Weidong Shi.

Weidong Shi · AI Solutions Architect

AI in Action

A modern AI product studio — live apps you can open and inspect.

Build → Validate → Improve → Document → Share. Personal production case studies in AI-assisted engineering — for business and technical audiences alike.

Live apps

What would you like to improve?

Five production apps — open the product, then read the story behind the build.

Method

Build → Validate → Improve → Document → Share

Each app follows the same loop: ship something real, validate in production conditions, improve from evidence, document the decisions, then share the case study.

Proof

Case studies behind the builds

Architecture decisions, trade-offs, and delivery notes — still here, still linked from every live app.

Open live

Local-First Habit Coach

Live

HabitCheck

Missed days shouldn’t force fake checkmarks; people need honest recovery that keeps momentum real.

AI Applications · Recovery · Facts vs Coach · Privacy-gated AI

  • nextjs
  • pwa
  • local-first
  • privacy
Open live

Decision-Support Application

Live

RetireCheck

People need a credible “will my money last?” answer without advisor-grade onboarding friction.

AI Applications · Domain architecture · Monte Carlo · Cloud delivery

  • nextjs
  • aspnet
  • monte-carlo
  • fintech
Open live

Local-First Wellness PWA

Live

SleepCheck

Wind-down tools often over-collect data; people need calm UX with a privacy-first architecture.

AI Applications · Local-first · Privacy · Mobile-first PWA

  • nextjs
  • pwa
  • local-first
  • privacy
Open live

Advisory Assessment Application

Live

AI Production Readiness Advisor

Shipping an AI demo is easy. Shipping AI that people can trust is much harder — teams need the right questions before deployment, not another checklist stamp.

AI Applications · Eight dimensions · Hard gates · OpenAI advisory narrative

  • nextjs
  • openai
  • rag
  • governance
Open live

Enterprise Architecture Intelligence

Live

ArchLens AI

Architecture reviews fail when recommendations are unfalsifiable — hand-authored findings with no check that sources exist or say what the claim asserts.

AI Applications · Verifier gate · Evidence spans · Human approval

  • nextjs
  • typescript
  • zod
  • governance

Capabilities

What I bring

Senior architecture judgment applied to AI-enabled delivery.

  • AI solution architecture

    Frame the problem, choose boundaries, and design systems that stay correct, private, and operable.

  • Cloud modernization

    Ship cloud-hosted products with clear service edges, CI, and production judgment—not demos that stop at the UI.

  • AI-enabled software delivery

    Use AI assistants to accelerate delivery while keeping architecture, tests, and risk ownership with the engineer.

  • Privacy-minded product design

    Decide what never to collect. Local-first and data-minimization when the product requires trust.

Featured insight

A line worth sitting with

Judgment on the page — start here if you want the thinking behind the builds.

Unity Catalog did not block it. By default, catalogs can be accessible from every workspace attached to the same metastore, subject to privileges.
Cloud & DataRead the insight →

About

Concise background

Based in the Greater Pittsburgh Region. Career spanning enterprise platforms, CMS/DXP, cloud delivery, and long-lived product systems — now documenting AI-enabled delivery through a personal lab.

Next step

Glad you stopped by

Exploring an AI-focused role, or want a senior perspective on architecture and delivery? I’d enjoy hearing what you’re building.