Personal IP Hub

Lyra Wang

A public record of work, method, learning, and writing.

View Work How I Work

What I Bring

The kinds of problems this work addresses

This section is reserved for a statement of what value this work creates.

Not yet published.

The value proposition is a decision reserved to the site owner and is published only once confirmed.

Featured Work

Selected proof

Selected proof through real products and systems — work that has been built and iterated through multiple phases.

01

Meeting Intelligence Agent

会议分析智能体

A meeting analysis agent integrated with real collaboration systems.

Problem

Meetings generate decisions, action items, and context that are hard to capture, structure, and follow up on — especially across tools people already use every day.

Practice

Built and iterated a meeting analysis agent through at least two tracked phases. Integrated with Feishu (Lark) systems, practiced third-party Open API integration, studied official API documentation, and worked through authentication, interfaces, events, and node chains. Gradually formed an "official docs + AI" development approach.

Current Stage

Used in a real collaboration context and iterated through multiple phases.

Evidence

Integrated with Feishu (Lark) systems, across multiple tracked phases of iteration.

02

Retail Operations System

进销存管理系统

A multi-year real-world retail operations system — a practice ground for product engineering.

Problem

A physical retail business needs sales, purchasing, and inventory to work together reliably over years — not as a one-off CRUD exercise, but as a system that can grow, be maintained, and be trusted.

Practice

Continuously practiced data structure design, began thinking about State Ownership and module boundaries, introduced Multi-Agent collaborative development with Architect / Developer / Reviewer / QA roles, and started paying attention to reliability, maintainability, and iterability.

Current Stage

Multi-year project, continuously evolving.

Evidence

A real, multi-year project serving an actual retail business scenario. Multi-Agent collaboration (Architect / Developer / Reviewer / QA) is being practiced.

03

WeChat Publishing System

微信公众号内容与发布系统

An AI-native publishing workflow that reduces the friction of public output.

Problem

Publishing written work publicly involves a chain of discussion, drafting, formatting, version control, platform submission, review, and release — each step adds friction that stops ideas from being shared.

Practice

Built a pipeline: ChatGPT for content discussion and crystallization → formatted files → GitHub for version control → automated entry into WeChat Official Account backend → human review → publication. Keeps human review in the loop by design.

Current Stage

AI-native publishing workflow in use.

Evidence

Real pipeline from ChatGPT through GitHub to WeChat Official Account backend. Human review is intentionally retained.

How I Work

Not just using AI tools — practicing an AI-native working method

AI is a way of working rather than a tool wall: framing problems clearly, defining contracts, letting AI implement, reviewing independently, and verifying through real runtime.

01 Problem Framing
02 Product / Architecture
03 AI Developer
04 Review / QA
05 Runtime
06 Feedback
07 Iteration

Read the full method

How I Learn

How understanding develops

Learning is recorded as it actually happens — through projects, reading, notes, and open questions — rather than as a list of courses or certificates.

Not yet published.

Learning records are added under the Learning domain once they are verified.

Journey

Time × Evidence

Public traces left over time, and the milestones that mark meaningful change.

github

GitHub

Public repositories and commit history over time.
Visit

No milestones published yet.

Milestones are added once the date and the change they represent are both confirmed.

Explore the journey

Selected Writing & Research

Formed for public expression

Essays, articles, research, and talks. Learning notes stay under Learning unless they are deliberately developed into a public piece.

Not yet published.

Nothing is listed here until a piece is actually published and its public link is confirmed.

Go to Writing & Research

Now

What I'm working on and learning — through practice

What is being learned by doing, right now, through real projects.

Product Engineering

Through the Retail Operations System, continuing to understand what it takes to build software that lasts.

Data structure design
State Ownership
Module boundaries
Reliability
QA
Maintainability
Product iteration

System Integration

Through the Meeting Intelligence Agent, deepening understanding of how systems talk to each other.

Open API
Authentication
Events
Callbacks
Request / Response
Data passing
System node chains

AI Collaboration

Continuously practicing how to work with AI as a real development partner, not just a tool.

Multi-Agent collaboration
Architect / Developer / Reviewer roles
Context provision
Contract definition
AI-native product development

See what I'm doing now

Connect

Where to go next

Explore the work, follow the writing, or get in touch.

GitHub
github.com/LyraWang6688

Contact details not published yet.

A contact address is added once it is confirmed and safe to publish.