GETTING STARTED
Kore.ai XO Platform
Virtual Assistants Overview
Natural Language Processing (NLP)
Concepts and Terminology
Quick Start Guide
Accessing the Platform
Navigating the Kore.ai XO Platform
Building a Virtual Assistant
Help & Learning Resources
Release Notes
Current Version
Recent Updates
Previous Versions
Deprecations
Request a Feature
CONCEPTS
Design
Storyboard
Overview
FAQs
Conversation Designer
Overview
Dialog Tasks
Mock Scenes
Dialog Tasks
Overview
Navigate Dialog Tasks
Build Dialog Tasks
Node Types
Overview
Intent Node
Dialog Node
Dynamic Intent Node
GenAI Node
GenAI Prompt
Entity Node
Form Node
Confirmation Node
Message Nodes
Logic Node
Bot Action Node
Service Node
Webhook Node
Script Node
Process Node
Agent Transfer
Node Connections
Node Connections Setup
Sub-Intent Scoping
Entity Types
Entity Rules
User Prompts or Messages
Voice Call Properties
Knowledge AI
Introduction
Knowledge Graph
Introduction
Terminology
Build a Knowledge Graph
Manage FAQs
Knowledge Extraction
Import or Export Knowledge Graph
Prepare Data for Import
Importing Knowledge Graph
Exporting Knowledge Graph
Auto-Generate Knowledge Graph
Knowledge Graph Analysis
Answer from Documents
Alert Tasks
Small Talk
Digital Skills
Overview
Digital Forms
Digital Views
Introduction
Widgets
Panels
Session and Context Variables
Context Object
Intent Discovery
Train
NLP Optimization
ML Engine
Overview
Model Validation
FM Engine
KG Engine
Traits Engine
Ranking and Resolver
Training Validations
NLP Configurations
NLP Guidelines
LLM and Generative AI
Introduction
LLM Integration
Kore.ai XO GPT Module
Prompts & Requests Library
Co-Pilot Features
Dynamic Conversations Features
Intelligence
Introduction
Event Handlers
Contextual Memory
Contextual Intents
Interruption Management
Multi-intent Detection
Amending Entities
Default Conversations
Conversation Driven Dialog Builder
Sentinment Management
Tone Analysis
Default Standard Responses
Ignore Words & Field Memory
Test & Debug
Overview
Talk to Bot
Utterance Testing
Batch Testing
Conversation Testing
Conversation Testing Overview
Create a Test Suite
Test Editor
Test Case Assertion
Test Case Execution Summary
Glossary
Health and Monitoring
NLP Health
Flow Health
Integrations
Actions
Actions Overview
Asana
Configure
Templates
Azure OpenAI
Configure
Templates
BambooHR
Configure
Templates
Bitly
Configure
Templates
Confluence
Configure
Templates
DHL
Configure
Templates
Freshdesk
Configure
Templates
Freshservice
Configure
Templates
Google Maps
Configure
Templates
Here
Configure
Templates
HubSpot
Configure
Templates
JIRA
Configure
Templates
Microsoft Graph
Configure
Templates
Open AI
Configure
Templates
Salesforce
Configure
Templates
ServiceNow
Configure
Templates
Stripe
Configure
Templates
Shopify
Configure
Templates
Twilio
Configure
Templates
Zendesk
Configure
Templates
Agents
Agent Transfer Overview
Custom (BotKit)
Drift
Genesys
Intercom
NiceInContact
NiceInContact(User Hub)
Salesforce
ServiceNow
Configure Tokyo and Lower versions
Configure Utah and Higher versions
Unblu
External NLU Adapters
Overview
Dialogflow Engine
Test and Debug
Deploy
Channels
Publishing
Versioning
Analyze
Introduction
Dashboard Filters
Overview Dashboard
Conversations Dashboard
Users Dashboard
Performance Dashboard
Custom Dashboards
Introduction
Custom Meta Tags
Create Custom Dashboard
Create Custom Dashboard Filters
LLM and Generative AI Logs
NLP Insights
Task Execution Logs
Conversations History
Conversation Flows
Conversation Insights
Feedback Analytics
Usage Metrics
Containment Metrics
Universal Bots
Introduction
Universal Bot Definition
Universal Bot Creation
Training a Universal Bot
Universal Bot Customizations
Enabling Languages
Store
Manage Assistant
Team Collaboration
Plan & Usage
Overview
Usage Plans
Templates
Support Plans
Invoices
Authorization
Conversation Sessions
Multilingual Virtual Assistants
Get Started
Supported Components & Features
Manage Languages
Manage Translation Services
Multiingual Virtual Assistant Behavior
Feedback Survey
Masking PII Details
Variables
Collections
IVR Settings
General Settings
Assistant Management
Manage Namespace
Data
Overview
Data Table
Table Views
App Definitions
Data as Service
HOW TOs
Build a Travel Planning Assistant
Travel Assistant Overview
Create a Travel Virtual Assistant
Design Conversation Skills
Create an ‘Update Booking’ Task
Create a Change Flight Task
Build a Knowledge Graph
Schedule a Smart Alert
Design Digital Skills
Configure Digital Forms
Configure Digital Views
Train the Assistant
Use Traits
Use Patterns
Manage Context Switching
Deploy the Assistant
Use Bot Functions
Use Content Variables
Use Global Variables
Use Web SDK
Build a Banking Assistant
Design Conversation Skills
Create a Sample Banking Assistant
Create a Transfer Funds Task
Create a Update Balance Task
Create a Knowledge Graph
Set Up a Smart Alert
Design Digital Skills
Configure Digital Forms
Configure Digital Views
Add Data to Data Tables
Update Data in Data Tables
Add Data from Digital Forms
Train the Assistant
Composite Entities
Use Traits
Use Patterns for Intents & Entities
Manage Context Switching
Deploy the Assistant
Configure an Agent Transfer
Use Assistant Functions
Use Content Variables
Use Global Variables
Intent Scoping using Group Node
Analyze the Assistant
Create a Custom Dashboard
Use Custom Meta Tags in Filters
Migrate External Bots
Google Dialogflow Bot
APIs & SDKs
API Reference
API Introduction
Rate Limits
API List
koreUtil Libraries
SDK Reference
SDK Introduction
SDK Security
SDK Registration
Web Socket Connect and RTM
Installing the BotKit SDK
Using the BotKit SDK
SDK Events
SDK Functions
SDK Tutorials
BotKit - Blue Prism
BotKit - Flight Search Sample VA
BotKit - Agent Transfer
Widget SDK Tutorial
Web SDK Tutorial
ADMINISTRATION
Introduction to Admin Console
Administration Dashboard
User Management
Add Users
Manage Groups
Manage Roles
Data Tables and Views
Assistant Management
Enrollment
Invite Users
Send Bulk Invites
Import User Data
Synchronize Users from AD
Security & Control
Using Single-Sign On (SSO)
Two-Factor Authentication (2FA)
Security Settings
Cloud Connector
Analytics
Billing
  1. Home
  2. Docs
  3. Virtual Assistants
  4. How Tos
  5. Creating a Banking Assistant

