Article Catalog
This library lists the original Chinese essays in three canonical categories. Completed English translations live under /en/articles/<slug> and share the same slug as the original.
Availability: Fully translated articles link directly to their English Markdown and localized Mermaid/table content. “Chinese original” means a full English edition has not yet been published; those links still lead to the original Chinese text.
01 / Module Deep Dives
Concrete mechanisms from input through execution to delivery.
Research, Reading and Computing
How Entry, Web, PDF, subagents and isolated computation cooperate.
- Entry: Why the Entry Point Became Simpler (Chinese original)
- Web Research: From Search to Deep Reading (Chinese original)
- PDF: From Text to Evidence
- Subagents: Isolation and Specialized Collaboration (Chinese original)
- Adaptive Research and Python (Chinese original)
- Python: From Tool to Computational Workbench (Chinese original)
- Connecting Portfolio Data Through a Read-Only MCP (Chinese original)
- Controlled Refresh for Stale Data
Context, Results and Knowledge
What the model sees and which evidence it may read.
Runtime, Extensions and Observability
How capabilities are discovered, authorized, executed and observed.
- Extension Host: From Feature Phone to Smartphone (Chinese original)
- MCP Host: From Discovery to Usable Tools (Chinese original)
- Tool Surface: Why the Model Cannot See an Available Tool
- Multi-Ecosystem Hooks: Claude, Pi and Codex (Chinese original)
- Observing the Tool-to-Model Input Lifecycle
- Run Budget and Constraint Governance (Chinese original)
- Scheduled Research Beyond a Conversation
- Langfuse: From Traces to Trustworthy Observability (Chinese original)
Answer Delivery and Recovery
An answer candidate, durable effects and delivery are separate facts.
02 / Architecture and Systems Thinking
System boundaries, responsibility, reliability and change.
System Architecture and Responsibilities
Who interprets, authorizes, owns facts and removes obsolete structures.
- From One Question to a Six-Layer Agent System (Chinese original)
- Models Understand; Code Authorizes
- Don't Turn the Model into a State Machine (Chinese original)
- Responsibilities of Model, Runtime, MCP and Skills (Chinese original)
- Run Termination, Stage Budgets and Safe Recovery (Chinese original)
- Why Financial Market MCP Became a Decision System (Chinese original)
Reliability, Feedback and Governance
Find the real point of failure instead of misdiagnosing feedback.
Evolution and Financial Boundaries
Distinguish analysis, advice, execution and reproducible financial calculations.
- Code Is Cheaper; Why Are Systems Harder to Evolve? (Chinese original)
- Why Saved HTML Can Still Fail Delivery
- Building an ETF Research Assistant
- Boundaries Between Research, Advice and Trading
- Financial Data: Time, Definitions and Reproducibility
- Why Python Results Can Still Be Misused in Reports
- A Trustworthy Evidence Chain for Financial Agents (Chinese original)
03 / AI Agent Engineering Practice
How coding agents develop, validate, maintain and evolve software.
Specs, Evidence and Engineering Memory
From specifications to execution evidence and durable project history.
Real Validation and Task Convergence
From misleading green tests to verifiable task completion.