[{"excerpt":"A concise RAG evaluation reference organized by retrieval, context, answer, citation, refusal, security, and production metrics, with practical formulas and a minimal release-gate set.","permalink":"/en/posts/rag-evaluation-metrics-cheat-sheet/","title":"RAG Evaluation Metrics Cheat Sheet"},{"excerpt":"A RAG reranking design guide for AI Application Engineers. It distinguishes retrieval fusion, semantic reranking, business ranking, and evidence-set selection, then provides a production-ready default pipeline.","permalink":"/en/posts/rag-reranking-best-practices-2026/","title":"How to Rerank RAG Retrieval Results: From Hybrid Retrieval to Cross-Encoders, Listwise Ranking, and Evidence-Set Selection"},{"excerpt":"Based on 20 public job descriptions each from mainland China, the United States, and Tokyo, this study maps the hiring stack for AI Application, Agent, and RAG engineers and gives a Tokyo-focused learning and portfolio roadmap.","permalink":"/en/posts/ai-engineer-job-market-2026/","title":"2026 AI Application Engineer Job-Market Tech Stack: A Deep JD Study of Tokyo, Mainland China, and the US"},{"excerpt":"A programmer-oriented guide to Multi-Agent and Sub-Agent system design: when multiple Agents are needed, task decomposition and coordination patterns, context, permissions, reliability, evaluation, and production delivery.","permalink":"/en/posts/robust-multi-agent-subagent-design-2026/","title":"From Single-Agent to Multi-Agent: A Guide to Robust Sub-Agent System Design"},{"excerpt":"This article systematically explains context-compression methods for production AI agents, distinguishing message trimming, tool-result cleanup, artifact externalization, structured summaries, and native compaction. Using Hermes Agent, LangChain v1, and LangGraph v1, it presents a layered implementation and evaluation approach.","permalink":"/en/posts/ai-agent-context-compression-best-practices-2026/","title":"Context Compression for Production AI Agents: From Message Trimming and Tool-Result Cleanup to Hermes Agent's Layered Compaction"},{"excerpt":"An intuitive introduction for programmers without a machine-learning background to gradient descent, loss functions, backpropagation, learning rates, and optimizers in LLM training, from next-token prediction through parameter updates.","permalink":"/en/posts/gradient-descent-for-llm-training/","title":"Gradient Descent: How Large Language Models Learn to Generate Text from Random Guesses"},{"excerpt":"Using a simplified online bookstore as one continuous example, this guide explains the software diagrams commonly used for requirements, business, architecture, data, interaction, and deployment design.","permalink":"/en/posts/software-design-diagrams-online-bookstore/","title":"Which Diagrams Should You Draw Before Coding Starts?"},{"excerpt":"Starting with asyncio.run(), coroutines, Tasks, and Futures, learn how Python’s event loop schedules waits, timers, and I/O, and where sequential await, concurrent tasks, and blocking code differ.","permalink":"/en/posts/python-event-loop-task-awakening/","title":"Python Event Loop Fundamentals"},{"excerpt":"A systematic guide to lexical retrieval, dense retrieval, hybrid fusion, reranking, evaluation, observability, and production governance in RAG systems.","permalink":"/en/posts/rag-retrieval-engineering-guide/","title":"RAG Retrieval Engineering: From Hybrid Retrieval to Production Governance"},{"excerpt":"Explains how to build an observability and evaluation system for RAG that covers runtime execution, retrieval quality, generation quality, and continuous regression testing.","permalink":"/en/posts/rag-observability-evaluation-design/","title":"Designing Observability and Evaluation for RAG Systems"},{"excerpt":"Introduces OpenTelemetry’s core components and observability signals, and explains how to use them with AI agents, RAG, and production systems.","permalink":"/en/posts/opentelemetry-ai-agent-observability-guide/","title":"OpenTelemetry for AI Applications and AI Agents: A Beginner's Guide"},{"excerpt":"An introduction to RAG chunking design, progressing from fixed chunks to structural, contextualized, and evaluation-driven approaches.","permalink":"/en/posts/rag-chunking-strategies-evaluation/","title":"Best Practices for Chunking in RAG Systems"},{"excerpt":"Explains the role, calculation, appropriate use cases, and main limitations of RRF in multi-retriever fusion for RAG.","permalink":"/en/posts/rag-rrf-retrieval-fusion/","title":"The Role of RRF in RAG: A Simple but Not Universal Retrieval-Fusion Method"},{"excerpt":"An introduction to the roles of dense search, sparse search, RRF, and rerankers