Amazon Web Services today at its AWS re:Invent conference introduced artificial intelligence capabilities for Amazon Connect, its cloud contact center suite, with features to improve the customer service agent experience and performance.
The four core components being introduced are as follows:
- Forecasting, capacity planning, and scheduling to help teams determine staffing support level needs based on historical volume data and tools to help automate the staffing of peak periods.
- Contact Lens conversational analytics for chat, which helps contact center leaders understand customer sentiment, redact sensitive customer information, and monitor agent compliance with company guidelines.
- Evaluation forms for agent performance as part of Contact Lens for Amazon Connect, helping managers create evaluation forms that can be automatically scored by Contact Lens' conversational analytics.
- Amazon Connect agent workspace, which adds step-by-step guidance to help agents resolve customer issues.
With the forecasting capability, Amazon Connect uses AI to analyze and predict future contact volume, average handle time, and inbound, transfer, and callback contacts in both voice and chat channels.
Capacity Planning uses the published long-term forecasts with planning scenarios and metrics, such as maximum occupancy, daily attrition, and full-time equivalent (FTE) hours per week, as the input to predict how many agents are required to meet service level targets for certain periods of time.
Using the short-term published forecasts together with shift profiles, staffing groups, human resources, and business rules, the new scheduling feature creates schedules optimized for service level or average speed of answer targets. Schedulers can review and edit schedules. Once they publish schedules, Amazon Connect notifies supervisors and agents in the relevant staffing groups that a new schedule is available.
Contact Lens adds conversational analytics to Amazon Connect Chat, extending the ML-powered analytics to assess chat contacts with agents and the Amazon Lex bot. Contact Lens' conversational analytics for chat helps understand customer sentiment, redact sensitive customer information, and monitor agent compliance with company guidelines. Managers can use the contact search feature to identify contacts where customers had issues based on specific keywords, customer sentiment score, contact categories, and other chat-specific analytics, such as agent response time.
Contact Lens now also offers chat summarization, using AI to classify and highlight key parts of conversations, such as issue, outcome, or action item.
Contact center managers can also create agent performance evaluation forms in Contact Lens, add relevant evaluation criteria, such as the agents' adherence to required scripts or compliance with sensitive data collection practices, and enable scoring that uses Contact Lens for Amazon Connect's conversational analytics.
The Amazon Connect agent workspace is a single, unified application that provides agents with tools to resolve customer issues. When accepting calls, chats, or tasks, agents can view updated customer information, search knowledge articles, and get real-time recommendations.
Managers can also use Amazon Connect's no-code, drag-and-drop interface to create custom workflows and step-by-step guides for agents. They can specify in their contact flows under which condition a guide is shown to an agent. Once the agent selects the guide, the Amazon Connect agent workspace provides the information and one-click actions across both Amazon Connect and third-party applications.