Production Projects

AI systems built with real constraints — real metrics, real costs, real results.

Featured Projects

GitHub Copilot Agent Pipelines

GitHub Copilot Agent Pipelines

Featured

Seven specialized Copilot agents that form a structured development workflow for a legacy Servoy enterprise application with 10,000+ functions, 1,000+ files, and 22 modules. Neo4j graph-powered code intelligence, cross-model orchestration, and a self-improving knowledge loop where every code review makes every agent smarter.

7 specialized agents in a structured workflow
10,000+ functions indexed in Neo4j graph
18 domain skills with self-improvement
GitHub Copilot Neo4j VS Code +1
View →
Ask Your Database Anything: The Metabase Version

Ask Your Database Anything: The Metabase Version

Featured

An AI-powered system that converts plain English questions into complete six-card Metabase dashboards in under 30 seconds, 100% SQL success rate on a 90.5-million-row production database, embeddable in any React application via the Metabase SDK.

Under 30 seconds from question to six-card dashboard
90.5M rows across 48 tables, 561 columns
100% SQL success rate across 10+ query categories
React 18 + TypeScript + Vite Metabase 0.56 + Embedded SDK FastAPI + Python 3.11 +2
View →
Ask Your Database Anything: Native React Dashboards

Ask Your Database Anything: Native React Dashboards

Featured

Type a question, get a six-card dashboard rendered with native React charts in under 30 seconds, no Metabase, no Java, no BI server. 100% SQL success rate against a 90.5-million-row production database.

Six-card dashboard in under 30 seconds
100% SQL success rate across 10+ query categories
90.5M rows across 48 tables, 561 columns
React 18 + TypeScript + Vite Apache ECharts 6 + AG Grid 35 + Leaflet 1.9 FastAPI + Python 3.11 +2
View →
RAG Document Assistant: From Single-Purpose Chatbot to Multi-Repository Document Platform

RAG Document Assistant: From Single-Purpose Chatbot to Multi-Repository Document Platform

Featured

A RAG-based document assistant that ingests 51,000+ chunks across 4 file formats, answers natural language questions in under 3 seconds using hybrid search with cross-encoder re-ranking, and required zero frontend changes to transform from a single-purpose chatbot into a general-purpose document platform.

51,000+ document chunks indexed
Under 650ms retrieval pipeline
Under 3 second total query time
Python 3.11 + FastAPI Qdrant Vector Database sentence-transformers (all-mpnet-base-v2) +3
View →
Obsidian Notes Pipeline: AI-Powered Knowledge Management

Obsidian Notes Pipeline: AI-Powered Knowledge Management

Featured

A full-stack RAG application that transforms YouTube videos into interconnected Obsidian notes -- 1,000+ notes, 2,757 auto-generated links, 5,000 searchable chunks, and a chatbot with 2.5s latency, all for $1.50.

1,000+ notes → knowledge graph
2,757 bidirectional links
2.5s RAG chatbot response
FastAPI React 18 PostgreSQL +3
View →
Job Search Agent: AI-Powered Career Pipeline

Job Search Agent: AI-Powered Career Pipeline

Featured

An automated job search system that monitors 1,975 companies across 11 ATS platforms, processes 58,807 jobs weekly through a 6-phase AI pipeline, and delivers 311 qualified matches for $5.04 per run.

1,975 companies monitored
58,807 jobs processed per week
311 curated matches delivered
Python 3.11 FastAPI Anthropic Claude (Haiku 4.5, Sonnet) +6
View →
Adversarial Agent Testing

Adversarial Agent Testing

Featured

AI agents that attack each other to find vulnerabilities. Red Team probes, Blue Team defends, a Referee scores both -- all using Claude Code with worktree isolation. Two rounds of live exercises against a real target drove ASR from 65% CRITICAL to 47% HIGH, with a regression wave proving patches hold at 20% and an escalation wave exposing architectural gaps at 85.7%.

ASR 65% → 47% across 2 rounds
27 attacks, 14 defense patches
10/10 OWASP category coverage
Claude Code Python UV Scripts (PEP 723) +2
View →
Claude Code Bootstrap Framework

Claude Code Bootstrap Framework

Featured

An agent swarm that builds agent swarms. A 12-step pipeline where Claude Code agents analyze any codebase and generate complete Claude Code infrastructure -- agent teams, hooks, skills, and slash commands -- in 30-55 minutes. Three production migrations validated. The second was harder but faster.

3 production migrations validated
17 skills + 17 hook templates
12-step generation pipeline
Claude Code Python UV Scripts (PEP 723) +2
View →