Case Study 02

Modernizing vehicle inspections

Replacing a paper-made-digital checklist with a camera-first walk-around — transforming daily vehicle inspections from a compliance chore into visual evidence that fleet managers can actually trust.

Role
Lead Product Designer
Company
Amazon (Last Mile)
Duration
2018 – 2020
Amazon delivery van inside an automated vehicle inspection tunnel

A paper form made digital — and drivers treated it that way

As lead product designer for safety and innovation at Amazon Last Mile, I inherited the daily vehicle inspection — a federally mandated check (DVIR) that every DSP driver completed before and after each route. The experience was a paper form made digital: a long checklist that drivers blasted through in under 30 seconds.

Compliance rates looked fine. Trust was the problem. Fleet managers couldn’t verify whether a driver actually walked around the vehicle or just tapped through from the driver’s seat. A checked box only means something if someone actually looked.


Adding photographic evidence for fleet managers

I integrated photo capture directly into the checklist: flag a defect, camera opens with specific instructions, photo attaches to the issue and ships to the fleet manager. First time they could actually see what the driver saw.

But photos only got taken when something was wrong. A clean inspection still looked identical to a skipped one.

DVIC photo addition flow — navigate to vehicle side, checklist with defects, camera capture, report with photo thumbnail
Flag a defect, capture a photo with specific instructions, and the image attaches directly to the report for fleet managers.

A hardware solution enters the picture

About a year and a half into my time on the team, Amazon invested in Automated Vehicle Inspection (AVI) tunnels — camera-equipped arches installed at delivery stations that scanned vehicles as they drove through. This was an entirely separate initiative from the checklist work, but it addressed the same core problem: how do you verify the condition of a vehicle without relying on a driver’s word?

My role was designing the driver experience around the tunnel — what happens in the app before, during, and after the scan. Drivers would sometimes jump into their manual inspection before the automated scan had finished processing, then hit a dead end. I designed a gating flow that kept the two halves in sync, and a results screen that merged automated and manual findings into a single report.

The AVI tunnel: a camera-equipped arch scans the vehicle exterior as the driver passes through, then routes them to parking for the manual portion.
AVI app flow — Did you drive through the tunnel? → Drive through now → Finish and park → Scan complete, start manual inspection
The Rabbit app flow: confirm tunnel drive-through, wait for scan processing, then launch manual inspection for what the tunnel couldn't see.
Full Automated Vehicle Inspection flow — AVI scan, manual inspection screens, results overview, and completion states
The complete post-route AVI flow: automated tunnel scan, manual inspection for interior items, combined results, and completion states — including iterations on the entry experience.

If photos are the most valuable part of every inspection, why not make the photo the entire inspection?

Putting AI-powered inspections in every driver’s hand

The tunnel worked — but at enormous cost, and only at stations that had one. Most didn’t. The real question: could we deliver the same quality of inspection through a phone, using AI, at a fraction of the price?

The concept: a guided camera walk-around that replaces both the checklist and the tunnel. The app directs drivers around the vehicle section by section with on-screen guides showing exactly how to frame each shot. AI validates each photo in real time. No infrastructure. No checkboxes. The future of the tunnel, in every driver’s pocket.

AR-guided photo capture — camera overlay with vehicle outline guides the driver into position, then confirms with a checkmark
On-screen guides direct the driver into position. When aligned, the photo captures automatically.
Second angle — AR-guided capture from front-right position, showing alignment guides and confirmation
Each angle follows the same pattern: outline guide → position → auto-capture → confirm.

Helping drivers understand what to do

Line illustrations alone aren’t enough — especially for drivers who’ve never done a photo-based inspection. The app provides real-time directional prompts (“Move back, down and right”) that update as the driver repositions, paired with visual overlays showing exactly how to frame the vehicle. No guesswork, no training required — the phone tells you when you’re in the right spot.

Real-time directional prompt UI — Move back, down and right
Directional prompts adjust dynamically as the driver moves, guiding them into the correct framing position for each vehicle angle.

The result: timestamped, geolocated photographic evidence of every vehicle angle, sent directly to the fleet portal. Consistent photo formats open the door for automated defect detection — turning every driver’s phone into an AI-powered inspection station.


Building trust into every inspection

97%
inspection completion rate, up from 73%
<52s
average inspection time, down from 3.5+ minutes
99%
completion rate with hand-held inspections

The checklist photo addition gave fleet managers their first visual evidence of vehicle condition. The AVI tunnel integration automated what drivers were most likely to skip. And the photo-first concept represents the logical conclusion: if photos are the most valuable part of every inspection, make them the entire inspection.

This project taught me that the best compliance tools don’t feel like compliance. When you design an inspection that produces something genuinely useful — a visual record that protects drivers, fleet managers, and the company — people actually want to do it right.

Next Project

Preventing roll-aways →

Amazon — Lead Product Designer
Roll-away prevention system