AI Builder Showcase

Building AI
agents that
actually ship.

A collection of production-ready AI projects — from multi-agent office automation to AI-powered ticket management and investment analysis frameworks.

CrewAI Agents
Auto Tickets
GPT-4o Powered
21 Frameworks
3
AI Projects
21
Analysis Frameworks
Multi
Agent Architectures
LLM
Powered at Core
AI Projects

What I've built

Each project tackles a real workflow pain-point using LLMs and autonomous agents — designed to be deployed, not just demoed.

01
Live
Agent Ticket System

AI-powered task ticket manager that analyses a software project (local repo or GitHub URL) and automatically generates structured, actionable tickets — no database required. Think Jira, but driven by an LLM that reads your code.

0-DB
Architecture
REST
API Layer
Full
Test Suite
LLM FastAPI Python OpenAI
02
Live
Agent Office System

Multi-agent office automation built on CrewAI and GPT-4o. Handles email drafting, document summarisation, and US stock analysis — all scheduled automatically and tracked in a Streamlit dashboard with SQLite cost logging.

4
AI Crews
Auto
Scheduled
Cost
Tracked
CrewAI GPT-4o Streamlit Gmail API SQLite

Agent Office System — how it works

Four specialised CrewAI crews run independently via APScheduler. Every run is persisted to SQLite so you can audit token usage and cost.

main.py
APScheduler
CrewAI Crews
GPT-4o
SQLite Ledger
01

EmailCrew

Drafts email body from natural-language intent, then sends via Gmail SMTP using GmailSendTool.

02

DocSummaryCrew

Reads PDF / DOCX / TXT → produces a structured summary → emails it automatically.

03

StockSummaryCrew

Pulls live yfinance data, runs GPT-4o analysis, delivers a market summary to your inbox.

04

SQLite Cost Ledger

Every crew run logs token count, cost, status, and timing — visible in the Streamlit dashboard.

agent_office_system / architecture
main.py (CLI) ├── email → EmailCrew → Gmail Agent → GmailSendTool ├── summarize → DocSummaryCrew → Document Analyst → DocReaderTool → GmailSendTool ├── stock → StockCrew → US Stock Analyst → yfinance → GmailSendTool ├── scheduler → APScheduler (reads schedule.yaml) └── ui → Streamlit Dashboard All agents → LLM: OpenAI GPT-4o → runs.db (SQLite)

InvestSkill — what's inside

Every framework is a battle-tested prompt that works as a slash command in Claude Code or as a plain-text input on any LLM. No installation for most platforms.

01

stock-eval

Piotroski score, ROIC, moat rating, FCF yield, buy / hold / sell signal in one shot.

02

sector-analysis

Identify rotation opportunities and relative strength across S&P 500 sectors.

03

insider-trading

Track SEC Form 4 filings — spot clusters of insider buying before they move.

04

earnings-call-analysis

Sentiment, key themes, and management tone extracted from earnings transcripts.

05

institutional-ownership

Track 13F filing changes — follow smart-money moves across hedge funds.

06

portfolio-review

Evaluate allocation, risk-adjusted returns, and concentration for any portfolio.

InvestSkill / quick-start
# Claude Code — recommended, full slash-command support claude /plugin marketplace add yennanliu/InvestSkill /plugin install us-stock-analysis /us-stock-analysis:stock-eval AAPL # Cursor / Gemini CLI / ChatGPT — zero install cat prompts/stock-eval.md | pbcopy # → paste into any LLM

Agent Ticket System — how it works

Point it at a repo, get structured tickets. The LLM reads your code, infers missing context, and writes tickets an engineer would actually act on.

Repo / URL
Indexer
LLM Analysis
Structured Tickets
REST API
01

Repo Ingestion

Feed a local path or a GitHub URL — the agent clones, indexes, and reads the codebase automatically.

02

Auto-Generation

LLM produces structured tickets with title, description, acceptance criteria, and priority.

03

FastAPI Backend

Clean REST API served by uvicorn — integrate with Jira, Trello, or any issue tracker via webhook.

04

Full Test Suite

pytest suite covering API endpoints and storage layer — designed to run in CI from day one.

agent_ticket_system / quick-start
# Quick Start uv sync --extra dev cp .env.example .env # add OPENAI_API_KEY uv run uvicorn main:app --reload open http://localhost:8000 # Tests uv run pytest tests/ -v
Let's build together

Interested in AI-powered systems?

I'm always open to collaborating on ambitious agent projects.
Reach out or explore more of my work below.

Get in Touch Full Portfolio GitHub