in an enterprise RAG retrieval pipeline.","permalink":"/en/posts/rag-dense-sparse-hybrid-search/","title":"Dense + Sparse Hybrid Search in RAG"},{"excerpt":"Use this article as a reference when building an enterprise RAG system.","permalink":"/en/posts/enterprise-rag-system-building-guide/","title":"A Guide to Building Enterprise RAG Systems"},{"excerpt":"On May 20, 2026, NVIDIA published a technical article explaining how to package AI-Q’s deep-research capability as a “specialized skill” callable by agent harnesses such as Claude Code, Codex, and OpenCode. The key point is not merely that another AI tool exists, but that the design proposes a clearer separation for enterprise Agents: a general-purpose agent harness manages conversation, tool orchestration, code execution, and user interaction, while a specialized research backend handles multisource retrieval, planning, synthesis, citations, evaluation, and enterprise data governance. (NVIDIA Developer) 1. Background: Why Shouldn’t a General-Purpose Agent Perform Deep Research Directly? Harnesses such as Claude Code, Codex, and LangChain Deep Agents are effective interaction entry points for developers. They maintain conversations, invoke tools, execute code, and turn user intent into action chains. But when the task becomes “generate a cited research report from multiple enterprise documents, internal databases, external materials, and regulated data sources,” the complexity quickly grows from “call several tools” into “build a complete research pipeline.” NVIDIA explicitly notes that enterprise teams must address data access, authentication, query routing, prompt tuning, output evaluation, and citation fidelity, and that these concerns should not be reimplemented in every harness. (NVIDIA Developer)","permalink":"/en/posts/deep-research-aiq-skill-agent-harness-mcp/","title":"Making Deep Research Pluggable: What NVIDIA AI-Q Skills Teach Us About Enterprise Agent Architecture"},{"excerpt":"Drawing on Latent Space’s interview with Shunyu Yao, this article reviews ReAct, Reflexion, Tree of Thoughts, memory, benchmarks, ACI, and Agent UX, and summarizes the importance of tools, environments, evaluation, and interface design when putting AI agents into practice.","permalink":"/en/posts/points-of-the-podcast-language-agents-from-reasoning-to-acting/","title":"What Did Tencent AI Leader Shunyu Yao Discuss in This Podcast?"},{"excerpt":"Starting from the trend of platforms absorbing basic RAG pipelines, this article examines the high-premium skills AI application engineers should prioritize in 2026: evaluation and observability, data governance and access control, and deep engineering capabilities for agentic workflows.","permalink":"/en/posts/ai-engineer-skill-value-map-2026/","title":"What AI Engineers Should Learn in 2026"},{"excerpt":"A personal schedule-adjustment manual based on sleep, circadian rhythms, and energy levels, designed to place high-value tasks at the times best suited to them.","permalink":"/en/posts/work-schedule-optimization-manual/","title":"Put the Most Important Work Where Your Body Performs Best: My Manual for Improving My Schedule and Using Time Well"},{"excerpt":"This article presents a core design framework for excellent AI agent systems, covering Spec-Driven Development, a three-layer architecture, resolvers, the boundary between latent and deterministic work, diarization, and a self-improving learning loop, helping engineers move from autocomplete-tool thinking to AI-augmented software engineering.","permalink":"/en/posts/ai-agent-architecture-design-guide/","title":"How to Design an Excellent AI Agent: From Architectural Principles to Practical Patterns"},{"excerpt":"Using the bandwidth gap between hidden states and tokens, this article offers one explanation for LLM engineering phenomena such as Chain of Thought, prompt length, few-shot learning, personality drift, and hallucinations.","permalink":"/en/posts/llm-from-hidden-state-to-token-output/","title":"When an LLM's Inner State and Its Words Diverge: A Master Key to Understanding LLM Behavior"},{"excerpt":"Drawing on 2025–2026 practices in AI coding agents and Spec-Driven Development, this article systematically explains the definition, value, essential components, workflow, and common pitfalls of a Software Spec, and provides a practical template for tools such as Claude Code, Codex CLI, and Cursor.","permalink":"/en/posts/ai-coding-agent-software-spec-best-practices/","title":"A Core Skill in the Age of AI Coding Agents: Writing Effective Software Specs"},{"excerpt":"A systematic tour of the entire LLM training pipeline—from data pipelines, scaling laws, system