Week of April 24th

Features

Extend your reach with voice bots

Hooray! They’re here: automated voice assistants a.k.a. voice bots.

Voice bots are a powerful way to engage with your consumers through communication that is utterly effortless and natural to them. And there are so many reasons to love them.

Advantages to consumers

• Convenience: Let consumers perform tasks hands-free and without the need for physical input. This is particularly useful in situations where consumers might not be able to use their hands. Driving. Cooking. Anywhere.
• Efficiency: Save consumers time and effort. Voice bots are designed to quickly and accurately perform tasks, such as answering questions or scheduling an appointment. No more long waits on the phone, as you hold for a human agent.
• Personalization: Create and offer more personalized experiences. Voice bots are designed to learn from consumer interactions and tailor their responses accordingly.
• Integration: Tie into third-party systems easily. Check the status of an order. Refill a prescription. Make an appointment. And more.
• Accessibility: Allow people with disabilities to interact with technology in a more natural and accessible way.

Advantages to your brand

• Reduce your overall operating costs by reducing the number of human agent seats that you need, through the increased use of bots with high containment.
• Drive efficiency by letting voice bots take care of simple, repetitive tasks.
• Reduct contact center telephony costs by minimizing the number of telco minutes that you use.
• Increase customer loyalty and lifetime value by improving customer satisfaction (CSAT). You can realize higher CSAT because your consumers can get things done quickly, in their own time. They don’t need to wait for agents to become available during business hours, nor do they need to wait on hold in agent queues.

Key features of Voice bots built in Conversation Builder

• Create English-language (only) voice bots in a variety of accents
• Use the same familiar tool (Conversation Builder) that you use to build messaging bots
• Use text-to-speech (TTS) and/or pre-recorded audio
• Support touch-tone (DTMF) responses from consumers
• Use Speech Synthesis Markup Language (SSML) to achieve a human-like experience: Move from cheerful to empathetic when appropriate, pause, emphasize words, and pronounce words a certain way. Make it Curiously Human™.
• Handle consumer interruptions
• Handle consumer silence
• Send SMS messages (instructions, reminders, links to products, directions to your office, and more)
• Transfers calls to other voice bots
• Transfer calls to humans:
  • Make SIP calls to a contact center over a SIP trunk with context
  • Make calls to a center’s E.164 number over the global public switched telephone network (PSTN)
• Transfer calls to Messaging
• Return enriched answers created via Generative AI (leveraging the knowledge content in your knowledge bases and the latest advancements in Large Language Models (LLMs). Enriched answers make integration of your content simpler and more powerful.

Is your interest piqued?

Check out our 3-minute video for bot builders.

With so many reasons to love voice bots, don’t hesitate to get started:

• If you’re an admin, access the Management Console to enable Voice bots. In the Management Console, search for “Voice bots,” and then use the in-product, self-service onboarding tool. It guides you through the terms and conditions that you must accept, and it allows you to activate the setup process.

Extend your reach to your consumers, and reap the rewards of better business outcomes.

More flexible targeting options when sending automated surveys

In a post-conversation survey bot, the Target Interactive Conversations setting is used to send automated surveys to engaged consumers only. This is a well-used option because you don’t want consumers who aren’t interacting with your brand to negatively impact your CSAT score without cause.

By brand request, for more granular flexibility, we’ve added 2 new configuration options for specifying the minimum number of messages that must be sent by the bot/human agent for the survey to be triggered.

If you turn on Target Interactive Conversations, you must specify values for all the subsettings (default values are provided). During a conversation, each condition is checked. A survey is only sent if all conditions are true.

Features

Provide better answers to consumers with Generative AI

At LivePerson, we’re thrilled that advancements in Natural Language Processing (NLP) and Large Language Models (LLMs) have opened up a world of possibilities for Conversational AI solutions. The impact is truly transformative. 

That's why we're delighted to announce that our KnowledgeAI application now offers an answer enrichment service powered by one of OpenAI's best and latest LLMs. If you’re using KnowledgeAI to recommend answers to agents via Conversation Assist, or to automate intelligent answers from Conversation Builder bots to consumers, you can now take advantage of this enrichment service.

How does it work? At a high level, the consumer’s query is passed to KnowledgeAI, which uses its advanced search methods to retrieve the most relevant answers from your knowledge base. Those answers — along with some conversation context — are then passed to the LLM service for enrichment, to craft a final answer. That’s Generative AI at work. The end result is an answer that’s accurate, contextually relevant, and natural. In short, enriched answers.

To see what we mean, let’s check out just a few examples in an automated conversation with a bot.

Here’s a regular answer that’s helpful…but stiff:

But this enriched answer is warm:

This regular answer doesn’t handle multiple queries within the same question:

But this enriched answer does so elegantly:

This regular answer is helpful:

But this enriched answer is even more helpful:

That’s Generative AI at work.

Are your agents using Conversation Assist? You can reap these same benefits in the enriched answers offered to them:

Ready to get started? Contact your LivePerson representative to discuss turning on these LLM-powered features. We offer 30 days of Preview access for free. Your brand’s authorized representative can start the Preview in the Management Console within Conversational Cloud.

Leverage your PDF and Web site content

As a brand offering products or services to consumers, you probably have a wealth of PDF and Web site content that you'd like to share with your consumers in conversations. A great example of this is an FAQ page. With our latest release, we're making it even easier for you to integrate knowledge content like this: You can import a set of Web URLs or PDFs into a knowledge base. Quickly go from this:

To this:

By doing this:

After the import, review the results and make any modifications that you require. Then use the knowledge base in your conversational AI solution as you normally would.

