Chatbot Overview
Conversational Bots
Intents & Entities
Intelligent Bots's Approach Conversational Platform
Bot Concepts and Terminology
Natural Language Processing (NLP)
Bot Types
Bot Tasks
Starting with Platform
How to Access Bot Builder
Working with Bot Builder
Building your first Bot
Getting Started with Building Bots
Using the Dialog Builder Tool
Creating a Simple Bot
Release Notes
Latest Updates
Older Releases
Bot Builder
Creating a Bot
Dialog Task
Working with User Intent Node
Working with the Dialog Node
Working with Entity Node
Supported Entity Types
Working with Composite Entities
Supported Time Zones
Supported Colors
Supported Company Names
Working with Message Nodes
Working with the Confirmation Nodes
Working with Service Node
Implementing Custom Authentication
Enabling 2-way SSL for Service nodes
Working with Script Node
Working with Agent Transfer Node
Working with WebHook Node
Defining Connections & Transitions
Managing Dialogs
Prompt Editor
Action & Information Task
Working with Action Tasks
Working with Information Tasks
Establishing Flows
Alert Tasks
Working with Alert Tasks
Managing Ignore Words and Field Memory
Knowledge Graph
Building Knowledge Graph
Generation of Knowledge Graph
Importing and Exporting Knowledge Graph
Knowledge Graph Analysis
Knowledge Extraction
Natural Language
Machine Learning
ML Model
Fundamental Meaning
Knowledge Graph Training
Ranking and Resolver
NLP Detection
NLP Settings and Guidelines
Bot Intelligence
Context Management
Session and Context Variables
Context Object
Dialog Management
Amend Entity
Multi-Intent Detection
Sentiment Management
Tone Analysis
Sentiment Management
Default Conversations
Default Standard Responses
Channel Enablement
Test & Debug
Talking to Bot
Utterance Testing
Batch Testing
Recording Conversations
Publishing your Bot
Analyzing your Bot
Custom Dashboard
Conversation Flows
Bot Metrics
Advanced Topics
Bot Authorization
Language Management
Collaborative Development
IVR Integration
Universal Bots
Enabling Languages
Smart Bots
Sample Bots
Travel Planning
Flight Search
Event Based Bot Actions
Bot Settings
Bot Functions
General Settings
PII Settings
Customizing Error Messages
Bot Management
Using Bot Variables
API Guide
API Overview
API List
API Collection
SDK Overview
SDK Security
SDK App Registration Web SDK Tutorial
Message Formatting and Templates
Mobile SDK Push Notification
Web Socket Connect & RTM
Using the BotKit SDK
Installing the BotKit SDK
BotKit SDK Configuration
Events for the BotKit SDK
Functions for the BotKit SDK
BotKit SDK Tutorial – Agent Transfer
BotKit SDK Tutorial – Flight Search Sample Bot
Using an External NLP Engine
Bot Administration
Bots Admin Console
User Management
Managing Users
Managing Groups
Managing Role
Bots Management
Inviting Users
Sending Bulk Invites to Enroll Users
Importing Users and User Data
Synchronizing Users from Active Directory
Security & Compliance
Using Single Sign-On
Cloud Connector
How Tos
Context Switching
Using Traits
Live Agent Transfer
Schedule a Smart Alert
Configure Agent Transfer
Custom Dashboard
Patterns for Intents & Entities
Build Knowledge Graph
  1. Home
  2. Docs
  3. Bots
  4. Bot Building
  5. Dialog Task
  6. Custom Meta Tags

Custom Meta Tags

While analyzing your Bot performances, you might want to give preference to or discard a particular scenario. For example, you might want to track how many people are booking tickets to Chicago. Or you might want to track how a specific user, a premium customer, requests are being catered to.

By adding Custom Meta Tags to the conversation flows, you will be able to profile bot user conversations and derive business-critical insights from your bot usage and execution metrics. Tags can be defined as part of the bot definition at any point of interest. When users interact with your bot, the platform will dynamically resolve these tags and adds them to chat transcripts so that you can later filter your conversations, and flows using those tags.

Defining Meta Tags Bot builder platform allows you to add tags to various nodes in a dialog task like dialog node, entity node, etc.

This option is available from the Instance Properties tab

You can define these tags at three levels:

  • User Level: These tags can be added to the user’s profile information to capture user information. For example, to track conversations with a premium customer you will define a user-level tag with the user name or some qualifier as the value.
  • Message Level: These tags can be added to the message of the current node. If the current node is not associated with a message, then the tag gets added to the immediately previous node that has a message associated with it. From the above example, to track bookings to a specific city Chicago, you would be defining a Message Level tag.
    The platform will roll-up these message level tags to task level. That is if a task ends up as ‘Success/Failed Task’, then all the ‘message level’ tags emitted anywhere during the task execution will be associated with the Success/Failed Task event. You can filter Success Tasks as well as Failed Tasks using the message level tags emitted anywhere during the task execution
  • Session Level: These tags can be added at the current session of the user. These can be used to track the conversation sessions from a specific time frame say holiday season or a geographic domain.

You can also define Tags as key-value pairs from Script written anywhere in the application like Script node, Message, entity, confirmation prompts, error prompts, Knowledge Task responses, BotKit SDK, etc. This would be useful if you want conditional tagging.

Be aware that Script tagging would work only if the prompt where you added the tag script is triggered during the conversation.

Following script can be used for adding meta tags:

  • To add a User level tag:
  • To add a Session level tag:
  • To add a Message level tag:

The tagvalue can be a value or a variable name containing the value.

Updating Meta Tag Values

Chances are the Meta Tag values, once assigned, may be modified, for either business or other reasons. In such cases following points need to be noted:

  • The latest value assigned for a key will over-ride the previously assigned value.
  • The updates to the tags follow the following rules:
    • Message-level tags: You may set value for a tag multiple times within the script and the last set value will be assigned against the message. The value cannot be updated after the message is sent to the user
    • Session level tags: Value for a given tag can be set any number of times throughout the session. The last value assigned will be retained and this is the value that you should be using for all analytics purposes. Value cannot be updated after the session is closed.
    • User level tags: Value for a given tag can be set any number of times throughout the session. The last value assigned will be retained and this is the value that you should be using for all analytics purposes. Value can be edited at any time.

Using Meta Tags

Once you have defined the Meta Tags, you can:

  • Use the filter option from Bot Metrics to filter the conversations based upon the Meta Tag values. The export file for the Bot Metrics would include the Meta tag information, too. See here for more.
  • Use the filter option from Bot Builder Dashboard and Admin Console Dashboard to filter the Bot activity details based upon the Meta Tag values.
  • Use to filter the Chat History. Export of Chat History will also include the Meta Tag values. See here for more.
  • Filter the records from Conversation History API and Sessions API by meta tags.