Hi, I'm Alfred Lin
AI product and Agent practitioner focused on the system-level collaboration between technology, product, and business.
AL

About

Work Experience

Skills

Python
HTML
CSS
JavaScript
Agent Eval
Agentic Engineering
Context Engineering
AI Product
System Thinking
My Projects

check out my latest work

I've built projects across content platforms, AI products, and full-stack web apps, including hands-on work with LLM, Agent, and RAG systems.

Open Record/Replay

Open Record/Replay

An open-source port of Codex's Record & Replay capability — letting any agent learn and replay macOS desktop workflows from a single user demonstration.

Node.js
Swift
macOS Accessibility API
Computer Use
Claude Code
Agent Skill Design
Context Engineering
Sdecky

Sdecky

A consulting-grade presentation AI agent that turns ideas into structured, data-driven decks.

TypeScript
Next.js
React
Tailwind CSS
LLM API
RAG
Agent System Design
Agent Eval
Context Engineering
The Story of Us

The Story of Us

A documentary-style website capturing real personal stories to reflect the China and world I experienced.

TypeScript
Next.js
React
Tailwind CSS
Markdown
PhotoSwipe

MACH Markdown2AIchat

A tool that renders Markdown into a high-fidelity mobile AI chat UI with streaming simulation and one-click export.

TypeScript
Next.js
React
Tailwind CSS
Markdown

THU Scooter 101

A one-stop information hub for Tsinghua e-scooter usage, including buying, charging, parking, maintenance, and policy updates.

TypeScript
Next.js
React
MongoDB
SQLite
Tailwind CSS
Framer Motion
My Blog

latest 4 blog posts

A quick selection of my latest writing and field notes.

Prompting for Agents: Practical Insights from the Claude Code Team

Prompting for Agents: Practical Insights from the Claude Code Team

Field notes and patterns for prompting agentic systems effectively, drawn from Claude Code and my own production experience.

Blog
Context Engineering Explained

Context Engineering Explained

Why context, not just model size, determines whether an LLM product holds up in production.

Blog
MCP: Breaking Data Silos, the AI Type-C

MCP: Breaking Data Silos, the AI Type-C

Why Model Context Protocol matters: a practical explanation of how MCP standardizes access between LLMs, tools, and external systems.

Blog
Nexus Beyond Homo Sapiens: Humanity and AI Through the History of Information Networks

Nexus Beyond Homo Sapiens: Humanity and AI Through the History of Information Networks

My reading notes on Nexus and why AI may become the first information technology capable of becoming a node inside civilization itself.

Blog
PRINCIPLE

One word defines how I build.

Emancipate

Let systems absorb complexity, and return time to people.

LinkedIn
X
中文