Fleet Redeployment Hub

Problem

An enterprise fleet client needed to validate whether AI-assisted interaction patterns could reduce a multi-hour redeployment workflow into a guided, auditable experience. Existing operations depended on fragmented spreadsheets, email threads, and manual status checks. The design challenge was not to make AI feel magical; it was to make it accountable by communicating intent, system state, confidence, and recovery paths clearly.

Discovery

• Analyzed how operators coordinated redeployment across spreadsheets, email threads, and manual vehicle status checks
• Worked with enterprise stakeholders and an engineering architect to define what an AI-assisted PoC needed to prove
• Identified trust requirements for AI interaction, including intent, system state, confidence, scope, and recovery paths

My Role

• Solo designer on the PoC: owned all UX, UI, and design system decisions from concept through handoff-ready prototype
• Design-to-development bridge: translated Figma designs into KendoReact implementation using AI-assisted front-end tooling (Lovable) and VS Code
• AI workflow evaluator: assessed AI-generated UI implementations against design intent, establishing ground-truth corrections and quality criteria
• Documentation author: wrote copilot-instructions.md and component specifications enabling the engineering architect to build accurately from design output

Leadership & Impact

• Owned UX direction as the solo designer while aligning an engineering architect and enterprise stakeholders around a compressed proof-of-concept scope
• Set design authority under constraints by defining what AI-assisted interaction could safely do, where confidence needed to be communicated, and how operators should recover from uncertainty
• Created implementation guidance and component specifications that turned prototype decisions into reusable KendoReact patterns
• Used AI-assisted prototyping as a facilitation tool, not a substitute for judgment, to accelerate iteration while preserving quality

Approach

• Designed a four-state natural language command bar (idle, processing, results, error) that communicates AI confidence and action scope clearly
• Built a semantic status badge system with consistent color semantics (blue/gray/orange/red) that communicates vehicle availability at a glance across a dense inventory grid
• Established vehicle grid with filtering, bulk selection, and batch redeployment actions, designed for operators managing hundreds of assets
• Designed a side drawer for individual vehicle detail and a batch redeployment modal for multi-vehicle action confirmation
• Used AI-assisted tooling (Lovable + Figma REST API) to generate and evaluate front-end implementations, directly informing what AI-generated UI gets right and where it needs human correction

Outcomes

• Delivered a client-ready PoC that validated AI-assisted redeployment workflows in a single operational interface on a compressed timeline
• Defined natural language interaction patterns with explicit idle/processing/results/error states so operators could interpret system status and next actions quickly
• Designed confidence-aware communication patterns that made AI output actionable by clarifying scope, certainty, and recovery paths when errors occurred
• Created reusable KendoReact patterns and implementation guidance that improved engineering handoff quality and reduced interpretation risk
• Demonstrated that a natural language + bulk-action model can replace multi-step coordination loops with a faster, lower-friction decision flow

Tools & Technologies

Figma · KendoReact · Lovable · Cursor · Claude Code · GitHub Copilot · Figma MCP · React

Links