DEV Community

Cover image for Reimagine an AI-powered contact center
Wendy Wong for AWS Heroes

Posted on

Reimagine an AI-powered contact center

Preparing to change the landscape of customer service

I've been working in contact centers for about 5 years including my days in finance.

In the US, the advancement of Contact Center as a service is changing how we can anticipate the needs of customers and use AI to transform workforce management and also reporting for supervisors and agents.

Scheduling

Real-time schedulers have problems with agents swapping shifts at the last minute.

Forecasts are rigid and cannot be changed after they are created and published every fortnight.

Supervisors

Supervisors have to maintain SLA and do not have time to provide 1:1 coaching to their team members or have the visibility to be proactive and to change queue priorities.

They do not have the ability to create their own real-time dashboards for day to day operations and to view the status of their agents. They may only view historical records or end of day reporting and cannot take immediate action to anticipate events or an increase in call volumes.

Agents

Agents do not have the flexibility to swap shifts and to manage their burnout.

As they have to maintain CSAT of 98%, adherence and provide customers with a survey after a call, they might not have time to accurately record file notes or wrap-up codes to understand the reason for the customer's call. Wrap-up codes are important for reporting.

Also with knowledgement management guides located on intranets and a lack of training for new events, they may lack the information to service their customers.

Amazon Q in Connect

Amazon Q in Connect is an AI powered assistant integrating with Amazon Connect to lighten the load for different contact center personas such as:

  • Supervisors
  • Agents
  • Real-time schedulers

We can have agents working with Amazon Q to help search for information on a call with enterprise knowledge base from documents uploaded to Amazon S3 or perform search with Amazon Kendra.

I have published my new course on LinkedIn Learning to help enterprise adopt AI in their future contact centers to build the future with generative AI to give time back to agents, help them capture and summarize calls and help supervisors produce real-time dashboards of their operations.

In Australia, contact center as a service to integrate data and provide personalized responses to customers is something that one of global contact center providers is anticipating.

However in Amazon Q in Connect you pay as you go and it is easy to create an instance for your virtual contact center to address a few pain points to boost productivity.

To change customer experience in contact centers that is powered by AI and enabled by cloud, we can help organizations have visibility and also a faster response time via search and text summarization.

NEW: LinkedIn Learning course

You are welcome to learn about AI-powered contact center in my new course:

https://www.linkedin.com/learning/amazon-q-in-connect-genai-contact-center/ai-powered-contact-center-with-amazon-q-in-connect

API Trace View

How I Cut 22.3 Seconds Off an API Call with Sentry 👀

Struggling with slow API calls? Dan Mindru walks through how he used Sentry's new Trace View feature to shave off 22.3 seconds from an API call.

Get a practical walkthrough of how to identify bottlenecks, split tasks into multiple parallel tasks, identify slow AI model calls, and more.

Read more →

Top comments (0)

Image of Checkly

4 Playwright Locators Explained: Which One Should You Use?

- locator('.cta'): Fast but brittle
- getByText('Click me'): User-facing, but can miss broken accessibility
- getByRole('button', { name: 'Click me' }): Most robust, best for a11y
- getByTestId('cta-button'): Stable, but ignores UX

Watch video

👋 Kindness is contagious

DEV is better (more customized, reading settings like dark mode etc) when you're signed in!

Okay