Chatlayer Documentation
Get in touchAbout Chatlayer
  • Welcome
  • What's new
  • Send feedback
  • start quickly
    • Leadzy tutorial
      • 0. Introduction
      • 1. New bot, new block
      • 2. Understand your users
      • 3. Collect and display user input
      • 4. Steer the conversation with Conditions
      • 5. Empower your bot with Actions
      • 6. Set up a channel and publish your bot
    • Templates
      • Banking
      • E-Commerce Returns
      • E-Bike Shop
      • E-Scooter Support
      • Feedback
      • Find Nearest Location
      • GPT
      • 🆕Gym
      • Job applications
      • Knowledge base AI template
      • Lead generation
      • 🆕NPS
      • Restaurant
      • Retail
  • navigation
    • Analytics
      • Dashboard
      • Customers
      • Conversations
      • User flow
      • Intents
      • 🆕Funnels [Beta]
    • Bot builder
      • Flows
        • Canvas functionalities
        • Collaborate with team members
        • Manage your flows
        • 🆕[Beta] Export and import flows
      • Bot dialogs view
      • Translations
      • Events
    • NLP
      • Dashboard
      • Intents
      • Expressions
      • Entities
      • Train
      • NLP settings
      • Improve
    • Knowledge base AI
      • Add content to your KBAI
      • Build your KBAI flow
      • Use your KBAI source URL in a button
      • Use tags to limit your KBAI content
      • 🆕Use Tables to store your KBAI questions
      • 🆕Manage handover where KBAI is unsatisfactory
    • History
      • Conversations
      • Execution logs
      • Versions
    • Channels
    • Tables
      • Create a table with records
      • Column types
      • Operate on your records
        • Insert record
        • Update record
        • Retrieve record
        • Delete record
      • API
    • Settings
      • Bot settings
      • Offloading
      • Variables
      • Voice
      • Import/Export
  • build your bot
    • Conversation design
      • Plan your bot
      • Conversation design workflow
    • Flow logic
      • Blocks
        • Message
        • Condition
        • Collect input
        • Action
      • Go-to connections
    • 🆕Emulator
    • Tips & best practices
      • Route your flow depending on the time
      • Improve the Not understood block
        • How to create better not understood messages
        • Not understood counter
        • Not understood Google search
      • Go to previous block
      • Recognizing a returning user
      • Skip introduction message
      • Route your flow depending on the channel
      • Reuse flows
      • Connect two bots to each other
  • understand users
    • Natural language processing (NLP)
      • Basic NLP concepts
      • Detect information with entities
        • Match entities
        • Contextual entities
        • System entities
        • Composite entities
      • NLP best practices
        • Word order and diversity of expressions
      • AI intent booster
      • Train your NLP
      • Context
      • NLP import & export
      • Sentiment analysis
    • Languages
      • Supported languages
      • Make your bot multilingual
      • Change language within the conversation
  • set up channels
    • Add a channel to your bot
    • All channels
      • 🚨Facebook Messenger [Deprecated soon]
        • Facebook Admin Removal
        • Facebook Webview Whitelisting
        • Facebook Messenger API updates for Europe
      • 🚨Google Assistant [Deprecated soon]
      • Webhook
      • Web
        • 🚨Web V1 [Deprecated]
          • Customize web widget
          • Live example web widget
        • 🆕Web V2
          • 🆕From Web V1 to V2
          • 🆕Web V2 methods and options
    • Sinch Conversation API
      • Configure your Sinch Conversation API
      • 🆕 Make the most of RCS with Carousels
      • WhatsApp Business API
  • integrate & code
    • API calls
      • Configure your API integration
      • Advanced API features
      • V1 API Reference
      • Custom integrations 101
    • Code editor
      • [Example] Sending data to Airtable (POST)
      • [Example] Retrieving data from Airtable (GET)
      • [Example] Making SOAP requests
    • App integrations
      • Airtable
      • Freshdesk
      • Freshdesk Messaging
      • 🆕Gmail
      • Intercom
      • Mailgun
      • OpenAI: GPT-3, ChatGPT and GPT-4
      • Salesforce
      • 🆕Slack
      • Topdesk
      • Zendesk Support
      • Zendesk Sunshine (beta)
    • 🆕Expression syntax
    • Human handover & live chat
      • Sinch Contact Pro
      • #Interact
      • Genesys Cloud
      • Offloading Webhook
      • Salesforce Service Cloud
      • Sparkcentral by Hootsuite
      • Zendesk Chat
    • Chatlayer messages specifications
  • Publish
    • Publish your bot
      • Publish a flow
  • Analyze & maintain
    • Analytics definitions
    • Data retention
    • Maintenance
    • Session
    • Track events for analytics
  • VOICE
    • 🆕Send bot response as audio
    • Voicebots
      • Create a voicebot
      • Voicebot-specific actions
      • Test your voicebot
      • From chat to voice
  • access & support
    • Identity & Access
      • Single Sign-On (SAML SSO)
    • Billing & subscription
    • Get in touch
    • Chatlayer glossary
    • SaaS Regions & IP Ranges
    • Status
    • Debug your bot
      • No correct response
      • Collect input not working
      • Video isn't working
Powered by GitBook
On this page
  • Understanding the DRAFT version
  • Understanding the LIVE version
  • Publishing options
  • 1. Publish
  • 2. Publish selected flow
  • 3. Publish NLP
  • Maintaining the bot

