Industry

Transportation

Client

Zoox

Client

Locked

Project Type

Internal

Status

Launched

Date

May 14, 2024

My Role

UI Design, UX Design, User Research, Front-end Prototyping

Core Team

1 Engineer Manager, 1 Software Engineer, 1 Design Manager, 1 UX Designer (Self), 10 Stakeholders

Vehicle Issue Tracking App. New Way to Empower Map Operations.

Main Project Image

Context & Problem

As autonomous vehicle fleets scaled across dense urban environments, mapping and operations teams needed to triage real-time, location-based issues across multiple cities. Existing workflows made it difficult to quickly understand priority, ownership, and context within dense geospatial data, slowing response times and increasing operational friction in time-sensitive scenarios.

My Role

Led end-to-end UX for the mapping triage experience, including research, workflow definition, prototyping, and close collaboration with engineering through implementation.

Constraints & Key Decisions

The system needed to support real-time geospatial data, multiple user roles, and high performance at scale. Rather than introducing automation prematurely, I prioritized clear manual workflows—map-first triage, bulk actions, and explicit routing—to unblock teams while learning which signals mattered most.

Large Project Gallery Image #1

Why These Decisions

Project Gallery Image for 50% width of the screen #1
Project Gallery Image for 50% width of the screen #1
Project Gallery Image for 50% width of the screen #2

To reduce cognitive load and speed adoption, the interface followed familiar mapping patterns from tools like Google MyMaps and other geospatial software. Workflows were separated into clear pages, while side panels surfaced detailed, actionable information when a location pin was selected—allowing users to investigate and resolve issues without losing spatial context.

Designs

Project Gallery Image for 50% width of the screen #1
Project Gallery Image for 50% width of the screen #2
Project Gallery Image for 50% width of the screen #1

Solution & Impact

The launch of the tool led to an 80% reduction in duplicate issues, reducing noise and accelerating operational decision-making.

Delivered a map-based vehicle issue tracker that surfaced high-signal issue context, enabled teams to block off problematic areas, and supported fast rerouting—helping fleet operations proactively avoid unsafe zones and maintain safe, reliable customer rides in real time.

Key Learnings and Next Steps

While AI-based issue grouping was a long-term goal, limited engineering capacity and insufficient training data made early automation impractical. We intentionally focused on manual triage workflows to unblock teams and understand which signals—such as issue type, location, and frequency—were actually meaningful in practice. These learnings informed a clear path forward: use the collected data to introduce AI-assisted recommendations when resources allow, starting with suggestions rather than full automation. This approach balanced immediate impact with long-term scalability.

  • The image featured in the carousel #1
  • The image featured in the carousel #2
  • The image featured in the carousel #3
  • The image featured in the carousel #4
  • The image featured in the carousel #1
  • The image featured in the carousel #2
  • The image featured in the carousel #3
  • The image featured in the carousel #4
  • The image featured in the carousel #1
  • The image featured in the carousel #2
  • The image featured in the carousel #3
  • The image featured in the carousel #4

Create a free website with Framer, the website builder loved by startups, designers and agencies.