Take advantage of this new feature to efficiently leverage more of your brand’s knowledge within your Conversational AI solution.

Features

Accelerate development of your NLU taxonomy with Generative AI

At LivePerson, we understand the challenges that come with building a robust taxonomy and ensuring that your NLU model is performing at its best. One of the pain points in this process is mining your data for suitable training phrases for each intent. Another is meeting the minimum requirement of our NLU engine: You need at least 15 training phrases for each intent to ensure optimal results. Overall, the task of creating enough suitable training phrases for all your intents is tedious. And time-consuming.

Generative AI to the rescue! Thanks to the latest advancements in Natural Language Processing (NLP) and Large Language Models (LLMs), we’re excited to announce Intent Manager’s latest tool: A training phrase generator powered by one of OpenAI’s best and latest LLMs. You provide the topic and “prompt engineering” guidance, and in return, the tool generates up to 30 training phrases at a time for the intent.

It’s more about data science than anything. But the time and effort it will save you just might make it feel, well, magical.

Ready to get started? Contact your LivePerson representative to discuss turning on this LLM-powered feature. We offer 30 days of Preview access for free. Your brand’s authorized representative can start the Preview in the Management Console within Conversational Cloud.

New Natural Language Understanding (NLU) external APIs

LivePerson has just made public several NLU APIs. You can use them to leverage your LivePerson domains programmatically inside of bots or from external systems.

Use cases

Inside of bots, you could use these APIs to check multiple domains and use the results to serve answers, set variables, or control the flow of the conversation.

Outside of bots, you could use these APIs to classify text or run tests on your NLU performance.

APIs at a glance

• NLU Prediction (Single Domain): Returns NLU classifications from a single domain
• NLU Prediction (All Tracked Domains): Returns NLU classifications from all domains with intent tracking enabled
• NER Prediction: Returns detected entities
• Small Talk Prediction: Returns NLU classifications from the small talk domain

Features

Boost business outcomes with the new Generative AI Analytics dashboard

In the release, we introduce a new Generative AI Analytics dashboard that enables you to leverage Generative AI and Conversational AI in tandem, driving better business outcomes.

Use the dashboard to help you answer these important questions: 

• How is the performance of Generative AI in my solution? 
• How much is Generative AI helping my agents and bots?

The Generative AI dashboard draws conversational data from all channels across Voice and Messaging, producing actionable insights that can drive business growth.

The new Generative AI Analytics dashboard—and Generative AI in general—is a game-changer, providing you with the tools you need to drive business growth and improve customer engagement. With this new solution, you can better understand the performance of your Generative AI solution, and make data-driven decisions to improve its overall effectiveness.

Features

Elevate your omni-channel strategies in new ways

Give your consumers the choice to connect with ease and flexibility! Consumers can now seamlessly engage with the Voice bot to begin with and can choose to move the conversation over to messaging with C2M. 

The context from the Voice Conversation to the Messaging Conversation will be passed to the Agents  within a conversational transcript.

Leverage your C2M capabilities and extend the full power of the LivePerson platform to meet consumers wherever they are.

Features

Historical conversations for Social Channels

Conversations in Social channels are enhanced by features that are specific to Social only like previewing parent messages, metadata on messages, options to view a post in the native channel, ability to reply to a specific message and most recently, moderation actions. 

Barring the reply and moderation actions, all other Social specific features are now visible in historical conversations as well.

Like public messages on Facebook and Twitter

Public posts and comments on Facebook, and public tweets on Twitter can now be 'liked' through the Agent Workspace. The actions becomes visible when a message bubble is hovered over.

Fixes

Facebook wall posts were allowing moderation 

Moderation of Facebook comments on brand posts is possible but moderation of community posts by consumers is not. This was being allowed in the Agent Workspace UI even though it doesn't work and has now been rectified.

Features

Automated Conversation Summary 

We are excited to announce the release of the Automated Conversation Summary feature in our Agent Workspace!

This feature provides agents with AI-generated summaries and has been designed to help agents quickly catch up on ongoing and historical conversations of previous customer handled by a bot or a human agent. The summary will include the customer's questions, concerns, key problems, and attempted resolutions by the bot or the previous agent across voice and messaging.

The summary can be accessed through the Summary Widget for ongoing conversations, and for historical conversations, it can be found above the transcript and under the Conversation History Widget. 

It's important to note that the summary is not editable in either of these areas.

With the Automated Conversation Summary feature, agents can now easily determine the current intent of the consumer without having to read through the entire transcript, which saves them time and effort. The summary is available for both ongoing and historical conversations, providing context and helping to resolve any ongoing issues.

This feature is expected to reduce conversation handle time, improve the agent experience during user hand-offs, reduce the time to respond, decrease the average number of agent responses, and increase CSAT. 

We believe that this feature will ultimately improve the efficiency and effectiveness of our agents, leading to higher consumer satisfaction and better business outcomes.

Note, as default, only conversations with a minimum of 10 messages would be summaries. This can be changed to a lower/higher number.

Ready to get started? Contact your LivePerson representative to discuss turning on this LLM-powered feature. We offer 30 days of Preview access for free. Your brand’s 

account representative can start the Preview in the Management Console within Conversational Cloud.

Language support

Automated summaries are only supported for English.

Prerequisites

The LP Generative AI package should be enabled.

Enablement

Please reach out to your account team to discuss pricing and enablement