LogoLogo
  • Dhee.AI
  • Concepts We Work on
    • What is NLP?
    • Natural Language Parser Pipeline
    • Word Embeddings
    • Textual Entailment
    • User Intent Recognition
    • Document Reading
  • Getting Started
    • Train your bot
      • Create your bot project
      • Train for Intent recognition
        • Define the Slots
        • Train the Triggers
        • Train for Stop-Triggers
      • Configure Agent Responses
      • Write your REST Endpoints
      • Configure Endpoints
      • Configure Workflow
        • Read Inputs
        • No Code Approach
        • REST Endpoints Approach
        • Acknowledge User
    • Build and Deploy
      • Build
      • Test
      • Deploy
        • Embedding Widget in Apps
  • Platform Reference
    • Manage Projects
    • Agent Settings
      • Basic
        • Language
        • Domain
        • Voice
        • Avatar Settings
      • Widget
        • Widget Theme
        • Widget Label
      • Advanced
      • Team
        • Development Team
        • Support Team
      • Import Export
      • Emailer
      • Billing
      • Botstore
    • Knowledge Management
      • Document Reading
      • Frequently Asked Questions
    • Intents and Automation
      • Intents
        • Slots
        • Triggers
        • Stop Triggers
        • Special Intents
      • Skills/DSM
        • Dialog Actions
        • Dialog State Transition
          • Slot State
        • Dialog Workflow
        • Skill API
      • Backend API
    • Extended Message Types
    • Entities And Other Data
      • Entities
        • Multilingual Entities
        • Language Specific Entities
        • Custom Entity Types
      • Agent Responses
        • Multilingual Responses
        • Missed Query Responses
        • Support-Unavailable Responses
      • Directive Utterances
        • Customize Inputs
        • Customize Outputs
      • Translations
      • Query Substitutions
      • Abbreviation Texts
    • Test & Deploy
      • Build
      • Test
      • Deploy
        • Launchpad
        • Widget
        • Signal
        • Telegram
        • Google RCS
        • Facebook
        • Alexa
        • Whatsapp
        • Custom App
        • Voice
        • Telephony
        • Email
    • Reports
      • Statistics
        • Summary
        • Daily Reports
          • Conversation Analytics
        • Weekly Reports
        • Monthly Reports
        • Output Spreadsheet
      • Conversations
        • Conversation Logs
        • C-SAT
      • Generate Report
        • Lead Report
        • Category Report
        • Device Demography Report
        • Utterance Report
        • Missed Query Report
        • Location Report
      • Report Settings
        • KPI
        • Schedule Report
      • Personnel Audit
        • Development Team
        • Support Team
          • Supervisory Sessions
          • Login Information
      • Bot Store
        • Reviews
        • Reported Issues
  • The Social Desk
    • Whatsapp
      • Customer Chat
      • Manage Template
      • Outreach Campaign
        • Create new
        • Manage Campaign
    • Reports
    • Settings
      • Team
      • Whatsapp
  • Extras
    • External Links
  • News
    • Dhee.AI's Edge Server for Telephony Achieves Breakthrough Optimization on Intel Architecture
  • Dhee.AI Telephony Edge Servers: Elevating Conversational AI Experience with Edge Computing
  • Pinnacle Teleservices Joins Forces with DheeYantra to Supercharge Conversational AI on WhatsApp
Powered by GitBook
On this page
  • Configure Workflow
  • Start Action
  • Read Inputs
  • Record Information
  1. Getting Started
  2. Train your bot
  3. Configure Workflow

Read Inputs

PreviousConfigure WorkflowNextNo Code Approach

Last updated 3 years ago

Now that we have the required slots and triggers configured, it is time to configure the actual workflow.

An ideal workflow for the applyLeave intent would be

  1. Ensure startDate and endDate are available.

  2. Ensure leaveReason is available.

  3. Mark the leave using the available end-point

  4. Response to User the action has been completed.

Let us begin creating the workflow.

Configure Workflow

Every workflow configured might contain a varying number of steps depending on the intent. Irrespective of the logic involved, each of the workflow will begin with a Start Action and is terminated by an End action.

Start Action

The Start Action marks the first step of the workflow. Every workflow defined has a single Start action. You can add the Start Action by dragging and dropping the action from the Action Panel to the Editor.

Read Inputs

Once we have marked the first step of the workflow, as per the outline of workflow we created at the beginning of this document, the next step is to ensure the key parameters (slots) which are required by the intent are captured.

This can be ensured by adding an Get Action. The Get action accepts a single parameter, which points to the slot that needs to be read. You can add the slotName as shown in the figure below.

Drag 3 Get actions to the workflow editor and specify each of the slots we require in each of them. We will begin by collecting the startDate, followed by the endDate and leaveReason. You can mark the order by using the transition/relation lines as shown in the figure.

Record Information

At this point, there are two options. The developer can design the workflow to make use of a Rest endpoint to save the values. On other hand, when the requirement to have a backend endpoint is not that high, you could also make use of our no-code approach and save the values in a spreadsheet. We will look into both approaches.

No Code Approach
REST Endpoints Approach
Start Action
Get Action
Read Inputs