Skip to content
Directory
GitHub Star

AI Agent Engineering Practice ​

Learn to build, validate and improve Agent systems, from specs, code and tests to incident analysis.

A passing local test does not establish final delivery; engineering observations do not certify financial research quality. Each article retains its actual evidence and unverified boundaries. Links marked “Chinese original” lead to articles without a published English edition.

IN THIS CATEGORY22 articles

Counts include articles in this category only; related reading is listed separately.

Tags · match all selected
01 / 02

Specs, Evidence and Engineering Memory

From specifications to execution evidence and durable project history.

  1. AI Coding Quality Panorama: Taking Responsibility for the Whole Project When AI Writes Most of the Code
  2. Agent Engineering Suite: Connecting Requirements to Release
  3. When Tests Outgrow the Code: Helping Docs, Code, and Tests Evolve Together
  4. Does the Code Really Support the Article? An Evidence Contract for Technical Writing
  5. Spec-Driven Agent Development: From Requirements to Trustworthy Delivery
  6. Evidence and Trustworthy Acceptance in Agent Development
  7. Why We Split a Large Weekly Review Spec into Three Phases
  8. Engineering Knowledge: Context, Memory and Retirement
02 / 02

Real Validation and Task Convergence

Testing runtime protocols, tracing, specialist handoffs and research quality beyond local green checks.

  1. Start with a Report You Can Read Back: Open ETF Agent v0.1
  2. Agent Evaluation Panorama: From Green Tests to Real Task Value
  3. Agent Evaluation Identity: Can Results Survive Model Failover?
  4. Building Agent Evaluation Sets Across Development and Acceptance
  5. How Do We Know the Main Agent Actually Used a Specialist’s Findings?
  6. How a null Broke an Agent Tool Call: A Streaming Compatibility Case
  7. RAG Recall Looks Great. Why Doesn’t That Prove the Agent Found the Right Financial Evidence?
  8. Why Did One Subagent Change Hold Up Our Work for an Entire Day?
  9. From Bug-Fix Loops to Task Convergence
  10. Why a Small ETF Investment Assistant Became an Engineering Problem
  11. The Expensive Part of AI Coding Is Deciding What Deserves Verification
  12. RAG: Revocation and Historical Replay
  13. Controlled Refresh for Stale Data
  14. Run Budget and Constraint Governance

All articles · Modules · Architecture

Engineering notes, evidence and boundaries. · Contact: hpoenixf@foxmail.com · WeChat: hpoenixf0510