E-Mail LinkedInLogo2
DESIGN
No items found.
ABOUT RESUME

Customer Support AI Chatbot

AI | SAAS | UX RESEARCH | UI DESIGN
An omni-channel AI chat experience where users can chat with an AI agent to resolve inquiries.

SECTIONS

◦  Overview ◦  Process ◦  Design ◦  Reflection

Overview

Problem

FINRA has a complex business model that requires a lot of support. Users are frustrated with long wait times to speak with live agents for customer support.

Time

3 months (Design)

6 months (Build)

Team

UX Research lead

Product Designer/UX Research support (me)

Product Manager

Engineering Team

Tools

Adobe XD

Miro

Jira

Confluence

Process

Discovery

Evaluating first party data

Strategizing with UX research on validation and discovery approach

Synthesis

Qualitative survey to understand user needs when looking for help

Comparative analysis of existing chatbots (UPS, Salesforce, Staples, Xfinity, American Airlines)

User scenarios

Affinity mapping survey data

Design

Low fidelity design ideation

High-fidelity prototype iteration

Develop

Document design specs in Confluence

Collaborate with product managers and engineers on JIRA tickets

Design

Please reach out if you would like to learn more about my work and process.

Reflection

Impact

  • 48% of 20,000 inquiries were resolved by the AI chatbot.
  • 48.5% of ratings for the AI chatbot were positive.
  • Significant reduction in the frequency of calls and chats with live customer support agents.

Learnings

  • Logging into an account is the most common problem FINRA’s call center agents receive inquiries about.
  • Users saved between 15 seconds to 5 minutes per login.
  • During usability testing, 9 out of 10 users said this new feature is beneficial for the multiple accounts they log into regularly.
NEXT PROJECT →

©2020 Designed & Built by Joanna Choi 🌸