Creating a Banking Assistant

This document helps you create a sample banking bot. This bot is used in various use case scenarios presented in the How-Tos section of the developer documentation.

Prerequisites

The following are the prerequisites:

  • You must have signed up with the Kore.ai Bots Platform.
  • You must be aware of the basics concepts of bot-building (refer to this link).
  • You must have created a simple bot (refer here for an example).

Bot Overview

The bot we build will perform the basic banking transactions. This bot will:

  • Get account balance based on the user’s Account Number and Account Type.
  • Update accounts with the balance. For more information, click here.
  • Transfer a specified amount from the user account to a payee account. For more information, click here.

Let us start building the bot and add Get Balance task to it.

Create a Bot

This document helps you to create a Standard Bot for banking activities. To create a standard bot, follow the below steps:

  1. Log in to your Kore.ai Bots Platform with valid credentials.
  2. On the bots landing page, click New Bot on the top-right and select Start from Scratch from the list.
  3. On the Create New Bot window, enter the bot details:
    1. Bot Name – Provide a name to your bot. For example, Banking Bot. If the name is already used, provide a different name.
    2. Set the Default Bot Language to English.
    3. Select the Bot Type as Standard Bot.
  4. Click Create.

Get Balance Intent

  • The Get Balance task prompts the user to enter an account number and the account type (Savings/Current).
  • It makes a service call to fetch the details.
  • The balance for the requested account is displayed.

Dialog Task

Successful creation of the bot directs you to the Bot Summary page. We need to add a Dialog Task as the first step in the Bot. Intent Dialog is the first step in the user-bot conversation flow.

