AI engineer building reliable agent systems and production-grade developer tools.
10 years in software engineering · Architecture · Evaluation · Reliability
I work where AI prototypes become dependable systems: agent architecture, evaluation, orchestration, and the engineering controls that make autonomous work observable and verifiable.
我专注于企业级 AI 应用与智能体工程，让原型真正具备可评估、可追踪、可交付的生产能力。
| Project | What it explores |
|---|---|
| octopus-skill 🐙 | Graph engineering for long-horizon agents: clean-context roles, durable state, and verified completion across Claude Code, Grok, Cursor, and Codex. |
| obsidian-llm-wiki | A maintainable knowledge system inspired by the LLM Wiki model, with namespace architecture, layered indexes, and reusable agent skills. |
| sherlock-claude | AI-assisted code analysis that turns repositories and runtime logs into focused diagnoses and actionable fix recommendations. |
- Agent systems — specialized roles, durable coordination, and bounded autonomy
- Evaluation & reliability — evidence-based acceptance, regression gates, and failure analysis
- Developer experience — tools that make advanced AI workflows easier to operate and inspect
- Knowledge engineering — structured context that stays useful as teams and codebases evolve
Make the state inspectable. Make “done” verifiable. Keep the system smaller than the problem it solves.
Python · FastAPI · LLM agents · Evaluation · Automation · Developer tooling