constraints, synthetic data, distillation, post-training, and evaluation systems to agent training—and how these mechanisms affect model selection, evaluation, and harness design for AI application engineers.","permalink":"/en/posts/llm-training-for-ai-engineers/","title":"The Full Landscape of LLM Training: What Every AI Application Engineer Should Understand"},{"excerpt":"Starting from how AI coding agents execute work, this article explains why agent-native documentation has evolved from reference material into infrastructure, defines the responsibilities and organization of AGENTS.md, PRD, Architecture, Spec, and Plan documents, and shows how Context Engineering and Spec-Driven Development can produce a context-efficient system that reliably directs agent behavior.","permalink":"/en/posts/agent-native-documentation-engineering/","title":"Agent-Native Documentation Engineering: Designing Documentation for AI Coding Agent-Driven Development"},{"excerpt":"This article systematically reviews frontline experience from OpenAI, Anthropic, HumanLayer, and other teams documenting AI coding-agent projects. It explains why entry-point files, layered knowledge bases, state-tracking files, and local documentation directly affect Agent performance, and provides an actionable path from a minimum viable documentation system to continuous maintenance.","permalink":"/en/posts/ai-coding-agent-documentation-best-practices/","title":"How to Write Documentation for an AI Coding Agent"},{"excerpt":"Begin with a Comparison You ask ChatGPT, “What is a KV cache?” The model answers, and the conversation ends. You tell Codex CLI, “Add a user-authentication module to this project, including tests.” The agent begins working autonomously: read the project structure → understand the existing code → plan the implementation → write authentication logic → write tests → run tests → observe a failure → fix it → get the tests passing → open a pull request. The process may span dozens of steps without requiring your intervention. The underlying LLM may be the same, but the behavior is entirely different. The first is the traditional use of an LLM. The second is an agentic use. This article explains the nature of that transition. It is more than a stronger model. It is a fundamental shift in the way the model is used, and that shift reshapes the entire engineering system around it.","permalink":"/en/posts/llm-agentic-evolution/","title":"The Agentic Evolution of LLMs: From Answering Questions to Working Autonomously"},{"excerpt":"The Landscape at a Glance If you are a Java backend engineer trying to understand the current standardization landscape for AI agents quickly, use the following correspondences: Communication/Configuration Type AI Agent Standard Java Analogy Originator Governing Body Adoption Status Agent ↔ tools/data MCP JDBC Anthropic AAIF (Linux Foundation) ✅ De facto standard Agent ↔ Agent A2A RMI / gRPC Google Linux Foundation ✅ Rapidly being adopted Project-rule configuration AGENTS.md application.yml OpenAI AAIF (Linux Foundation) ✅ De facto standard Reusable capability package SKILL.md Maven Plugin Anthropic agentskills.io (open standard) ✅ De facto standard Application framework Goose / Claude Agent SDK / ADK Spring Boot Various vendors Some governed by AAIF 🔶 Multiple competitors Microservice governance Harness Engineering system Spring Cloud — — 🔴 No standard Testing/evaluation Agent evaluation framework JUnit — — 🔴 No standard Code-quality governance Entropy management SonarQube — — 🔴 No standard The upper half marked ✅ has reached industry consensus or de facto standard status. The lower half marked 🔶 or 🔴 remains a frontier under exploration. This article primarily explains the complete picture of the upper half, then considers how the lower half may evolve.","permalink":"/en/posts/ai-agent-standards-full-landscape/","title":"The Full Landscape of AI Agent Industry Standards: A Java Engineer's Perspective"},{"excerpt":"For developers learning AI application engineering, this article maps the complete RAG pipeline from ingestion, chunking, retrieval, reranking, and generation to evaluation and operations, and presents an evolution path from a minimal viable solution to production.","permalink":"/en/posts/rag-system-complete-guide/","title":"The Complete RAG Systems Guide: From Zero to Production"},{"excerpt":"This article connects cross-entropy, perplexity, temperature, conditional entropy, hallucination detection, and prompt constraints into one line of reasoning, showing how entropy provides a unified language for understanding LLM training, inference, and product design. It also explains entropy’s practical value in RAG and engineering governance.","permalink":"/en/posts/entropy-in-llm/","title":"Entropy in LLMs: A Unifying Language from Training to Inference and Products"},{"excerpt":"This article systematically explains the core concepts and four-stage workflow of Spec-Driven Development, as well as its fundamental difference from vibe coding. Drawing on today’s tools and maturity levels, it explains why writing a specification before implementation substantially reduces ambiguity and rework in the age of AI coding agents.","permalink":"/en/posts/spec-driven-development-guide/","title":"Spec-Driven Development Explained: From Prompt and Pray to Spec and Steer"},{"excerpt":"Drawing on benchmarks and industry practice from multiple organizations, this guide presents default RAG chunking settings, parameter-tuning methods, and strategies for different document types.","permalink":"/en/posts/rag-chunking-best-practices/","title":"RAG Chunking Best-Practices Guide"},{"excerpt":"LangChain’s breakdown of the agent harness connects context engineering, memory, MCP, and the agent loop into one coherent map.","permalink":"/en/posts/agent-model-harness/","title":"Agent = Model + Harness"},{"excerpt":"Starting with the fundamental distinction between concurrency and parallelism, this guide systematically explains when to use Python’s GIL, threading, multiprocessing, asyncio, and concurrent.futures, how they work together, and how to choose among them.","permalink":"/en/posts/python-concurrency-parallelism-complete-guide/","title":"The Complete Guide to Concurrency and Parallelism in Python: The Evolution from One Thread to Multiple Cores"},{"excerpt":"Build a practical mental model for Python async programming in web backends and AI applications, from iteration protocols, generators, and coroutine objects through awaitables, Tasks, Futures, the event loop, structured concurrency, async iteration, and thread and process pools.","permalink":"/en/posts/python-async-programming-complete-guide/","title":"Python Async Programming: A Complete Guide from Iteration Protocols to Coroutines, Tasks, and Thread Pools"},{"excerpt":"A long-form Prompt Engineering guide for AI application engineers, covering foundational principles, context design, task chains, injection defenses, agent prompt design, and evaluation-driven development.","permalink":"/en/posts/prompt-engineering-best-practices-guide/","title":"The Complete Best-Practices Guide to Prompt Engineering"},{"excerpt":"Starting from Anthropic’s Contextual Retrieval article and Appendix II, these notes summarize the core method, experimental findings, and RAG architecture principles suitable for production.","permalink":"/en/posts/anthropic-contextual-retrieval-reading-notes/","title":"Notes on Anthropic's Contextual Retrieval"},{"excerpt":"A curated list of ten high-value articles on Contextual Retrieval, Context Engineering, and RAG evaluation, spanning Anthropic’s original publications, open-source implementation guides, and a review of 2025 trends.","permalink":"/en/posts/contextual-retrieval-rag-reading-list/","title":"Essential Reading for Contextual Retrieval and RAG"},{"excerpt":"A practical breakdown for AI engineers of what the M5’s changes over the M4—from CPU, cache, and memory bandwidth to Neural Accelerators—mean for local LLM and diffusion inference.","permalink":"/en/posts/apple-m5-vs-m4-practical-comparison-ai-engineers/","title":"Apple M5 vs. M4: A Practical Comparison for AI Engineers"},{"excerpt":"KV Cache is a key concept connecting Transformer theory with LLM engineering and deployment. Understanding it completes the path from how a model computes to how it runs.","permalink":"/en/posts/llm-api-kv-cache/","title":"What Is an LLM API KV Cache?"},{"excerpt":"Understand what LLM Chain-of-Thought (CoT) is and how prompt engineering can elicit Chain-of-Thought (CoT) from an LLM.","permalink":"/en/posts/llm-chain-of-thought-cot/","title":"The Complete Guide to LLM Chain-of-Thought (CoT)"},{"excerpt":"Prompt engineering? It may not be as simple as you think.","permalink":"/en/posts/prompt-engineering-from-concept-to-implementation/","title":"Prompt Engineering: From Principles to Practice"},{"excerpt":"Understand LLM prompt injection and several fundamental defensive measures.","permalink":"/en/posts/understanding-prompt-injection/","title":"Prompt Injection"},{"excerpt":"This article gave me—and may give you—a deeper understanding of the basic principles behind Transformers, replacing a black-box view of today’s mainstream LLMs. Cheers!","permalink":"/en/posts/understanding-transformer-intuition/","title":"Understanding the Mathematical Intuition Behind Transformers"}]