Create a custom bot

LivePerson recommends that —before you create a bot— you set up the domains, intents, and entities that the bot will need. This makes creation of the bot much faster and easier because the NLU Assist tool can use that information along the way to suggest suitable intents and entities to use.

To create a custom bot

  1. If you logged into Conversation Builder directly (that is, not via single sign-on from Conversational Cloud) and you have access to multiple organizations within your Conversational Cloud account, verify in the upper-right corner that the organization under which the bot should exist is displayed. If the correct organization isn’t displayed, select it from the Org Name dropdown list.

  2. From the dashboard that lists your bots, click New Bot in the upper-right corner.
  3. In the dialog box that appears, select the template on which to base the bot.

    The Custom Bot template uses English and includes just a Welcome dialog and a Fallback dialog (see Dialog Types), so it’s ideal if you want to start from scratch. In this case, you’ll be prompted to enter a name and configure a few other settings before the bot is created.

    There are also many, industry-specific, English-language templates available. If you select one of these, all settings are configured for you. We recommend that you change the bot’s name (removing the date and time stamp at a minimum) and review the other settings. For help, see Configure bot settings.

  4. If you selected the Custom Bot template, in the next dialog, specify the following:

    • Name: Enter a name that’s concise and clear. Make sure abbreviations can be understood, and consider adding a prefix or suffix to indicate the environment (Dev, Prod, etc.) or language (En, Sp, Fr, etc.) if applicable.
    • Description: Enter a description that’s meaningful to you and others. Consider including language that identifies the bot's goal and key behaviors
    • Bot Language: This setting identifies the language that the bot will use to respond. Select the language based on how you'll train the bot: If you will use an intent domain, you must select the language of the domain that will be associated with the bot. For example, if the intent domain uses English, select "English" here. If these languages don't match, errors during NLU processing will occur. Alternatively, if the bot will use only pattern matching, you can select or enter any language.
    • Bot Group: Optionally select the bot group for the bot. A bot can be a member of exactly one group.
  5. Build out the bot, completing and adding the necessary dialogs and interactions. As you work, test the bot using the Preview tool.
  6. Save versions of the bot at important points in its development. This allows you to restore a version if you need.
  7. Train and tune things as you do more testing.
  8. Save a version of the final “Development” bot.

    For a Development-to-Production release workflow, see here.