Conversational AI

LivePerson’s Conversational AI platform offers end-to-end orchestration of brand-to-consumer conversations to deliver the best experience
  • Messaging
  • Chat

Conversational Commerce has opened new channels for consumers to interact with brands across all stages of their journey. With the growing number of consumer interactions from different messaging apps, innovative companies are looking for ways to efficiently handle high-volumes of messaging conversations, while delivering a great consumer experience.

LivePerson's Conversational AI offers end-to-end orchestration of brand-to-consumer conversations using:

  • Intent Manager for intent detection
  • Conversation Builder for building bots
  • Conversation Orchestrator for dynamic routing
  • Conversation Assist for recommending answers and bots to agents

With LivePerson’s conversational AI capabilities, you can personalize the conversational experiences of your consumers throughout their journey...and at scale.

Key capabilities

Using LivePerson’s powerful tools, Conversational AI can:

  • Assess consumer intent and conversation context to predict what might happen next
  • Route dynamically to human agents or bots to solve customer requests quickly
  • Recommend the next best conversational actions, including asking clarifying questions, suggesting knowledge base answers, routing to a particular agent, and transferring to bots built in the Conversation Builder or in a third-party tool
  • Give you transparency into every AI decision, so you can control and manage the way AI is used in your conversational pipelines, accelerating consumer experience improvements and brand efficiency

How Conversational AI works

Conversational AI offers end-to-end orchestration of brand-to-consumer conversations using the following AI tools and automations:

Intent Manager

Identify the consumer's intent in real time, through every turn in a conversation

Intent Manager automatically analyzes consumer messages sent to human agents and bots, instantly identifying and recording the consumer's intent through every turn in the conversation. The Conversation Orchestrator takes intent data and combines information from different data sources to identify the best intent match.

You can build and train intents in Intent Manager, or upload them from an existing system or other NLU engine. And you can create intent dashboards to optimize operations intent by intent, and build a data-driven automation program.

Image

Dynamic routing by Conversation Orchestrator

Create dynamic, personalized routing policies using intent, context and predictive attributes

Conversation Orchestrator is LivePerson’s AI engine that orchestrates every consumer conversation with your brand to an outcome you both value. Conversation Orchestrator works in the background to quickly understand the consumer’s intent, and route to human agents or bots to solve customer requests in the best way possible.

Conversation Orchestrator’s Dynamic Routing uses the consumer’s identified intent and assesses the conversation’s context from various data sources (consumer attributes, operational metrics, and enterprise systems, etc.) to route to the right agent.

Image

By combining information from an external system like a CRM, the consumer can be immediately identified by name, location, and other information, such as VIP status. LivePerson Functions allows brands to easily integrate data from external systems, like Salesforce, using secure, LivePerson-managed function services.

Using the Conversation Orchestrator’s workspace, you receive a self-service experience to manage and operate the way that AI is used in your conversational pipelines, ensuring you continue to deliver a great consumer experience.

Conversation Assist

Use AI to recommend answers and bots to the agent based on conversation context

Conversation Assist analyzes all available answers (knowledge base articles) and bots for the identified consumer intent and recommends the best next actions, such as having a bot join the conversation in real time. Recommendations are made by choosing the highest ranked answers and bots by score; scores are based on machine-learned signals about the historical performance.

The agent can opt to use an answer to help the user. Or, they can opt to join a bot to the conversation, where they can monitor the conversation and remove the bot if needed.

Image

Conversation Builder

Easily design, build and integrate bots

You can create bots in LivePerson’s Conversation Builder or integrate third-party bots using a connector for IBM Watson or Google Dialogflow.

Conversation Builder is fully integrated into LivePerson’s Conversational AI platform, allowing for seamless back-and-forth escalation with human agents and real-time monitoring by humans. In this way, LivePerson enables both human agents and bots to interchangeably handle consumer interactions to deliver the best consumer experience possible for each conversation.

Image

Conversation Builder allows you to build bots, including everything from creating intents and building dialogs, to back end integrations that connect to all consumer messaging channels and everyday systems like Salesforce.

