LEARNER · THINKER · BUILDER
Across the stack, from idea to working product.
I’m Fish. I hold a master’s degree in physics, received rigorous training in scientific computing, and have more than a decade of experience in software development and systems design. I now focus on AI agents, data intelligence, and product engineering. Across enterprise software, cross-border commerce, and Web3D, I learn new domains quickly and turn requirements into reliable products that can keep evolving.
Journal
Latest Writing
Sub2API Gateway Internals and Enterprise Agent Architecture
A source-level study of streaming proxying, account-pool scheduling, atomic Redis concurrency control, multi-level authentication caching, and idempotent billing in Sub2API.
Knowledge Engineering and Tunable Cockpit Architecture for Enterprise RAG
A deep dive into enterprise RAG knowledge engineering: structure-aware chunking, hybrid Dense+Keyword retrieval with RRF reranking, lifecycle metadata governance, MCP boundaries, and the Retrieval Lab evaluation loop.
Branch Governance with Cherry-Pick in Multi-Factory Deployments
Managing multi-site code deployments: using single-path cherry-pick workflows to distill features into atomic trunk commits before promoting to factory deployment branches.
Labs
Three Fields, Three AI Practices
Quantitative research, cross-border commerce intelligence, and enterprise knowledge systems: three projects exploring how AI agents can improve research, business decisions, and knowledge work through different engineering stacks.
RunningAI Quant Research Cockpit
An auditable research loop for market data, fundamentals, sentiment, factors, backtests, and learning.
RunningCross-border Trend Report
Traceable product discovery and margin analysis from multi-source catalogs, trends, and exchange rates.
RunningEnterprise AI Cockpit
A single workspace connecting enterprise knowledge, vector retrieval, streaming answers, and business charts.