Conversation Assist — Setting Up Bots | LivePerson Developer Center (2024)

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 you’ll be using intents to match consumer utterances to dialog flows, 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 this Getting Started info.

High-level workflow

1. In Conversation Builder or the third-party application, create the bot.
2. In Users & Skills, create the skill and bot user.
3. In Conversation Builder, deploy the Conversation Builder bots. Or, in Third Party Bots, connect the third-party bots.
4. In Conversation Assist, create bot-level recommendation rules.
5. In Conversation Assist, configure relevant settings.

Step 1: Create the bot

Create at least one bot.

Step 2: Create the bot user

In Users & Skills, create a bot user for the 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 bot

If you've created a Conversation Builder bot, then use Conversation Builder to deploy the bot. 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 third-party bot, follow this Getting Started Guide. 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: Create bot-level recommendation rules

In this step, you create the rules that determine when the bot is offered as a recommendation to agents.

Rules affect 1) recommendations offered in line in conversations and 2) recommendations offered in the On-Demand Recommendations widget.

1. Access Conversation Assist, and click Recommendation Sources.
2. Click the Bots tab.
3. Click Add rule.
4. Define the rule that determines when the bot(s) are recommended to agents. Each rule element is described farther below.
5. When the bot is added to and removed from a conversation, you need to notify the consumer. Specify the messages to use.
6. Click Save and activate.
7. Add additional rules as required.

Rule elements - general

• Name: Enter a short, meaningful, and unique name that highlights the rule’s basic function and purpose.
• Description: If desired, provide a more in-depth description of the rule: rationale, approach, i.e., anything that’s useful.

• Skills: Select the Conversational Cloud skills that you want this rule to apply to. You must specify at least one skill. A skill can be used in only one bot rule.

  In conversations routed to these skills, bots listed in this rule will be offered as recommendations. (A conversation is routed to the skills assigned to the campaign's engagement.)

Rule elements - add-ons

A rule add-on completes the rule’s definition. You must define at least one rule add-on because, at a minimum, that’s where you specify the bots to use in the rule.

If you define multiple add-ons, the order of the add-ons matters: At runtime, the add-ons are evaluated in order, and the first one that’s matched is executed. So, order the add-ons as required.

• Agent groups AND/OR profiles: You can further limit bot recommendations to specific Conversational Cloud agent groups and/or profiles. Or, if the rule will be only skill-based, leave these blank.
• Recommend bots {bot names} with min. confidence {score}: Specify here the bots that are in play. Also specify the minimum confidence score that the bot must have to be retrieved. The higher the score, the more relevant the match. To increase the likelihood of a matched bot, try a lower score.

Example rule

Our example rule below is for a fictitious, national automotive brand named Acme Auto. The rule is for a single skill named Support, which the brand assigns to all of its customer support agents.

Acme Auto agents are highly specialized, so the brand divides its agents into two Conversational Cloud agent groups:

• ICE Support for handling FAQs about cars with an internal combustion engine (ICE)
• EV Support for handling FAQs about electric vehicles (EV)

Thus, the rule includes two add-ons:

The first add-on is for offering the ICE Car Finder bot as a recommentation to agents in the ICE Support agent group. The second add-on is for offering the EV Car Finder bot as a recommendation to agents in the EV Support agent group.

So, for example, for an agent to receive the EV Car Finder bot as a recommendation, the following must happen:

• The agent must pick up a conversation that is routed to the Support skill. (A conversation is routed to the skills assigned to the campaign's engagement.)
• The agent must be in the EV Support agent group.

As mentioned earlier, the order of the add-ons matters: At runtime, the add-ons are evaluated in order, and the first one that’s matched is executed. So, in our example here, if the agent were a member of both groups, the agent would never receive the EV Car Finder bot as a recommendation because the first add-on (for the ICE Support agent group) always evaluates to true for the agent.

Learn more about how recommendations are made.

Step 5: Configure settings

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