We built Conversation Builder as a dialog-based tool for creating bots at scale. This allows you to leverage non-technical staff to build, optimize, and improve bots and automated conversation flows - creating bots that are more effective, and drastically speeding up bot development and optimization.

Conversational AI features list

Conversation Builder features

Dialog management

  • Dialog management - no code
  • Dialog management - code-based
  • Automatic context switching
  • Slot filling
  • Disambiguation
  • Bot templates provide a way to quickly generate different dialogs

Coding

  • Custom bot implementations can use JavaScript code to write logic
  • Ability to inject code at every step of the interaction and also for processing user responses

Channels

  • Channels - ABC, RCS, WhatsApp, Facebook, SMS, Web Bots support all channels supported by LivePerson
  • IVR support

API integrations

  • API integrations for connection to your REST APIs; CRM; billing, inventory or other business system
  • Function as a Service (FaaS) support
  • Authentication methods (e.g., OAuth 2.0, Basic Auth, mTLS, Tokens)

Content management

  • Search-based knowledge bases
  • Ability to use different NLU engines for training a knowledge base
  • Both English and non-English languages are supported. For non-English languages, external NLU engines are recommended

NLU

  • CB native NLU - intent detection (text-based)
  • CB native NLU - entity detection
  • CB native NLU - slot fill
  • External NLU engine support for IBM Watson and Google Dialogflow

User personas

  • Developer user persona
  • Non-technical user persona

Developer experience

  • APIs for intent detection
  • APIs for Knowledge Base query lookup
  • APIs for bot analytics

Bot Analytics

  • Measure bot performance using different reports:
    • Messages, Conversations, Users, Sessions
    • Intent match/unmatch reports
    • Custom event reports

Language support

For info on this, see here

Deployment options

  • LivePerson Private Cloud
  • AWS Public Cloud
  • Customer Private Cloud

Conversation Assist features

  • Uses NLU to match the consumer's intent and recommend answers and bots to join the conversation
  • Integration of bots from LivePerson’s Conversation Builder, Google Dialogflow, and IBM Watson

Conversation Orchestrator features

Conversation Orchestrator workspace

  • Self-service experience to configure Conversation Orchestrator features
  • Analytics for Conversation Orchestrator features (e.g., availability, usage)

Dynamic Routing

  • Create intent-based and context-based (e.g., consumer profile data, wait time) routing policies
  • Apply actions: route/transfer to human agent, skill or bot
  • JSON-based, low-code authoring

Conversation Context Service

  • API access to inbox system attributes (e.g., user, conversation, and operational context)
  • Create custom attributes with static data (e.g., list of emails)
  • Create custom attributes with Functions as a Service variables (e.g., CRM integrations via FaaS)
  • Carry over custom context through conversational journey

Next Actions API

  • REST API to Conversation Orchestrator that exposes next action to concierge bot/LOB app for routing decisions

Conversation Orchestrator concierge bot

  • Conversation Builder’s concierge bot template pre-built with intents and Next Actions API integration

Intent Manager features

Intent building

  • Self-service intent building using Conversation Builder NLU
  • Self-service intent building using third-party NLU service (i.e., Google Dialogflow, IBM Watson)
  • Self-service intent building using starter packs for a supported verticals (for brands with no existing intent modeling) - coming soon

Real-time intent detection

  • Intent identification for human agent conversations (messaging only) & bots* (*with intents defined in Intent Manager)

Analytics dashboard

  • Intent Manager dashboard integrated with Conversation Builder
  • Top line metrics and messages with intent
  • Intent volume and confidence
  • Intent time series
  • Intent list with details
  • Conversation quality by intent
  • Conversation viewer with drill down

Professional services

  • Professional services for intent modeling starter packs and advanced custom taxonomy

Raw data

  • Message-level classification data available via public API



Missing Something?

Check out our Developer Center for more in-depth documentation. Please share your documentation feedback with us using the feedback button. We'd be happy to hear from you.