MINT MOBILE
FOCUS
Review Loris workflows and report which ones work well and which need fixes. Highlight those that help agents work faster and better, flag any that are confusing or unused, and suggest clear improvements to boost efficiency, accuracy, and key metrics like AHT and CSAT.
​
DESCRIPTION
Mint Chat Contact Center teamed up with Loris to add an AI tool to the chat platform. This tool helps agents during live chats by suggesting the next best steps—like troubleshooting tips or process workflows—so they can handle issues faster and more effectively. The goal is to make support smoother, quicker, and more accurate.
TEAM
Me, Loris Team, Mint Chat Ops
MY ROLE
Vendor Manager, UX, Data analysis
PLATFORM
Loris AI chat support tool
TOOLS
Loris AI, Figma, MS Suites, Google Suites, GMeet
Disclaimer: Some the parts on this project are private while I’m at Mint Mobile. If you’d like a closer look, just drop me an email and I’ll be happy to share a password with you.
Learn more about Loris and the Mint Help Center by visiting their sites.
Overview
Loris is an AI tool within the Khoros chat platform that helps agents with real-time suggestions and guided workflows to improve response quality and resolve customer issues faster. It includes workflows that guide agents through troubleshooting, issue handling, and standard processes, all accessible anytime through the Loris icon in the chat interface.
​​
Objective
Evaluate Loris tool effectiveness by combining data analysis, live chat reviews, and simulations to uncover pain points, streamline workflows, and deliver actionable recommendations to cross-functional stakeholders
30-60-90 Days Approach
Learn & Asses
Improve and Execute
Deliver Results
Review performance data (Disposition, tool usage and QA)
Understand Loris’ functions and features utilize Chat simulation tool.
Validate Loris workflows accuracy
FGM to gather user feedbacks
Define Opportunities
Tool
Redesign Loris workflows
Simplify agent steps
Start coaching or training initiatives
Measure improvements
Tie improvements to KPIO
Gather actionable feedback
LEARN & ASSES (30 Days)
KPI Analysis
Reviewed 26 chats from late July following Quality feedback that agents were not adhering to Suspected Fraud Account guidelines. We found 0% adoption of Loris—7% of agents relied on the knowledge hub, while 93% skipped all tools. (Appendix: Loris workflow sites findings)
Chat Review
I reviewed 60+ Fraud and Chargeback chats, comparing agent verbiage to the workflow. 85% didn’t follow the Loris script, often skipping it or using free-form responses. The script was outdated and missing key details, leading to inaccuracQA risks (Appendix: Loris workflow sites findings)
Chat Simulation
I used the Khoros chat simulation tool to get hands-on experience and better understand its functions and features. By exploring the tool directly, I was able to see how it works in real scenarios, practice different use cases. I identified several outdated workflows that no longer align with current processes.
Explain, Show and Practice (ESP)
I ran a test with four managers and four supervisors to check their understanding of the Loris tool. Afterward, we did an ESP session where I answered the test myself to show the correct way to approach it and set a clear example. Participants struggled not only with navigating the Loris tool but also with their overall product knowledge.
Define Opportunities
-
Agents skipping Loris tool. Agents use free-form responses, leading to inaccuracies and misinformation
-
Operations came across a few outdated workflows that were causing them to skip using the Loris tool (System gap)
-
Operations lacks understanding of the workflows—it’s unclear to them how it should be applied during customer interactions (Skill gap)
-
Agents were confused with multiple workflows being offered by AI (System gap)
IMPROVE & EXECUTE (60 Days)
Updated Workflows
I designed clear flowcharts and built 10+ workflows in Loris, removing the need for agents to switch between tools and making the process more seamless and efficient end-to-end. Previously, agents would leave the chat to pull workflows from another system and paste them back—adding unnecessary steps and slowing down resolution time. (Appendix: Loris Active workflows)
Loris AI interface enhancements
Using Figma, I built a high-fidelity mockup of the Loris interface with updated workflows, partnering with Customer Success and product teams to simplify the agent experience, reduce tool-switching, and help agents resolve issues faster end-to-end. (Appendix: Figma Loris Prototype)
I updated the guidelines and scripting for critical call types like the Fraud and Chargeback workflows within Loris to make the scripting clearer, more accurate, and easier for agents to follow. These changes help agents deliver consistent messaging, reduce errors, and ensure they stay in compliance (See Figma Loris Prototype)
DELIVER RESULTS (90 Days)
After pitching the enhancements to the Loris CSMs and Product Engineers, by September we had 200+ chat agents already using the new workflow—huge jump in adoption and it really helped;
-
Reduce AHT 30% from July, as agents were able to resolve customer issues more efficiently using guided responses instead of manual or free-form handling.
-
Reduce the risk of quality auto-fails and ensured better compliance with standard workflows. (Appendix: Loris workflow sites findings)
