Agent-Invoked Virtual Assistant Conversations for Voice Support
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
There is a challenge in the contact center industry to increase adoption of self-service AI bots, as customers are unaware or unwilling to engage with AI-assisted services, particularly in voice channels, leading to a preference for human interaction.
Innovation Solution
A system that integrates AI bots with live contact center agents, allowing the bot to be invoked by the agent during a voice call, visible to the customer, to perform tasks and demonstrate capabilities, thereby reducing manual steps and enhancing customer engagement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If AI bots are deployed for self-service in contact centers, then automation capability is improved, but customer adoption rate deteriorates due to customer unawareness or unwillingness to engage with AI-assisted services
Solution Approach 1:
The patent introduces a live contact center agent as an intermediary who bridges the gap between customers and AI bots. The agent invokes the bot during voice calls, making the AI assistance invisible to the customer while still providing automated service. This mediator approach allows automation to function without requiring direct customer engagement with the AI bot, thus maintaining high adoption rates while improving automation capability.
2Loss of time
If AI bots handle customer service tasks, then call handle time is reduced, but customer engagement deteriorates due to preference for human interaction
Solution Approach 1:
The live contact center agent serves as a mediator who maintains customer engagement while enabling AI bot assistance. The agent remains visible to the customer throughout the interaction, providing human connection and trust, while simultaneously invoking the AI bot to perform tasks and reduce handle time. This dual-role approach preserves customer engagement through human interaction while achieving time efficiency through automation.
3Productivity
If AI bot capabilities are demonstrated to customers, then future self-service adoption is improved, but current call complexity increases due to additional demonstration steps
Solution Approach 1:
The AI bot is invoked and configured in advance by the contact center agent before the customer needs assistance. The bot is pre-loaded with relevant capabilities and context, so when the customer interacts with the agent, the automation is already prepared and ready to assist. This preliminary setup eliminates the need for complex real-time demonstrations during the call, reducing call complexity while still allowing capabilities to be showcased when appropriate.
Data Source
AI summary
Techniques and architectures for implementing a team of virtual assistants are described herein. The team may include multiple virtual assistants that are configured with different characteristics, such as different functionality, base language models, levels of training, visual appearances, personalities, and so on. The characteristics of the virtual assistants may be configured by trainers, end-users, and/or a virtual assistant service. The virtual assistants may be presented to end-users in conversation user interfaces to perform different tasks for the users in a conversational manner. The different virtual assistants may adapt to different contexts. The virtual assistants may additionally, or alternatively, interact with each other to carry out tasks for the users, which may be illustrated in conversation user interfaces.