Just getting started? Complete the Using Conversation Assist tutorial.

It takes up to 3 hours for changes in Conversation Assist configuration to take effect.

Supported bot types

  • Bots created in LivePerson Conversation Builder
  • Bots created in Google Dialogflow ES and CX
  • Bots created in IBM Watson Assistant v1 and v2
  • Any third-party bot made available via LivePerson Functions (FaaS) or a custom endpoint

Prerequisite knowledge

To set up Conversation Assist to recommend bots, you need some prerequisite knowledge of other applications in the Conversational AI suite.

If you intend to build your bots using Conversation Builder, you must be able to use Conversation Builder to create and deploy a bot. And if, for utterance matching, you’ll be using intents instead of patterns, you must also be able to use Intent Manager to create a domain and the intents. For exposure to these applications and tasks, we recommend that you complete the Getting Started with Bot Building - Messaging tutorial series.

If you intend to build your bots using a third-party application, see the Getting Started info.

High-level workflow

  1. In Conversation Builder or the third-party application, create the bots.
  2. In Conversational Cloud, create the skills and bot users.
  3. In Conversation Builder, deploy the Conversation Builder bots. Or, in Third-Party Bots, connect the third-party bots.
  4. In Conversation Assist, configure the bots for Conversation Assist.
  5. In Conversation Assist, configure relevant settings.

Step 1: Create the bots

Access Conversation Builder and create at least one bot. For help, try the tutorial.

For help with creating a third-party bot, see the Getting Started info.

Step 2: Create the bot users

Configure Conversational Cloud by creating a bot user for each bot. This is illustrated in the Conversation Assist tutorial. Specify a bot user name that make sense for your use case.

Step 3: Deploy the bots

If you've created Conversation Builder bots, then use Conversation Builder to deploy the bots. This is illustrated in the Conversation Builder Deploy the Bot tutorial. When you add the agent connector for the bot, be sure to select to allow Messaging conversations. And after adding the agent connector, be sure to start it to enable the bot to handle traffic.

To connect a Google Dialogflow or IBM Watson bot to LivePerson’s Conversational Cloud, follow the Getting Started Guide for third-party bots. Then follow the specific guide for the vendor you're using. Be sure to press the play button in the bot dashboard to enable the bot.

Step 4: Configure the bots

  1. Access Conversation Assist, and click Recommendation Sources from the menu at the top.
  2. Click the Bots tab.
  3. Click Sync button over on the right. This fetches the available bots. Available bots include those you’ve deployed and started (i.e., they’re valid bots that can serve a conversation). You should see all of the bots that you’ve created (both public and private) and other public bots within your organization.

    Bots tab showing a list of bots and an indicator pointing to one bot that is turned off

  4. Verify that your bot is displayed. If it isn't, consult the troubleshooting info.

    Your bot doesn't have any assigned skills yet, so its Status is initially set to "Off." For the bot to be recommended in conversations, you must assign one or more skills and change the Status.

  5. Assign one or more skills to the bot:
    1. Beside the bot, click the Pencil icon (Manage source) icon.

    2. In the Manage recommendation source dialog, change the Status to "ON," enter a description of the bot's capabilities, and add one or more skills.

      Manage recommendation source window with options for turning the bot on and off and for assigning skills

    3. Click Save.

  6. Repeat this process for additional bots as needed.

    After you assign at least one skill to each of the bots, the bots can be recommended in conversations that are routed to the same skills. In this manner, you can control on a skill-by-skill basis which bots are candidates for recommendation to human agents.

    In our example below, for the agent to be recommended the Ordering Bot, the agent must pick up a conversation that was routed to either the “Support” or “Ordering” skills.

    Bots tab with all bots now turned on

    Keep in mind that a conversation is routed to the skills assigned to the campaign’s engagement.

If you later change the bot user for a bot, you’ll need to manually refresh the bot list here within Conversation Assist so that the configuration change is picked up. This avoids issues that might occur. Similarly, if you delete a bot, you’ll also need to refresh the bot list so that the bot is removed from it.

Step 5: Configure settings

  1. Access Conversation Assist, and click Settings.
  2. Configure relevant settings.