As North America’s largest privately held freight transportation company, Estes has earned a reputation for delivering high levels of customer care across all 50 states, Canada, Mexico, Puerto Rico, and the Caribbean. They consider every pickup request, tracking question, delivery instruction, and billing inquiry as an opportunity to keep freight moving and build customer confidence and loyalty.
Behind every Estes delivery is a contact center team focused on quality, consistency, coaching and agent productivity. Their 95-year-old company already had a strong quality process involving call reviews, agent report cards, performance tracking, and personalized coaching. But as with many large contact centers, their team faced a familiar challenge. Traditional quality management typically depends on manually assessing less than 2% of calls. Meanwhile, agents still must resolve their after-call effort in addition to focusing on customers.
The result is that valuable signals could be hidden inside everyday conversations. For example, what customers were asking, where agents needed support, which processes created friction, and where coaching could improve the next interaction.
Estes addressed the challenge through their close collaboration with Cisco. Together, the teams used Webex Contact Center, Webex AI Quality Management, and Cisco AI Assistant capabilities to expand visibility, strengthen coaching, reduce repetitive work, and create a more connected view of customer care.
Partnering with Cisco has been a great experience. From the beginning, we had regular opportunities to share ideas, learn from each other, and work together to improve our operations. We thought we had a good quality audit program in our call center, but we realized we were only scratching the surface of what was possible. Our managers and agents now have real-time access to actionable insights, allowing us to coach more effectively, respond faster, and continuously improve the customer experience.”
— Jill Townsend, Director, Corporate Customer Experience, Estes Express Lines
Overcoming Quality Visibility Gaps
Estes moved to Webex Contact Center in 2023, creating the cloud foundation for a more modern customer care environment. The AI journey began with a focused question: Could AI help evaluate repeatable parts of more customer interactions while keeping supervisors in control of judgment?
Estes team members John Hoy, Chandler Fuller, Jill Townsend, Jason Amick, and Kyle Sais worked under the leadership of Vice President, Customer Experience and Innovation Carrie Estes Johnstone. Through early-access trials and design-partner sessions, they collaborated with Krishna Tyagi, Shivani Kolala, Mags Moran, Katie NicGabhann, Kirsten Esplin, Karen Sharpe Smith, and other Cisco contributors. The Cisco FDE-led engagement connected Estes directly with AI practitioners as well as Cisco product and engineering. The results turned real-world operational feedback into requirements and coordinated follow-up.
Choosing the right technology partner is a critical business decision. Our experience with the Cisco AI Team has validated our choice at every turn. Cisco acts as a true strategic partner rather than a traditional software vendor. They took the time to understand our specific operational pain points before recommending solutions.”
— John Hoy, Network Engineer, Estes Express Lines
Building Quality Intelligence and Agent Assistance
Using Webex AI Quality Management, Estes began expanding from a narrow manual sample toward broader quality intelligence. At the same time, Webex AI Assistant capabilities helped gather intelligence for agents through post-call summaries, mid-call summaries, and auto wrap-up codes as well as visibility into customer sentiment. And the combination mattered. Supervisors gained a broader view of quality while agents were assisted with the work surrounding each interaction.
For the target lines of business, automation became the primary evaluation path for completed quality records. Automated QM activity grew by roughly 80% from March – June 2026.
AI could help evaluate procedural elements consistently, such as whether a required step was followed or whether a customer was placed on hold appropriately. Supervisors could then spend more time on the areas that require experience and context: whether the agent gave the right information, showed empathy, set realistic expectations, and helped move the customer forward.
That distinction is especially important in freight transportation. Customer care often depends on the service center’s practices and regional differences as well as the knowledge agents build from working across teams. Estes did not use AI to remove people from the process. Instead, it used AI to give supervisors better evidence and agents better support so they could focus on improving customer experience while supporting continued business growth.
Turning Insight Into Coaching and Agent Productivity
As AI-generated quality data scaled, Estes began seeing encouraging signs of adoption across the supervisor workflow. Unique users visiting the Agent Performance grid increased 165% quarter over quarter, and the system recorded hundreds of coaching runs in the last quarter.
Those signals matter because AI value is realized when people use the insight. Estes wanted quality teams to move faster from a score to the story behind it — all to identify the interactions, patterns, and agents that needed closer attention. Post-call summaries also became part of the agent’s workflow, helping agents document interactions more consistently, reduce repetitive after-call effort, and return their attention to the next customer.
Measuring Impact
Wrap-up time declined from 15.3 seconds in March 2026 to 10.9 seconds in June 2026 — a reduction of about 28%. This is an early capacity signal; that less time in wrap-up means more time for customer-facing work, coaching, and higher-value follow-through.
Connecting Quality, Agent Assistance, and Operations
Using near-real-time Topic Analytics, Estes identified more than 480 customer-contact topics, including delivery inquiries, dispatch-location issues, driver-location questions, dock-pickup requests, and pickup rescheduling. Supervisors could focus on the topics relevant to their queues and use near-real-time views when conditions change. The team also explored Webex AI Workforce Management, testing handle-time anomalies, adjustments, and occupancy assumptions.
Cisco is on a very positive track towards being able to offer great QM/Auto-QM and WFM solutions for customers that may not require all the capabilities and resources that a call center with thousands of representatives would. They’re creating simpler solutions that are more manageable for supervisors and team leaders. Furthermore, it’s always a plus when you can have all your tools available to you in one suite or interface. It’s clear that Cisco has put lots of work into making a seamless and smooth experience for the end-user to navigate. While there are some enhancements that we’re still looking forward to, ‘I’m personally pleased with the products and am very appreciative of Cisco’s willingness to take and action feedback of real users.”
— Chandler Fuller, Analyst, Customer Experience, Estes Express Lines
A Foundation for What’s Next
Together, these results show AI moving from trial into the daily workflow — expanding quality visibility, supporting agents, and turning insight into action. Through the collaboration of Estes, Cisco, and our partner ePlus, the team is building a disciplined learning loop around adoption, productivity, capacity, and customer outcomes.
For Estes and Cisco, the next chapter is to continue the transformation across AI QM, AI Assistant, and AI Agent and validate the outcomes that matter most: supervisor time redirected from manual assembly to coaching, AI and human evaluation alignment, repeat-contact and resolution improvements, forecasting accuracy, plus the real-world impact of routing, language translation, and AI memory. The destination is a contact center where every interaction can help improve the next customer’s experience.
About The Authors
