This series consolidates my learning journey on AI Agents, mostly my own experiences working with Codex in various projects.

AI Agents 101

This section is my foundation map for AI agents. Most of the first drafts were created with Codex, but I still treat them as my own learning notes rather than finished references. The goal is to build a clear path from the basic idea of an agent to the engineering details that make agents useful in practice.

My contribution to this section is:

  • create the first draft of the high-level topics I want to understand
  • define the structure of each topic, starting from a high-level abstraction and then moving into more concrete engineering details
  • review each draft and add references, examples, or resources when I find something relevant later. For example, I recently noticed more discussion around Loop Engineering, so I added it to From Prompt Engineering to Agent Systems Engineering
  1. Why Agents, Why Now
  2. From Prompt Engineering to Agent Systems Engineering
  3. The Core Agent Model
  4. Agent Loop and Runtime Design
  5. Context and Memory
  6. Tools, MCP, Skills, and Plugins
  7. Orchestration Patterns
  8. Data Layer and Enterprise Integration
  9. Safety, Security, and Governance
  10. Evaluation and Observability
  11. Production Agent Architecture
  12. Agentic UX
  13. Coding Agents as a Case Study
  14. Standards and Ecosystem

Deep-Dive Topics

This section is for topics that I personally find more interesting and want to study more deeply with Codex. Compared with AI Agents 101, these posts are less like a broad curriculum and more like focused research notes. I usually spend more time reading papers, checking claims, organizing evidence, and refining the explanation before publishing them here.