  1. On the Bot Summary page, click + New Task on the Tasks widget.
  2. Select Dialog Task from the list.
  3. On the Create Dialog window, enter the following details:
    • Enter a name in the Intent Name field. This is the phrase that triggers the dialog. The intent name must be simple and not more than 3-4 words. For example, Get Balance.
    • Enter a description in the Description field.
    • In the Intent Training field, add unique utterances to improve the user intent recognition.
    • Under More Options, you can add other dialog-related details. Let us retain the default settings.
    • Select Try Conversation Driven Dialog Builder option.
  4. Click Proceed.
    Note: For instructions with the older Dialog Builder, refer here

Entity Node

Entity Node is typically used to gather information from the user. Here, it is used to capture the user input for Account Number and Account Type.

  1. Click the + icon below the User Intent (Get Balance) node.
  2. Select Entity from the list and click + Entity.
  3. Click on the newly created Entity node to open the Property window.
  4. Under the General Settings section, enter the following details:
    • Name: AccountNumber
    • Display Name: Account Number 
    • Type: Number
    • User Prompts: Enter the following text and press Enter to save:
      Enter the account number.

  5. Close the AccountNumber Entity Property window.
  6. Repeat the above steps to add another entity with the following details:
    • Name: AccountType
    • Display Name: Account Type 
    • User Prompts: Enter the following text and press Enter to save:
      Enter the account type.
    • Display List Of Values: Select Yes, use channel-specific standard formatting for default messages and show the available list of values to the end-user. This presents the list of values in a button template for the supported channels.
    • Type: Select List of Items (enumerated) from the drop-down list.
    • Provide the list of values that the user can select.
      1. Click the Settings icon that appears next to the field.
      2. Under the Account Type section, select the Static List radio button.
      3. Under the Keys & values to use section, enter
        1. the Display Name as Savings and Current. 
        2. Value and Synonym columns will auto-populate. Change the Value to savings and current, since our mockapi has the account type saved in lowercase.
      4. Click Save on the top-right of the page.
    • Close the AccountType Entity Property window.

Bot Action – Service Node

Service Node allows you to make a backend API call and is under Bot Action.

Here, the service node is used to call an API to fetch the account balance for the user-entered account number. You can find a dummy API setup for this tutorial. A mock API is created specifically for this purpose with the following fields – FirstName, LastName, Address, City, Country, ZipCode, AccountNumber, AccountType, Balance.

  1. From the left pane, drag and drop the Bot Action node below the Account Type entity node.
  2. The newly created Bot Action node would be expanded. If not, click the + icon to expand
  3. From the left pane, drag and drop the Service node to the Bot Action node layout,
    or on the Bot Action node layout, click the + icon and select Service from the list, and click + New Service.
  4. A Service node is added to the Bot Actions node layout.
  5. Click the Service node to open its Property window.
  6. Under the General Settings section, enter the following details:
    • Name: GetAccountBalance
    • Display Name: Get Account Balance
    • Description: Enter a description to describe the service node.
    • Click DEFINE REQUEST.
      • On the Define Request page, enter the following details:
        • Request typeGET
        • Request URLhttps://5c3c633d29429300143fe4d2.mockapi.io/AccountDetails?filter={{context.entities.AccountNumber}}
          Due to the limitations of the dummy API service, instead of fetching the record for the given account number, the response is filtered for the required account number.
        • This API does not require any Auth, or Header Parameters.
        • Click the Test Request tab.
        • Enter an account number in the Sample Context Values section. This is the filter parameter needed by the API, you can use the following account number 02929664.
        • Click Test on the top-right of the page. Wait for the test to be completed and you get a Status Code: 200.
        • You can see an array of records returned by the API call. In the next step, values are parsed using JavaScript.
        • Click Save as Sample Response.
        • Click Save on the top-right of the page.
  7. On the Service node Property window, click the Connections tab.
    • Under the Connection Rules section, ensure that the Default connection is set to End of Bot Action.
  8. Close the Service Property window.
  9. Click  next to the Bot Action node to collapse the bot action node.

Message Node

A Message node displays a message from the bot to the user. Here, the Message node is used to show the balance.

