Ai on Mengboy 技术笔记

RAG Accuracy Playbook: Retrieval Recall, Re-Ranking, and Evaluation Loop

Tue, 17 Feb 2026 10:56:00 +0800

If your RAG system feels unreliable, switching to a more expensive LLM is usually the wrong first move. In most cases, the bottleneck is retrieval quality: weak recall, poor ranking, and no measurement loop.

This guide gives a practical path: make recall broader, make ranking sharper, then close the loop with offline + online evaluation.

RAG 不准怎么办：检索召回、重排与评估闭环落地指南

Tue, 17 Feb 2026 10:56:00 +0800

很多团队做 RAG 的第一反应是“把 embedding 换成更贵的模型”，结果成本上去了，效果却不稳定。真正的问题通常不在生成，而在检索链路：召回不全、排序不准、评估缺失。

这篇给一套可直接落地的做法：先把召回做厚，再把重排做准，最后用离线 + 在线指标形成持续优化闭环。

OpenAI Responses API + MCP in Practice: From Function Calling to Agent Workflows

Wed, 11 Feb 2026 23:15:00 +0800

If you’ve already used function calling but keep writing glue code for every non-trivial task, you’re likely at the point where Responses API + MCP makes more sense.

This guide is practical: how to move from single tool calls to a scalable agent workflow where retrieval, execution, validation, and write-back follow a consistent structure.

OpenAI Responses API + MCP 实战：从函数调用到 Agent 工作流

Wed, 11 Feb 2026 23:15:00 +0800

如果你已经做过函数调用（function calling），但一上复杂流程就开始写一堆胶水代码，那你差不多到了该用 Responses API + MCP 的阶段。

这篇不讲空概念，直接给你一个可落地的路线：把“模型调用工具”升级成“可扩展 Agent 工作流”，让检索、执行、校验、回写变成标准流程。

Claude / Codex / OpenAI CLI 工作流对比：开发效率怎么选

Mon, 09 Feb 2026 23:28:00 +0800

如果你把 AI 只当“聊天工具”，三家看起来差不多；但一旦进入真实开发链路，差异会非常明显。

我的结论先放前面：日常编码+项目内改动优先 Codex，长文推理和方案拆解用 Claude，OpenAI CLI 适合做标准化自动化和跨工具串联。

Claude vs Codex vs OpenAI CLI: Which Workflow Actually Improves Dev Productivity

Mon, 09 Feb 2026 23:28:00 +0800

If you use AI as a chatbot only, these tools feel similar. In real engineering workflows, they behave very differently.

My conclusion first: use Codex for repo-native coding changes, Claude for deep reasoning and long-form planning, and OpenAI CLI for standardized automation pipelines.

Software Engineering History: From Software Crisis to AI Co-Creation

Wed, 31 Dec 2025 12:30:15 +0800

Large language models are changing how we clarify requirements, generate code, and design tests, and many teams feel that traditional workflows are being rewritten. To understand what is truly changing, it helps to place today inside the longer history of software engineering.

This article walks through the major stages of software engineering and ends with the AI-era variables and a simple checklist so you can map your current problems to the right time scale.

软件工程发展史：从软件危机到AI共创

Wed, 31 Dec 2025 12:30:15 +0800

AI大模型让需求澄清、代码生成、测试生成都出现了新的路径，很多团队感到传统开发流程被重写了。要看清这一轮变化的本质，先把软件工程的历史脉络梳理出来会更有帮助。

本文按阶段回顾软件工程的发展路径，最后落到AI时代的变量与判断方法，方便你把当下的问题放回更长的时间尺度里看清楚。

常见prompt框架

Sat, 01 Mar 2025 22:16:47 +0800

deepseek出现后，AI的势头更加一路不可阻挡， cursor最近又更新了Claude 3.7，编程体验进一步提高，身为码农对未来还有几年职业生涯充满了焦虑。熟话说打不过就加入，AI的浪潮已经阻挡不了，最好的方式就是学习接受，细节算法实现暂且不提门槛太高，还是先从使用上入手，下面整理常见的prompt框架。