GETTING STARTED
Introduction to AgentAssist
Architecture and Configuration
Glossary
FAQ
Release Notes
Recent Updates
Previous Versions

SET UP AgentAssist
AgentAssist Setup Guide
Sign Up for AgentAssist
Conversation Automation
Automations Board
Create a Bot
Add Multiple Bots
Create Use Cases
Overview
FAQs Setup
Create Dialog Tasks
Welcome Events
LLM and Generative AI
Search AI
Agent Coaching
Playbook
Customizing the AgentAssist Widget
Configure Auto Summarization with Custom Dialog Tasks
Feedback Settings
Widget Theming (Layout Customization)
Supported Languages

INTEGRATIONS
AgentAssist Integration with Third-Party Applications
Amazon Connect
Amazon Connect with AgentAssist Voice Installation Guide
Amazon Connect with AgentAssist Chat Using Custom CCP
Amazon Connect with AgentAssist – Voice via AWS Third Party Applications
Channels
Voice
Configure Voice Channel
Configure Speech Recognition
Chat
SmartAssist
Configure AgentAssist
Demos
Voice Demo
Chat Demo
Salesforce
OmniChannel
Omni-Channel Configuration - Chat
AgentAssist Configuration - Chat
Genesys CTI
AgentAssist Voice Integration
NICE-CTI
Kore Agent AI with Salesforce NICE CX-CTI
Demos
Voice Demo
Chat Demo
Zendesk
Set up AgentAssist for Zendesk
Genesys
AgentAssist Integration with Genesys - Manual Setup Instructions
Agent AI Integration with Genesys Cloud CX
Set Up AgentAssist for Genesys
Change AgentAssist Bot in Genesys
Integrate Kore.ai Bot on Genesys Cloud CX Messaging
NICE MAX Desktop
Talkdesk
Twilio

AGENT EXPERIENCE
AgentAssist Widget
Bot Override and Automations

ANALYTICS
Conversation Logs
Dashboard
Agent AI ROI Analyzer (Beta)
APIs
Raw Data API v1
Raw Data API v2
Conversation Summary Trigger

Introduction to AgentAssist

AgentAssist is your agent’s personal intelligent virtual assistant. Sometimes even your best contact center representatives need assistance. Each time a customer is put on hold while an agent searches for an answer, customer satisfaction decreases, and the risk of churn increases.

AgentAssist is an AI-first intelligent virtual assistant that helps improve agent service quality by providing relevant information, customer insights, suggestions, and fulfillment workflows when needed. AgentAssist allows your agent to focus on providing timely delivery and personalized service, leaving repetitive or time-consuming tasks like transaction execution, information retrieval, and others to automation.

Agents collaborate one-on-one with AgentAssist, asking questions or initiating tasks for AgentAssist to perform in parallel during live conversations with customers. Faster resolution of customer queries significantly reduces the Average Handling Time (AHT).

This document provides a comprehensive summary of all the features and the architecture diagram used for the standalone AgentAssist solution. 

AgentAssist uses Kore.ai’s proprietary Artificial Intelligence (AI)/Machine Learning (ML) technology to provide suggestions to human agents when conversing with a customer. AgentAssist uses Natural Language Processing (NLP) to understand the intent behind customer utterances and suggests relevant dialog tasks or FAQs in response. AgentAssist helps the agent to use these suggestions to address customer concerns in a prompt and streamlined manner.

The AgentAssist widget resides within the SmartAssist solution for contact centers. 

AgentAssist is utilized as a widget in third-party agent desktop consoles and works best for both voice and chat-based interactions. You can configure the widget in third-party solutions like Salesforce, Twilio, Avaya, and Genesys.

Value additions of AgentAssist:

  1. There is a seamless interaction between the search function, automation, and the active tab the agent is working on, thus minimizing the number of clicks and tab switching. 
  2. AgentAssist suggests automation to keep the number of clicks low and reduces AHT for the agent.
  3. AgentAssist is designed to reduce the number of switches across multiple open tabs. 
  4. The agent does not have to open tabs manually, and pre-fill information, thus reducing the number of clicks. AgentAssist delivers information on the active tab. 
  5. AgentAssist has search functionality that helps the agent to search required information across AgentAssist while switching the agent back to the active tab after providing search results, thus saving time.  

AgentAssist Smart Attributes

  • Monitors Conversations
    AgentAssist monitors conversations alongside live agents and initiates automation. AgentAssist monitors the conversation, detects intent, advises (auto-suggests) agents, and performs tasks throughout the engagement, auto-collecting responses as the conversation progresses.
  • Provides Real-Time Assistance
    AgentAssist is a personal intelligent virtual assistant for agents that helps them to focus on
    delivering timely, personalized service. AgentAssist automates transaction execution, information retrieval, and repetitive/time-consuming processes.Agents collaborate one-on-one with AgentAssist, asking questions or initiating tasks for AgentAssist to perform in parallel during live conversations with customers.
  • Performs Tasks Based on Intent Detected or Agent Request
    AgentAssist automates tasks and fulfillment during the conversation. Examples of AgentAssist tasks include common transactions like balance transfer, book appointments, scheduling field service, changing travel, updating policy, gathering customer information, and finding and retrieving information from multiple systems. In addition, AgentAssist can automate and perform more tasks during live conversations, saving agents valuable time. Agents can also engage directly with AgentAssist and ask questions or initiate tasks or transactions for AgentAssist to execute that AgentAssist does not suggest.
  • Proactively Directs the Conversation Forward
    AgentAssist provides the ‘next best action’ prompts to agents based on the intent detected or the conversation’s stage. The actions can also include buttons to trigger API calls, launch applications, or trigger a Robotic Process Automation (RPA) process.
  • Helps Humanize Conversations
    AgentAssist informs and empowers agents throughout conversations by performing sentiment analysis and offering timely empathetic responses as suggestions for better customer and agent experiences.
  • Elevates Agent Experience
    AgentAssist has built-in automation that significantly improves agent experience and increases productivity to deliver the best possible customer service experience. AgentAssist brings the right information to the agent at the right time.
  • Summarizes Conversations to Speed Up a Post-Call Wrap-Up
    AgentAssist automatically summarizes conversations for agents for review and editing, saving valuable time in post-call processing, helping in compliance, and boosting agent as well as contact center efficiency.
  • AgentAssist gets smarter over time
    Machine-Learning (ML) algorithms enable AgentAssist to learn from each conversation and continuously improve the agent-customer experience. In any conversation on any channel, AgentAssist can pull customer information from CRM and other third-party systems to provide agents with the right context. Context includes the user’s session history, previous chat history, and current sentiment. The infographic below shows the smart functions of AgentAssist:

