Article Catalog
Start with the nine architecture principles and seven engineering methods to orient your reading. Every article links back to that map, whether or not it belongs to a numbered principle.
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.
ESSENTIAL READING · START HERE
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)
- When an Agent Says Today: User Time and Market Sessions
- PDF: From Text to Evidence
- Subagents: Isolation and Specialized Collaboration
- A Custom Expert Should Be More Than a Prompt Field
- Adaptive Research and Python
- Python: From Tool to Computational Workbench
- 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.
- Provider: Why a Unified API Still Needs Shared Admission
- Why the Next Model Request Still Queues After HTTP 200
- Extension Host: From Feature Phone to Smartphone
- MCP Host: From Discovery to Usable Tools
- Tool Surface: Why the Model Cannot See an Available Tool
- Prompt Injection Is More Than Malicious Text: An Agent Content Trust Boundary
- Multi-Ecosystem Hooks: Claude, Pi and Codex
- Observing the Tool-to-Model Input Lifecycle
- Run Budget and Constraint Governance
- Agent Usage: Requests, Tokens and Shadow Credits
- Why an Agent Cannot Execute a Stop Command Immediately
- Scheduled Research Beyond a Conversation
- Langfuse: From Traces to Trustworthy Observability
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.
Deep and Continuous Research
Long-running background research, staged delivery, recovery and continuity of investment theses.
Subagents and Experts
Investment perspectives, bounded peer dialogues and collaboration across expert agents.
Finance and Engineering
Financial evidence, reproducible results, system evolution and end-to-end engineering quality.
- Why Financial Market MCP Became a Decision System
- 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)
- A Research Agent Needs More Than Tools: Model, Harness, and Loop
- Why More Citations Do Not Prove Reliability
- Building an ETF Research Assistant
- Code Is Cheaper; Why Are Systems Harder to Evolve?
- What Should Stay Stable—and What Should Change—in an Agent Architecture?
- Stop Blaming Every Failure on the Model
- Local Improvements Are Not System Progress
Other Architecture Topics
System overviews, model/runtime responsibilities, authorization and capability ownership.
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.
Historical architecture editions
The current six-layer V3 lifecycle is the one canonical reading entry. The complete V2 English edition and the V1 Chinese original remain readable as dated historical snapshots and are not counted again.