I designed the UX for an AI-powered assistant, streamlining the test case planning flow from 7 manual steps to 4 AI-assisted steps without disrupting developer flow. The goal was to help engineers create stronger coverage with less effort by embedding intelligent, context-aware support into their existing tools.
[CASEΒ STUDYΒ INΒ PROGRESS]
β
All visuals and product details are fully anonymized and recreated to respect confidentiality while accurately reflecting the challenges, design process, and impact of my work.
β
β
Creating and reviewing test cases is time-consuming, repetitive, and fragmented. Developers often switch between tools, documents, and tabs to plan test cases.
This constant context switching breaks focus, increases the chance of errors, and slows productivity.
β
β
β
Leverage AI to:
β
β
β
β
β
β
β
From mapping the end-to-end planning workflow, seven recurring pain points were identified current experience.
β
β
β
To make AI support feel natural, I explored where assistance should appear:
β
β
β
β
Concept 1:π§ Trigger AI via modal from highlighted text
Concept 2:π¬ On-demand chat panel
β
β
β
β
I merged the best of both worlds: guidance and control.
Final Flow:
β
β
β
β
Once I identified clear AI entry points, I worked on making review more efficient. Developers could accept multiple test cases at once using batch selection. Expandable previews let them quickly scan suggestions. When edits were needed, they could either make changes inline or ask the AI to adjust content in the side panel.
(Recreated illustration of inline editing and batch selections)
β
β
β
β
β
β
β
β
β
Good AI design is not just about adding intelligence. It is about integrating it in ways that feel natural, keep people in control, and make their work easier without getting in the way.