 

Introduction to AgentAssist

AgentAssist is your agent’s personal intelligent virtual assistant. Sometimes even your best contact center representatives need assistance. Each time a customer is put on hold while an agent searches for an answer, customer satisfaction decreases, and the risk of churn increases.

AgentAssist is an AI-first intelligent virtual assistant that helps improve agent service quality by providing relevant information, customer insights, suggestions, and fulfillment workflows when needed. AgentAssist allows your agent to focus on providing timely delivery and personalized service, leaving repetitive or time-consuming tasks like transaction execution, information retrieval, and others to automation.

Agents collaborate one-on-one with AgentAssist, asking questions or initiating tasks for AgentAssist to perform in parallel during live conversations with customers. Faster resolution of customer queries significantly reduces the Average Handling Time (AHT).

This document provides a comprehensive summary of all the features and the architecture diagram used for the standalone AgentAssist solution. 

AgentAssist uses Kore.ai’s proprietary Artificial Intelligence (AI)/Machine Learning (ML) technology to provide suggestions to human agents when conversing with a customer. AgentAssist uses Natural Language Processing (NLP) to understand the intent behind customer utterances and suggests relevant dialog tasks or FAQs in response. AgentAssist helps the agent to use these suggestions to address customer concerns in a prompt and streamlined manner.

The AgentAssist widget resides within the SmartAssist solution for contact centers. 

AgentAssist is utilized as a widget in third-party agent desktop consoles and works best for both voice and chat-based interactions. You can configure the widget in third-party solutions like Salesforce, Twilio, Avaya, and Genesys.

Value additions of AgentAssist:

  1. There is a seamless interaction between the search function, automation, and the active tab the agent is working on, thus minimizing the number of clicks and tab switching. 
  2. AgentAssist suggests automation to keep the number of clicks low and reduces AHT for the agent.
  3. AgentAssist is designed to reduce the number of switches across multiple open tabs. 
  4. The agent does not have to open tabs manually, and pre-fill information, thus reducing the number of clicks. AgentAssist delivers information on the active tab. 
  5. AgentAssist has search functionality that helps the agent to search required information across AgentAssist while switching the agent back to the active tab after providing search results, thus saving time.  

AgentAssist Smart Attributes

  • Monitors Conversations
    AgentAssist monitors conversations alongside live agents and initiates automation. AgentAssist monitors the conversation, detects intent, advises (auto-suggests) agents, and performs tasks throughout the engagement, auto-collecting responses as the conversation progresses.
  • Provides Real-Time Assistance
    AgentAssist is a personal intelligent virtual assistant for agents that helps them to focus on
    delivering timely, personalized service. AgentAssist automates transaction execution, information retrieval, and repetitive/time-consuming processes.Agents collaborate one-on-one with AgentAssist, asking questions or initiating tasks for AgentAssist to perform in parallel during live conversations with customers.
  • Performs Tasks Based on Intent Detected or Agent Request
    AgentAssist automates tasks and fulfillment during the conversation. Examples of AgentAssist tasks include common transactions like balance transfer, book appointments, scheduling field service, changing travel, updating policy, gathering customer information, and finding and retrieving information from multiple systems. In addition, AgentAssist can automate and perform more tasks during live conversations, saving agents valuable time. Agents can also engage directly with AgentAssist and ask questions or initiate tasks or transactions for AgentAssist to execute that AgentAssist does not suggest.
  • Proactively Directs the Conversation Forward
    AgentAssist provides the ‘next best action’ prompts to agents based on the intent detected or the conversation’s stage. The actions can also include buttons to trigger API calls, launch applications, or trigger a Robotic Process Automation (RPA) process.
  • Helps Humanize Conversations
    AgentAssist informs and empowers agents throughout conversations by performing sentiment analysis and offering timely empathetic responses as suggestions for better customer and agent experiences.
  • Elevates Agent Experience
    AgentAssist has built-in automation that significantly improves agent experience and increases productivity to deliver the best possible customer service experience. AgentAssist brings the right information to the agent at the right time.
  • Summarizes Conversations to Speed Up a Post-Call Wrap-Up
    AgentAssist automatically summarizes conversations for agents for review and editing, saving valuable time in post-call processing, helping in compliance, and boosting agent as well as contact center efficiency.
  • AgentAssist gets smarter over time
    Machine-Learning (ML) algorithms enable AgentAssist to learn from each conversation and continuously improve the agent-customer experience. In any conversation on any channel, AgentAssist can pull customer information from CRM and other third-party systems to provide agents with the right context. Context includes the user’s session history, previous chat history, and current sentiment. The infographic below shows the smart functions of AgentAssist: