RAG Agents
to Production AI.

A production-oriented RAG backend that turns documents into grounded answers through an 8-node LangGraph workflow. The graph classifies the request, rewrites queries, retrieves from hybrid search, reranks candidates, grades relevance, generates the answer, and runs a hallucination check before returning the response. A second LangGraph supervisor routes complex requests across specialized RAG, Code, Analysis, and Chitchat workers, then aggregates the result. The system is exposed through FastAPI endpoints with SSE streaming, Docker deployment, RAGAS evaluation, and LangSmith tracing.

A manuscript editing agent built to turn English-first or translation-heavy drafts into natural Korean technical prose. The workflow uses LangGraph for staged writing and revision, ChromaDB for style retrieval, and SentenceTransformers for semantic search over reference books and blog samples. It preserves code blocks and headings, validates revised sections, detects length collapse or meta text leakage, and falls back to source text when revision quality fails. The pipeline was used on two technical books across Tauri 2 desktop app development and Python quant trading AI.

An ML-driven stat-arb system, designed and operated solo — from alpha research through live execution on IBKR. The core problem with statistical arbitrage is regime dependency: cointegration that holds in mean-reverting conditions deteriorates in trending regimes, causing pair spreads to diverge without reversion. An HMM regime classifier detects the current market state in real time and routes signals to the appropriate strategy branch. A SAC RL agent handles position sizing — its entropy-maximizing objective scales exposure with predicted signal strength, automatically cutting risk when conviction is low. Entry and exit signals are generated by an XGBoost / LightGBM / CatBoost ensemble and a PyTorch TFT sequence model, trained on multi-timeframe features from FMP, FRED, yfinance, and Alpha Vantage. QuestDB stores 10 years of 5-minute bars for time-series queries, with DuckDB used for analytical feature work. Live orders execute on IBKR via ib-async.

A Tauri 2 native desktop app for reading English technical books in your native language, paragraph by paragraph. The original approach attempted to fine-tune T5 and fairseq models directly on Korean–English pairs — this was abandoned when the Korean training corpus proved too thin, producing token-level noise instead of coherent output. The architecture was rebuilt around Claude Haiku via the Anthropic API, with the Rust backend handling all network I/O through reqwest, while pdfjs-dist on the SvelteKit frontend extracts and segments paragraph-level text blocks from PDF files. An SSE-streamed Ask AI panel lets users ask questions mid-read, injecting the current page text as context so answers are always relevant to what's on screen.

A Tauri 2 desktop app that replaces three separate productivity tools — Mandala Chart, GTD, and Pomodoro — with one coherent workflow. The Mandala Chart gives goals a spatial structure: each outer cell expands into its own 3×3 action plan, with a drill-down navigator that moves through hierarchy levels. GTD state management runs as an explicit state machine in Rust, tracking items across Inbox → Next Actions → Waiting → Done with enforced transitions. Pomodoro sessions drive the focus cycle and write session data to DuckDB through the Rust backend, keeping everything local-first with no cloud dependency. An Ask AI feature injects the current goal and its context into an OpenAI/Anthropic prompt and streams the coaching response back via SSE.