  1. From the left pane, drag and drop the Message node below the Bot Action node, or click the + icon below the Bot Action node.
  2. Select Message from the list and click + New Message.
  3. Click the Message node to open its Property window.
  4. Enter the following details:
    • Name: BalanceMessage
    • Display Name: Balance Message
    • Bot Responses: Define a standard message to send to the user.
      • Click Manage.
      • On the Manage User Prompts page, you can find the user prompt.
      • Open the user prompt to define JavaScript to parse the message for all channels.
      • Under the Channels section, select All from the drop-down list. Refer to the image below.
        • Under the Message section, click the Advanced tab.
        • Add the following JavaScript. The JavaScript is written to compare all the records filtered for the AccountType as entered by the user and then display the Balance.
          var balance, i;
          for (i=0; i < context.GetAccountBalance.response.body.length; i++ )
          { if (context.GetAccountBalance.response.body[i].AccountType == context.entities.AccountType)
             { balance = context.GetAccountBalance.response.body[i].Balance;
             }
          }
          if (balance === undefined)
              { print ('Invalid Account, try again ');
              }
          else
              {
              print ('The Balance in your account is ' + balance);
              }
        • Click Save
  5. Go back to the Dialog Builder.
  6. On the Message node Property window, click the Connections tab.
    • Under the Connection Rules section, change the Default connection from Not Connected to End of Dialog.
  7. Close the Property window.

Test

To test the dialog task, you can use the Talk to bot option at the bottom-right.

  1. Enter the following utterance (intent name) Get Balance.
  2. Follow the bot instructions:
    • Enter Account Number – 67846279
    • Select Account Type – Savings
  3. See the Account Balance.

Next Steps

Now that you have added the Get Balance dialog task to the Banking bot, the next step is to add the Update Balance task. For convenience, the steps for Update Balance are split into different documents. Click here to continue.

Creating a Banking Assistant

This document helps you create a sample banking bot. This bot is used in various use case scenarios presented in the How-Tos section of the developer documentation.

Prerequisites

The following are the prerequisites:

  • You must have signed up with the Kore.ai Bots Platform.
  • You must be aware of the basics concepts of bot-building (refer to this link).
  • You must have created a simple bot (refer here for an example).

Bot Overview

The bot we build will perform the basic banking transactions. This bot will:

  • Get account balance based on the user’s Account Number and Account Type.
  • Update accounts with the balance. For more information, click here.
  • Transfer a specified amount from the user account to a payee account. For more information, click here.

Let us start building the bot and add Get Balance task to it.

Create a Bot

This document helps you to create a Standard Bot for banking activities. To create a standard bot, follow the below steps:

  1. Log in to your Kore.ai Bots Platform with valid credentials.
  2. On the bots landing page, click New Bot on the top-right and select Start from Scratch from the list.
  3. On the Create New Bot window, enter the bot details:
    1. Bot Name – Provide a name to your bot. For example, Banking Bot. If the name is already used, provide a different name.
    2. Set the Default Bot Language to English.
    3. Select the Bot Type as Standard Bot.
  4. Click Create.

Get Balance Intent

  • The Get Balance task prompts the user to enter an account number and the account type (Savings/Current).
  • It makes a service call to fetch the details.
  • The balance for the requested account is displayed.

Dialog Task

Successful creation of the bot directs you to the Bot Summary page. We need to add a Dialog Task as the first step in the Bot. Intent Dialog is the first step in the user-bot conversation flow.

  1. On the Bot Summary page, click + New Task on the Tasks widget.
  2. Select Dialog Task from the list.
  3. On the Create Dialog window, enter the following details:
    • Enter a name in the Intent Name field. This is the phrase that triggers the dialog. The intent name must be simple and not more than 3-4 words. For example, Get Balance.
    • Enter a description in the Description field.
    • In the Intent Training field, add unique utterances to improve the user intent recognition.
    • Under More Options, you can add other dialog-related details. Let us retain the default settings.
    • Select Try Conversation Driven Dialog Builder option.
  4. Click Proceed.
    Note: For instructions with the older Dialog Builder, refer here

Entity Node

Entity Node is typically used to gather information from the user. Here, it is used to capture the user input for Account Number and Account Type.

  1. Click the + icon below the User Intent (Get Balance) node.
  2. Select Entity from the list and click + Entity.
  3. Click on the newly created Entity node to open the Property window.
  4. Under the General Settings section, enter the following details:
    • Name: AccountNumber
    • Display Name: Account Number 
    • Type: Number
    • User Prompts: Enter the following text and press Enter to save:
      Enter the account number.

