Index 03
What I think

Writing.

Notes on AI engineering, independent development, products, and life systems.

Traditional Tests Pass, but How to Prove the Agent Is Actually Better

Traditional tests only prove the code isn't broken; they can't evaluate whether the Agent has truly improved. Eval is needed: run a fixed task set with unified scoring rules repeatedly, comparing success rate, cost, time, and regressions. The two systems complement each other; before release, pass traditional tests first, then run Eval, to avoid optimizing by feel.

#Agent开发 #AI评测Eval #大模型应用开发

2026/08/21

I Built a Coding Agent and Realized Calling the Model Is Just the Beginning

Building a coding agent taught me that calling the model is just the beginning. In long tasks, state management, tool logging, observability, and failure recovery are key. Chat is just the entry point; the system must act like a runtime to keep progressing and validating results. Reliability often matters more than a one-off impressive answer.

#效率提升 #产品思维 #AI编程

2026/08/21

ChatGPT and Codex Merge, Protocol Changes Again

After ChatGPT and Codex merged, the protocol changed again: tool definitions moved into additional_tools, and third-party models that don't receive tools may fake calls. The author's local gateway AgentGate has adapted, restoring tools and forwarding upstream; the merged desktop client can still point to localhost to call DeepSeek and other models.

#本地网关 #协议转换 #AI编程

2026/08/21

Sharing a Small Tool I Use Myself (Self-Made)

ReviewGate is an open-source MIT-licensed pre-merge filtering tool that screens for high-risk issues from perspectives like security, performance, logic, and AI Smell, categorizing them as block or warn. It prefers to fail rather than give a false green light. It supports --fix, CI integration, and false-positive sharing, and is read-only by default. It's recommended to observe first, then gradually enable.

#需求验证 #AI编程

2026/08/21

After Middle Age, Fitness Is Not Just for the Body, but Also for Preserving Time for Solitude and Thinking

After middle age, the meaning of fitness goes beyond physical exercise; it becomes a deliberate way to carve out uninterrupted personal time. It allows one to temporarily step away from work, family, and fragmented information, restoring attention and order, and reclaiming quiet space for independent thought. This ability to 'return to oneself' is more important than mere physical management.

#一人做事 #节奏感

2026/08/21

Working alone, it's easy to overestimate execution and underestimate direction and pace

When working alone, it's easy to overestimate execution and underestimate direction and pace. Execution is visible, but if the direction is wrong or the pace is chaotic, the harder you work, the further you may drift from key results. What truly matters is constantly judging the main line, stage priorities, and what's most important, avoiding being busy but not making real progress. A sense of direction and pace matter more than sheer effort for steady long-term progress.

#执行力 #方向感 #节奏感

2026/07/29

I Like Codex, but It Can't Use DeepSeek, So I Built a Local Gateway

The author likes Codex but wants to use DeepSeek, and finds the protocols incompatible. So they developed a local gateway called AgentGate. This tool converts Codex's Responses API requests into DeepSeek's Chat Completions format, and further implements intelligent routing: text-only tasks automatically go to DeepSeek, while multimodal tasks with images switch to KimiCoding. This solves the fragmentation of tool and model protocols in AI coding, letting users focus on development.

#本地网关 #协议转换 #AI编程

2026/07/29

Why Many Projects Become Unprofitable: It’s Not Slow Development—It’s Scope Creep

Project unprofitability is often attributed to slow development, but the more critical factor is scope creep. Slow development affects efficiency, while scope creep undermines the profit structure. Small requirements accumulate, causing scope creep, distorted quotes, and gradually eroded profits. Holding the line on boundaries is more important than improving efficiency: clarify what's not included, designate decision-makers, watch out for accumulating small changes, and define clear acceptance criteria.

#边界失控 #项目利润 #需求蔓延

2026/07/29