Work

ScholarFlow

AI
FastAPI
Next.js
Product Thinking

An academic publishing workflow system that showcases AI-friendly stack choices, demand clarification workflows, and agent-driven development.

A layered workflow system representing academic publishing and AI-assisted development

The Problem

Academic publishing workflows are usually shaped by unclear requirements, many roles, and long feedback loops. I wanted to build a system that could handle those realities while also being comfortable to develop with AI agents.

The Approach

I chose a stack that fits both the product and the way I work:

  • FastAPI for the backend because the project needed text processing, API orchestration, and Python-friendly AI workflows.
  • Next.js for the frontend because it fits well with TypeScript, React, and AI-assisted UI iteration.
  • shadcn for UI consistency and fast component work.
  • Supabase, Vercel, and Hugging Face Spaces to keep the deployment story practical across the stack.

What It Demonstrates

ScholarFlow is the project where I moved from “AI helps me write code” to “I design workflows that help AI and humans make better decisions.”

It covers:

  • product and workflow thinking
  • full-stack implementation
  • requirement clarification through agent conversations
  • git-history-driven iteration
  • my shift from GUI-first AI tools to CLI agents and skill-based workflows

This is the project I would point to when explaining how I approach complex product work end to end.