Deploy Bots with CXone Bot Builder

CXone Bot Builder uses a two-stage deployment process, so you can deploy to either stage or production. This process lets you:

Typically, one model is deployed to stage and one model is deployed to production. Sometimes it is the same model. In most cases, you'll deploy the model that is currently in stage to production. However, you can deploy any model to production regardless of whether it is currently in stage. You can easily see which models are in which environments on the Training and Deployment page.

Training and Deployment Page

The Training and Deployment page, showing several models for one bot and their current training or deployment states.

The Training and Deployment page displays a list of all your trained bot modelsClosed Version of a bot that has been trained and staged. Each row in the list shows the duration, timestamps, and status of the training and deployment. You can also use the Actions column to:

  • Deploy to stage or production.
  • Cancel a training or deployment that is in progress.
  • View Info on a training that experienced an error or was cancelled.
  • Export a model to your local machine as a YML file.

Complete each of the following tasks in the order given. All tasks are performed in the Digital Experience portal.

Deploy to Stage

Required permission: Chatbot (ACD > DFO > Roles > [choose one] > Core Modules)

Every time you click the Train and Stage button, your bot is deployed to stage.

If you are making improvements to a bot that's been deployed to production, Train and Stage creates a new bot modelClosed Version of a bot that has been trained and staged and deploys that model to stage. If you want your improvements to be reflected in production, you need to manually deploy this new model. This ensures no bot model enters production without your explicit consent.

You can also deploy a model to stage from the Training and Deployment page:

  1. In CXone, click the app selector and select Bot Builder.

  2. Click the bot you want to work with.
  3. Click Deployment icon, which looks like an arrow that splits into two directions. in the left icon menu.
  4. In the Actions column for the modelClosed Version of a bot that has been trained and staged you want to deploy, click the drop-down and select Deploy to Stage.

Deploy to Production

Required permission: Chatbot (ACD > DFO > Roles > [choose one] > Core Modules)

If your botClosed A software application that handles customer interactions in place of a live human agent. is handling a channel where SLAClosed Commitment between a service provider and a customer with a defined service level threshold, including quality, availability, and responsibilities is important, you should set up an automated safety net before you deploy the bot.

Deploying a modelClosed Version of a bot that has been trained and staged to production sends that configuration and data to the bot user in CXone. This does not mean the bot will immediately become active and start receiving cases. You still need to go online, just like a live agent would.

You deploy a model to production from the Training and Deployment page.

  1. In CXone, click the app selector and select Bot Builder.

  2. Click the bot you want to work with.
  3. Click Deployment icon, which looks like an arrow that splits into two directions. in the left icon menu.
  4. In the Actions column for the modelClosed Version of a bot that has been trained and staged you want to deploy, click the drop-down and select Deploy to Production.

Go Online

Required permission: Chatbot (ACD > DFO > Roles > [choose one] > Core Modules)

At any time, you can switch from Offline to Online. You only need to do this once. Once your botClosed A software application that handles customer interactions in place of a live human agent. is online, it doesn't need to go offline. Typically, your bot's availability to bring in new cases will be handled by the routing queue you assigned it to.

  1. Click Preferences icon, which looks like a gear. in the left icon menu.
  2. On the Settings tab, click General.
  3. Click the drop-down and select Online.

From this point, your bot modelClosed Version of a bot that has been trained and staged that is deployed to production will behave just as live agents do when they are online. CXone assigns new incoming cases to the bot's digital inboxClosed Area where cases appear in the digital interaction workspace in an agent application from the routing queueClosed Digital First equivalent of a skill; routes each contact to an agent assigned to handle that type of contact the bot is assigned to. If your bot is deployed to production and is online, but is still not receiving cases, you may need to check the routing configuration.