Skip to selected work
Harvey Zheng

Harvey Zheng

Product designer and frontend engineer. Experience building AI/ML products across AWS Bedrock and SageMaker.

Carnegie Mellon — HCI and Statistics/ML.

Selected work

5 projects, 2022–2026

Selected order

01

Plover — running training analysis

Solo designer & engineer · Private beta

  • Reworked the run journal so findings appear before the underlying measurements.
  • Shared chart components across the app and website; calculations stay in Python.
Plover run journal: a run card with distance, pace and heart rate beside a performance signal, and a summary of the checks run on recent training.

My running watch collects more data than I know what to do with. I built Plover to explain changes in my training and let me check the data behind each finding. Built with Claude Code and tested only with my own running data. It does not predict injuries.

02

AWS Bedrock IDE: Model picker

UX Designer · Shipped in Bedrock IDE

  • Tested three picker designs with roughly six engineers.
  • Reduced selection of frequently used models from five clicks and a scroll to two clicks.

Amazon Bedrock lets developers build apps with AI models from different providers, but choosing a model meant looking through a list of names without knowing what each supported. I redesigned the picker to show that information alongside search and recently used models. It shipped across six parts of Bedrock IDE.

Password required

03

Reusable AI chat components for AWS

Frontend Engineer (research + prototyping) · Research prototype

  • Built an interactive documentation prototype to research demand across AWS teams.
  • Engineers built the package; parts now run in the Bedrock playground.

Teams across Amazon were building similar AI chat interfaces from scratch. I built a prototype site where developers could try out our proposal for shared chat components, including switching designs and configuring features. The goal was to learn what other teams needed before engineers built the library.

Password required

04

SageMaker Canvas: Training models to classify images

UX Designer (Intern) · 12-week intern project, shipped

  • Designed the workflow from uploading images to checking model results.
  • Worked with four engineering interns and a PM intern.

Business analysts needed a way to train models to recognize categories of images without relying on a data scientist. During my internship, I designed that workflow in SageMaker Canvas, with a focus on organizing and labeling batches of images before training a model.

Password requiredView AWS blog (opens in a new tab)

05

Anagnori — a self-guided exposure therapy prototype

Solo designer & engineer · iOS prototype

  • Designed and built a SwiftUI app based on my experience with exposure therapy.
  • Reworked the review screen to show what I predicted alongside what happened.
Anagnori: a pattern card with an avoidance name, values tags and an intensity slider, beside an experiment card tracking trigger, prediction, observed intensity and takeaway.

Anagnori is an iPhone prototype based on practices that helped me in therapy. I use it to plan something I’d normally avoid, write down what I think will happen, then compare that with what happened. I’m the only person who has used it so far, and it hasn’t been clinically evaluated.

From the lab

Browse the lab

Personal tools and experiments I build with AI. 11 projects, newest first.

Web Effects Pack

Fifteen film and print effects for web pages, including film burns, crumpled paper and neon. Built with CSS, SVG, Canvas and WebGL.

Demo ↗

Plover

I turned a notebook for my Coros watch data into a running app with Claude Code. Deployed in private beta and tested only with my own data.

Demo ↗

unit-of-trust

An interactive essay about reviewing AI decisions, drawing on my recommender, agent-log viewer and small language model. Still a draft.

Demo ↗