  5. Close the AccountNumber Entity Property window.
  6. Repeat the above steps to add another entity with the following details:
    • Name: AccountType
    • Display Name: Account Type 
    • User Prompts: Enter the following text and press Enter to save:
      Enter the account type.
    • Display List Of Values: Select Yes, use channel-specific standard formatting for default messages and show the available list of values to the end-user. This presents the list of values in a button template for the supported channels.
    • Type: Select List of Items (enumerated) from the drop-down list.
    • Provide the list of values that the user can select.
      1. Click the Settings icon that appears next to the field.
      2. Under the Account Type section, select the Static List radio button.
      3. Under the Keys & values to use section, enter
        1. the Display Name as Savings and Current. 
        2. Value and Synonym columns will auto-populate. Change the Value to savings and current, since our mockapi has the account type saved in lowercase.
      4. Click Save on the top-right of the page.
    • Close the AccountType Entity Property window.

Bot Action – Service Node

Service Node allows you to make a backend API call and is under Bot Action.

Here, the service node is used to call an API to fetch the account balance for the user-entered account number. You can find a dummy API setup for this tutorial. A mock API is created specifically for this purpose with the following fields – FirstName, LastName, Address, City, Country, ZipCode, AccountNumber, AccountType, Balance.

  1. From the left pane, drag and drop the Bot Action node below the Account Type entity node.
  2. The newly created Bot Action node would be expanded. If not, click the + icon to expand
  3. From the left pane, drag and drop the Service node to the Bot Action node layout,
    or on the Bot Action node layout, click the + icon and select Service from the list, and click + New Service.
  4. A Service node is added to the Bot Actions node layout.
  5. Click the Service node to open its Property window.
  6. Under the General Settings section, enter the following details:
    • Name: GetAccountBalance
    • Display Name: Get Account Balance
    • Description: Enter a description to describe the service node.
    • Click DEFINE REQUEST.
      • On the Define Request page, enter the following details:
        • Request typeGET
        • Request URLhttps://5c3c633d29429300143fe4d2.mockapi.io/AccountDetails?filter={{context.entities.AccountNumber}}
          Due to the limitations of the dummy API service, instead of fetching the record for the given account number, the response is filtered for the required account number.
        • This API does not require any Auth, or Header Parameters.
        • Click the Test Request tab.
        • Enter an account number in the Sample Context Values section. This is the filter parameter needed by the API, you can use the following account number 02929664.
        • Click Test on the top-right of the page. Wait for the test to be completed and you get a Status Code: 200.
        • You can see an array of records returned by the API call. In the next step, values are parsed using JavaScript.
        • Click Save as Sample Response.
        • Click Save on the top-right of the page.
  7. On the Service node Property window, click the Connections tab.
    • Under the Connection Rules section, ensure that the Default connection is set to End of Bot Action.
  8. Close the Service Property window.
  9. Click  next to the Bot Action node to collapse the bot action node.

Message Node

A Message node displays a message from the bot to the user. Here, the Message node is used to show the balance.

  1. From the left pane, drag and drop the Message node below the Bot Action node, or click the + icon below the Bot Action node.
  2. Select Message from the list and click + New Message.
  3. Click the Message node to open its Property window.
  4. Enter the following details:
    • Name: BalanceMessage
    • Display Name: Balance Message
    • Bot Responses: Define a standard message to send to the user.
      • Click Manage.
      • On the Manage User Prompts page, you can find the user prompt.
      • Open the user prompt to define JavaScript to parse the message for all channels.
      • Under the Channels section, select All from the drop-down list. Refer to the image below.
        • Under the Message section, click the Advanced tab.
        • Add the following JavaScript. The JavaScript is written to compare all the records filtered for the AccountType as entered by the user and then display the Balance.
          var balance, i;
          for (i=0; i < context.GetAccountBalance.response.body.length; i++ )
          { if (context.GetAccountBalance.response.body[i].AccountType == context.entities.AccountType)
             { balance = context.GetAccountBalance.response.body[i].Balance;
             }
          }
          if (balance === undefined)
              { print ('Invalid Account, try again ');
              }
          else
              {
              print ('The Balance in your account is ' + balance);
              }
        • Click Save
  5. Go back to the Dialog Builder.
  6. On the Message node Property window, click the Connections tab.
    • Under the Connection Rules section, change the Default connection from Not Connected to End of Dialog.
  7. Close the Property window.

Test

To test the dialog task, you can use the Talk to bot option at the bottom-right.

  1. Enter the following utterance (intent name) Get Balance.
  2. Follow the bot instructions:
    • Enter Account Number – 67846279
    • Select Account Type – Savings
  3. See the Account Balance.

Next Steps

Now that you have added the Get Balance dialog task to the Banking bot, the next step is to add the Update Balance task. For convenience, the steps for Update Balance are split into different documents. Click here to continue.

Menu