Personal Projects (Side)

Designed a personal workflow framework that automatically manages AI coding agents' context, cost, and rules, deployed across 3 machines/instances

• Growing markdown knowledge base made manual context discovery by agents inefficient — Adopted a local-embedding (BGE-M3) vector RAG over cloud vector DBs (e.g., Pinecone) — chose local to auto-reindex immediately on markdown changes and avoid sync latency/cost; combined sqlite-vec with FTS5 (RRF fusion) for accuracy, exposed via MCP for direct agent search, Indexed 548 files / 3,347 chunks, 0.7s warm query, all 5 gold test queries hit within top-2/3
• 95% of AI agent token cost came from hidden areas (system prompt, subagents), making it untrackable — Built a cost analyzer that decomposes session transcripts into 8 categories instead of simple session/model aggregation, which could not trace hidden costs — added residual tracking to consolidate multi-machine, multi-tool usage into a single profile, Made 95% hidden cost visible by category; found and fixed a multi-instance usage-aggregation bug
• Doc-only rules were not applied when needed, and startup context bloated as instances grew — Switched from doc-only rules — not applied at the right moment — to Git hook enforcement (hook-first), and aligned core/agent configuration across 3 instances to reduce startup context, Cut rule files 20→7 / 1,174→163 lines, aligned startup context to 336 tokens across 3 instances

Built the deployment and scheduling infrastructure for a side project that auto-collects and normalizes job postings

• Free-tier hosting lacked cron support and the managed DB's free tier auto-paused, blocking scheduled jobs — Adopted a self-hosted Mac mini workflow-automation (n8n) scheduler instead of hosting cron, and standardized warm-up endpoints and secrets, Kept the free tier alive via daily DB warm-up and restructured manifest-based sync