Hackathon, 2nd Place
Smart-Routing Voice UI for WP Engine Support
Customer support call volume resulted in significant hold times. Phone trees (IVR) are linear and rigid, forcing customers through irrelevant options before reaching a human.
Tools
Google Gemini
NotebookLM
11 Labs
n8n
Google Sheets
Slack
Goal
To deploy a Voice UI (VUI) agent capable of identifying customer intent, resolving low-level queries and intelligently route issues to the correct internal teams.
Role
As the sole designer, I defined conversational guardrails for various user personas and conducted Red Testing to expose where the conversational logic failed.
Team
9 people (including myself) across the organization from Design, Product, Engineering, Customer Support and Sales assisted in this project.
Outcome
Out of 7 teams that participated in the even, our team earned 1st place in the annual 2025 Hackathon.
Definitions
Conversation Guardrails - We trained the VUI with common and edge-case user personas such as a distressed user and non-native speaker.
Red Testing - A testing process to intentionally probe the AI system to force it to misbehave, bypass it's safety guardrails or reveal hidden vulnerabilities before bad actors do.
The Problem
WP Engine is known for the award winning customer service. However, as the business scales and the customer base grows, Customer Support demand increases effectively creating longer wait times.
Our human agents needed a more efficient way to re-route or escalate the increased number of support calls.
Key Features
Intent-first
Instead of a menu-based hierarchy (e.g., "Press 1 for Sales"), we implemented an open-ended conversational trigger ("How can I help you today?").
Distress detection
Users that showed signs of frustration e.g., speaking over the bot, or repeated "I need a human" responses. This triggered immediate escalation to a live agent.
Cognitive awareness
Limited VUI to handle low-level scenarios such as checking their balance.
Multi-language support
With a global customer base, we also needed to ensure the VUI could handle multiple languages.
Lessons learned
The Red Testing process highlighted that the quality of the conversation is a business outcome, not just a design feature.
Addressing AI apology fatigue
Minimizing robotic apologies like "I’m sorry, I didn’t get that" with "I need a bit more detail to get you to the right team." added a layer of intentional design.
Dynamic Data Handshaking
Ensuring the agent could pull account-level data (e.g., "I see you're on an Enterprise plan") to adjust the tone and speed of the routing process dynamically prioritized high-value clients.
Outcome
By replacing the rigid menu with an intent-based conversational agent, we significantly reduced the Average Handle Time (AHT) and saw a measurable increase in Call Resolution Rate (CRR) for common, simple problems. The system effectively acted as a "smart gatekeeper" allowing WP Engine’s senior support staff to focus exclusively on high-value, complex technical issues.