' node, ensuring the customer receives pertinent responses to their inquiries.

Step-by-step guide
  1. Access an 'Answer' Node: Initiate by selecting an existing 'Answer' node.

  2. Generate a New Intent: Employ Generative AI intent recognition to create a 'goodbye' intent.

  3. Establish a Fallback: Set up a fallback 'AI' node for unrecognizable queries.

  4. Create an 'END' Node: Designate this as the target for the 'goodbye' intent.

  5. Configure the 'AI' Node: Tailor the system message to meet your requirements.

  6. Incorporate a Follow-Up 'Message' Node: Position this after the 'AI' node to query additional customer questions.

  7. Link for Continuous Interaction: Connect this 'Message' node back to the 'Answer' node, enabling an infinite interaction loop.

Implementing AI Node

An 'AI' node is established with a predefined system message (for details, refer to the linked resources). Post-response, a subsequent 'Message' node inquires if the customer has further questions, linking back to the 'ANS_ask' node to foster a continuous dialogue loop. This structure is pivotal for crafting a seamless ask-and-answer loop within the virtual assistant, laying the groundwork for our Conversation Flow builder.

Proceeding to Further Development

As this step lays the foundational AI integration, it's crucial to progress to STEP 3 - Training and Testing Your Project, to refine and validate the system's functionality.

Step 2: - Adding the intent and AI node