Design of agentic AI and content workflow for Customer service

Transforming Telecom Support from Cost Center to Revenue Driver

Before and after business results​

Note: Because of the non-disclosure agreement, some of the information on this page has been replaced with fictitious ones or has been blurred out


Core product team responsible for decisions​

UX Research: Call quality crisis


Problem: Confusing UI is actively stealing 45% time from the human interaction.

The call center is the Final Safety Net for retention.

SecResearch2

Secondary research: Observing agents' behaviour and analyzing data

As-is journey map revealed where the problem was.

Workflow showing the major pain-points

Top three painpoints from UX research

Workshop: Stakeholder alignment

  • Participants: UX (Lead), AI Engineering, Data Architect, and Call Center Floor Manager.

  • The Problem: Finding the AI capabilities and limitations.

  • The Strategy: Not reworking the existing UI

  • The Outcome: We determined that manual data retrieval was the primary bottleneck. AI was selected to automate the ‘Information Hunt,’ allowing agents to focus 100% on the customer’s emotional state.

Automated Content Pipeline

I created a pipeline to generate content, evaluate it against the rubrics and show it to the agent only if it succeeds.

AI content creation pipeline using Fuel IX.

Why Not Just Redesign the UI?


We needed to see how the agents feel about the Agentic AI integration

Workflow with agentic AI content w/ Human-in-loop

To-be journey map: Shows agent and customer interaction


To-be journey for service design

Lean UX: A/B Testing 

Creating and testing the concepts live to get a feel of improvements



Churn risk indicator concepts
I found that seeing a 'Red' risk score wasn't enough (Challenge 1: Trust Gap).
Agents needed to know why the risk was high to believe the AI.
Example of concept 1 on existing UI for testing​

Learnings from testing

1. The Lag Challenge (Technical): AI took 3 seconds to load.

2. The Trust Gap (Psychological): Most agents ignored AI warnings.

Feedback from agents

3. Most agents requested help to navigate difficult conversations

4. Many agent miss cross-sell opportunities while manually calculating complex orders.

5. Many agents  reported that they retype conversations after the call. This increases After-Call Work (ACW).

Agentic AI content designs

The final designs showing two possible states: Smooth call and a difficult call

AI assists the agents in all the functions

Launch challenges and decisions

Overcoming Technical & Psychological Hurdles

Challenge 1: The Trust Gap (Psychological)

Problem: Agents ignored AI churn warnings due to low trust.

Solution: Introduced “why” context (e.g., billing disputes), raising trust by 40%.


Building trust through transparency by adding reasons for AI predictions

Challenge 2 : The Lag Challenge (Technical):

Problem: MVP showed a 3-second latency for AI processing.

Solution: To prevent "dead air" on the call, I designed a Progressive Loading Sequence.


Progressive loading for overcoming AI latency in the final launch

Challenge 3: Helping agents navigate difficult conversations

Problem: Agents needed polished script to speak to customers

Solution: Low cognitive load, AI generated talking points that agents can use

Example of talking points that help agents navigate difficult conversations.

Challenge 4: Identifying and capturing sales opportunities

Problem: Agents miss cross-sell opportunities while manually calculating complex orders.

Solution: An AI engine that instantly surfaces high-propensity offers with reasoning.

AI shows the offers customer is most likely to buy

Challenge 5: Automating post-call documentation

Problem: Agents retype conversations after the call. This increases After-Call Work (ACW).

Solution: Structured AI generated CRM ready transcript.

Live Scribe: Automates documentation by capturing resolution and sentiment in real time.

Results

Quantifiable Impact on Business & People

Ultimately, this design turned the call center from a high-friction 'cost center' into a proactive 'retention engine,' proving that better UX for AI in workflow reduces churn