Building intelligent systems with a quiet rhythm.
AI engineer in Shenzhen, focused on LLM applications, agent workflows, multimodal generation, and RAG systems. I care about turning prompt experiments into reusable, observable, product-grade systems.
Built a staged LLM pipeline for script parsing, narrative slicing, scene analysis, and shot generation. The system moves storyboard generation from single-prompt output into a reusable workflow with cross-episode character and scene memory.
Reframed the bottleneck from isolated highlight detection to cross-episode identity stability. The rebuilt path supports entity alignment, retrieval, scheduling, and cache reuse for more continuous generated edits.
Designed hierarchical document chunking, multi-stage retrieval, dynamic threshold filtering, and prompt-assisted safety review. Internal tests reached about 90% recall and answer accuracy.
Virtual pet statusline for Claude Code -- watches your rhythm, coaches your pace, grows with you.
Developer workflow memory for AI-assisted engineering. Preserves intent, decisions, risks, and recycles them into daily notes, weekly reports, and architecture docs.
CLI that turns web sources into structured research reports with evidence tags, source citations, and automated compliance checks.
AI-focused Hacker News digest that fetches and analyzes daily AI and agent-related posts with commentary.
Structured AI-assisted development sprint workflow for planning, execution, and review in agentic coding sessions.
Local continuity layer for agentic work. Turns interrupted sessions into replayable continuation points via Agent Capsules.
Junlin Zhu, Jiaye Wu, Xudong Luo*, Jie Liu (*Corresponding authors)
Artificial Intelligence and Law (Artif.Intellig.& L), Vol. 32. · Journal Article
Jiaye Wu, Xudong Luo* (*Corresponding authors)
Knowledge Science, Engineering and Management (KSEM), 2021. · Conference paper