Was this helpful?

  1. Publish

Publish your bot

Is your bot ready to go live and start talking to your users? Great, on this page we'll tell you how to push your bot live and make changes without breaking it.

PreviousChatlayer messages specificationsNextPublish a flow

Last updated 2 months ago

Was this helpful?

Please note that are not published from the DRAFT to the LIVE version of your bot. If you would like to have the same data retention settings in your LIVE version as in your DRAFT version, please set up the data retention on that version directly.

Understanding the DRAFT version

When you're building your bot, you do so in the DRAFT version of that bot. When you surf to , you always start building in DRAFT.

The DRAFT version is the one you use to build your bot. It's where you can make changes to the bot, test out flows, and work on the NLP. Once you're happy with your bot and want to push it towards your customers, you need to publish a LIVE version of your bot.

As part of the latest update, you now have the convenience of switching between live and draft mode using a simple button located on the top navigation bar.

Understanding the LIVE version

After publishing your bot, you can view the published version under the 'History' tab to keep track of all the changes made and when they were published.

Switching to the live version provides you with immediate access to the latest version of your bot, including all the flows you have just published. This version of your bot users will interact with, and any changes made to it will have an immediate impact.

We recommend not changing any data or configurations directly in your LIVE environment as this can break the bot that your customers are actively using.

Publishing options

There are three distinct publishing options:

  1. Publish: This action releases both flows and NLP to the live version.

  2. Publish Selected Flows: Use this option to publish specific flows only. NLP will remain unaffected.

  3. Publish NLP: Select this option when you want to publish only your NLP, leaving the flows unchanged.

1. Publish

  • Once your changes are complete, simply click on the 'Publish' button located next to the live/draft switcher button and select the 'Publish' option to make your updates live and visible to the live version.

  • Before publishing your chatbot, it is important to ensure that your NLP model is up-to-date. To make this process easier, we have added an 'Update NLP' button which can be found in the 'Publish' menu. Don't forget to update your NLP model to ensure that your chatbot provides the best possible experience for your users.

  • When creating a new version of your bot, you can add notes to help you keep track of the changes made in that specific version. This is especially handy when multiple people are working on the same bot.

Depending on the size of your bot, publishing could take a while. Relax, your bot is on its way!

2. Publish selected flow

3. Publish NLP

Publishing your NLP model has never been easier. Simply click the 'Publish' button and select 'Publish NLP' to make your NLP model live.

Take into account that:

  • You must have published to the live version at least once.

  • The NLP needs to be trained before publishing it.

  • You cannot publish just the NLP if no NLP changes have been made since the last publish.

  • You cannot publish just the NLP if intents have been removed from your DRAFT version since the last publish. This is to avoid showing flows that are linked to intents that no longer exist. That means that removing intents from the LIVE version is only possible through 'Publish full bot'. Adding new intents to LIVE with 'Publish NLP Only' on the other hand, is possible.

Different NLP models in different environments will never be 100% identical. There are random factors inherent to this kind of machine learning that create different results, even with the same data. These differences are usually small, but in some cases where intents are very similar, the differences can be more apparent and lead to significant differences in confidence or entirely different classifications.

Maintaining the bot

Once your bot is live and users are talking to it, you can keep making changes to your bot in the DRAFT version. Once your changes are final, you can publish a new LIVE version of your bot. The existing version of your LIVE bot will then be overwritten with your current DRAFT version.

Now you can select a specific flow to publish. This can be useful if you only want to make updates to a specific flow and don’t want to publish the entire project. Please read the full documentation .

here
data retention
app.chatlayer.ai