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
  1. Platform Reference
  2. Intents and Automation
  3. Skills/DSM

Dialog Actions

To speak is to act

Conversational interactions of the virtual agent, especially when running a business process can be broken down into discrete dialog actions. For example, prompt for an input, what to expect during a turn of a conversation etc.

Please find the dialog actions that Dhee supports using which you can define the dialog transitions as described in further automation chapters.

Function
Description

CALL_API

To make a call to a backend REST API

GET

To expect a slot value while displaying the prompt

EXPECT (Silent GET)

To expect a slot value without prompt

SPEAK

To display a message on the chatbot

SPEAK_N_EXIT

To display a message and exiting an intent

SPEAK_4_EACH

To speak multiple messages with the messages comma separated

SET

To equate or initialise a value to a slot

DO

To call upon another intent

TAKE_PAYMENT

To take the payments from end users

COMMAND

To perform a specific command, for example, COMMAND END_CONVERSATION to end the conversation

COMMAND_N_TEXT

To perform both command and text together

ESCALATE

To escalate the conversation to supervisors

WAIT

To add a waiting period in the chatbot

EMAIL

To perform emailer action

SAVE_2_SHEET

Save to spreadsheets action

SAVE_2_THIS_SHEET

Save to spreadsheets action from multiple intents

STORE_FEEDBACK

To store the user feedback

Find below the syntax for some the functions

SAVE_2_SHEET

SAVE_2_SHEET {slot 1} {slot 2} .. {slot K} The above command is to be called once per run of a top level intent. The location to find these spreadsheets is - Reports & Invoice/ Live Statistics/Output Spreadsheets

SAVE_2_THIS_SHEET

SAVE_2_THIS_SHEET {sheet name} {slot 1} {slot 2} .. {slot K} The advantage of this command over the existing intent specific sheets is that you can write to the same sheet from multiple intents (by using the same arbitrarily set name for the sheet from those intents' DSMs)

TAKE_PAYMENT

TAKE_PAYMENT ${amount slot} INTO {payment status slot} amount slot will be holding the value of amount to be asked from user, and can be replaced with any slot name which you use for the purpose.

Similarly, payment status slot will hold Boolean result of the transaction (true or false). Can be replaced with any slot name which you use for the purpose.

COMMAND

  • For signalling javascript events to parent pages use DSM Transition function - COMMAND EVENT (any event code you want to pass, without these brackets)

  • For closing widget and ending conversation - COMMAND END_CONVERSATION

COMMAND_N_TEXT

COMMAND_N_TEXT <COMMAND> <MLT> The advantage of this command over the COMMAND is that we can now send command and text together. For example, COMMAND_N_TEXT RingAlarm TimeForMeetingMLT

EMAIL

EMAIL emailId1|emailId2|emailIdN subjectMltName contentMltName subjectMltName should contain the subject of the email and contentMltName should contain the contents of the email

ESCALATE

  • To escalate the conversation for every supervisor - ESCALATE

  • To escalate to a specific domain (domain-wise escalation) - ESCALATE domainName

PreviousSkills/DSMNextDialog State Transition

Last updated 2 years ago