Deploy Bots with CXone 机器人生成器

CXone 机器人生成器 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 models关闭 经过训练和上演的机器人版本. 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 > Digital Experience > 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 model关闭 经过训练和上演的机器人版本 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. 在 CXone 中单击应用程序选择器 并选择机器人生成器.

  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 model关闭 经过训练和上演的机器人版本 you want to deploy, click the drop-down and select Deploy to Stage.

Deploy to Production

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

If your bot关闭 代替现场人工坐席处理客户交互的软件应用程序。 is handling a channel where SLA关闭 服务提供商和客户之间的回电，具有确定的服务水平阈值，包括质量、可用性和责任 is important, you should set up an automated safety net before you deploy the bot.

Deploying a model关闭 经过训练和上演的机器人版本 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. 在 CXone 中单击应用程序选择器 并选择机器人生成器.

  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 model关闭 经过训练和上演的机器人版本 you want to deploy, click the drop-down and select Deploy to Production.

Go Online

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

At any time, you can switch from Offline to Online. You only need to do this once. Once your bot关闭 代替现场人工坐席处理客户交互的软件应用程序。 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 model关闭 经过训练和上演的机器人版本 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 inbox关闭 在坐席应用程序的数字交互工作区中出现案例的区域 from the routing queue关闭 相当于一种技能的 Digital First；将每个联系人转接到分配处理该类联系人的坐席 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.