Screenshot of the LivePerson Maven bot platform.
Conversation Service Provider Conversation LivePerson came out with a new platform that relies on customer service agents who work with AI to create and orchestrate chatbots.
"We now know," said founder and CEO Robert LoCascio, "that people in contact centers, who converse with consumers every day, are the best conversation designers for AI."
How can customer agents install it? Called Maven the new platform uses AI to track text-mode conversations between users and agents via SMS, Facebook Messenger, WhatsApp and others. canals.
A new conversation builder allows agents and other users to map chatbot conversations for frequent interactions. Here is a screen showing a conversation built from a previous conversation:
Conversations on frequent topics can exploit transcripts of previous conversations of a mark. In addition, there are predefined model-based conversations, such as billing, that agents can select and edit. Chief Scientist, Joe Bradley, commented that this type of building does not rely on menus, which allows for directing the conversation flow in a manner unrelated to the Mark.
How are chatbots deployed? During a live conversation between an agent and a user, Maven determines the intent of the conversation and may recommend the following actions or specific chatbots to resume the conversation. ]
Bradley added that LivePerson was deploying various special chatbots, such as those designed to transmit the status of an order, make a purchase or change an address.
For example, if the agent explains the status of the order, Maven can suggest the command-oriented chatbot already built by the brand. (See the screenshot at the top of this page.) When the conversation moves to another topic, the chatbot sends the conversation back to the live agent.
When comments from Maven and agents determine that the use of a given chatbot has reached a level of precision defined by the mark in terms of responding to the user, the transfer The chatbot can be automatic the next time a live text chat becomes this topic.
Maven's recommendation of a chatbot in a conversation may include chatbots from other integrated platforms, such as Dialogflow, Watson, and Amazon from Google. The conversation of these chatbots will then be available in Maven. Bradley pointed out that, if LivePerson already had the ability to integrate with other chatbot platforms, he could not recommend their chatbots before.
Why you should care Customer service is now another form of marketing. As a result, customer service agents need to respond quickly, on a large scale and with knowledge on a wide range of topics, a task that can be supported by intelligent platforms and automated discussion engines.
This story was first published on MarTech Today. For more information on marketing technology, click here.
About the author
Barry Levine covers marketing technology for Third Door Media. Previously, he covered this space as a senior editor for VentureBeat, and he wrote on these technical topics, among others, for publications such as CMSWire and NewsFactor. He founded and managed the website / unit of PBS Thirteen / WNET; worked as a Senior Producer / Writer Online for Viacom; created a successful interactive game, PLAY IT BY EAR: The first CD game; founded and directed an independent film, CENTER SCREEN, based at Harvard and M.I.T .; and served for five years as a consultant to the M.I.T. Media Lab. You can find it on LinkedIn and Twitter on xBarryLevine.