Blog
Development logs, learnings, thoughts, and coding adventures.
A practical architecture for governing AI agents through inventory, risk-tiered autonomy, policy enforcement, versioned evidence, change gates, and incident controls.
Vercel AI SDK 7에서 도구 승인, durable 실행, Codex·Claude Code 하네스, 타임아웃과 관측성을 운영 기준으로 구성하는 방법을 설명합니다.
생성된 MDX를 실제 Astro 콘텐츠 컬렉션 스키마에 맞춰 게시 전에 검증합니다.
Design a vendor-neutral operational agent with a domain model, constrained actions, policy checks, approval, idempotency, audit logs, and deployment-focused evaluation.
A practical comparison of Codex and Claude Code models, reasoning effort, fast modes, context options, permissions, and task-specific defaults.
A vendor-neutral architecture and 90-day roadmap for enterprise agent runtimes, identity, tools, business context, governance, evaluation, observability, and lifecycle management.
관심 주제와 문체, 조사·작성 규칙을 GitHub에 저장하고 ChatGPT·Codex가 매번 읽어 글을 검증·발행하는 Content OS 구조를 설명합니다.
A practical guide to Nous Research's Hermes Agent: models, memory, skills, messaging, cron, subagents, Docker isolation, and a safe rollout path.
A vendor-aware architecture analysis of Palantir Ontology, from objects and links to actions, functions, permissions, AIP Chatbots, evaluation, and platform trade-offs.
A practical architecture for persistent LLM-maintained knowledge, with source provenance, mutation rules, linting, retrieval boundaries, and evaluation.
Why operational AI agents need an explicit model of business objects, relationships, policies, permissions, and actions, and when that extra layer is worth building.
A practical rollout guide for LangChain OpenWiki, covering repository mutations, deterministic safeguards, CI permissions, review gates, and evaluation.
A practical guide to model routing, permission boundaries, verification loops, and cost controls for production agents built with GPT-5.6 and its 1.05M-token context window.
GPT-5.6 세 모델의 차이와 API 가격, 105만 토큰 컨텍스트, 추론 강도, 캐싱 비용을 비교하고 실제 서비스에서 모델을 고르는 기준을 정리합니다.
Trends and practical predictions for coding agents, model adaptation, and team operations.
How OpenClaw workflows and reusable skills can become an internal developer platform capability.
A reference architecture combining managed and open models for engineering organizations.
Practical guidance on fine-tuning incident response with a focus on production software teams.
Practical guidance on openllm incident response with a focus on production software teams.
Practical guidance on skills incident response with a focus on production software teams.
Practical guidance on openclaw incident response with a focus on production software teams.
Practical guidance on claude agent team incident response with a focus on production software teams.
Practical guidance on codex incident response with a focus on production software teams.
Practical guidance on fine-tuning release readiness with a focus on production software teams.
Practical guidance on openllm release readiness with a focus on production software teams.
Practical guidance on skills release readiness with a focus on production software teams.
Practical guidance on openclaw release readiness with a focus on production software teams.
Practical guidance on claude agent team release readiness with a focus on production software teams.
Practical guidance on codex release readiness with a focus on production software teams.
Practical guidance on fine-tuning code review workflow with a focus on production software teams.
Practical guidance on openllm code review workflow with a focus on production software teams.
Practical guidance on skills code review workflow with a focus on production software teams.
Practical guidance on openclaw code review workflow with a focus on production software teams.
Practical guidance on claude agent team code review workflow with a focus on production software teams.
Practical guidance on codex code review workflow with a focus on production software teams.
Practical guidance on fine-tuning ci/cd integration with a focus on production software teams.
Practical guidance on openllm ci/cd integration with a focus on production software teams.
Practical guidance on skills ci/cd integration with a focus on production software teams.
Practical guidance on openclaw ci/cd integration with a focus on production software teams.
Practical guidance on claude agent team ci/cd integration with a focus on production software teams.
Practical guidance on codex ci/cd integration with a focus on production software teams.
Practical guidance on fine-tuning governance and policy with a focus on production software teams.
Practical guidance on openllm governance and policy with a focus on production software teams.
Practical guidance on skills governance and policy with a focus on production software teams.
Practical guidance on openclaw governance and policy with a focus on production software teams.
CTR prediction, real-time bidding, RecSys architectures, and the ML behind ads
Feature stores, data pipelines, streaming, and batch processing for AI systems
Benchmarks, red teaming, guardrails, and responsible AI practices for production systems
Essential machine learning theory, neural network architectures, and training fundamentals every AI engineer must know
Knowledge graphs, Neo4j, RDF, and ontology engineering for AI applications
Training pipelines, model serving, monitoring, and the infrastructure behind production AI
From BM25 to RAG: understanding search systems that power modern AI applications
Patterns for building production LLM applications: prompts, chains, agents, and evaluation
Deep dive into vector databases, embeddings, and similarity search for production AI systems
Practical guidance on claude agent team governance and policy with a focus on production software teams.
Practical guidance on codex governance and policy with a focus on production software teams.
Practical guidance on fine-tuning onboarding playbook with a focus on production software teams.
Practical guidance on openllm onboarding playbook with a focus on production software teams.
Practical guidance on skills onboarding playbook with a focus on production software teams.
Practical guidance on openclaw onboarding playbook with a focus on production software teams.
Practical guidance on claude agent team onboarding playbook with a focus on production software teams.
A comprehensive analysis of Anthropic's Claude Code — the values behind it, how it works, why it matters, and how teams and organizations can adopt, deploy, and manage it effectively.
Deep dive into Google DeepMind's Gemma 4 — architecture, benchmarks, multimodal capabilities, and how it compares to Llama 4, Qwen 3.5, and other leading open LLMs in 2026.
Learn how to build a harness around Claude Code using CLAUDE.md, hooks, commands, skills, and permissions. A practical guide with real examples and diagrams.
Practical guidance on codex onboarding playbook with a focus on production software teams.
Practical guidance on fine-tuning documentation standards with a focus on production software teams.
Practical guidance on openllm documentation standards with a focus on production software teams.
Practical guidance on skills documentation standards with a focus on production software teams.
Practical guidance on openclaw documentation standards with a focus on production software teams.
Practical guidance on claude agent team documentation standards with a focus on production software teams.
Practical guidance on codex documentation standards with a focus on production software teams.
Practical guidance on fine-tuning performance optimization with a focus on production software teams.
Practical guidance on openllm performance optimization with a focus on production software teams.
Practical guidance on skills performance optimization with a focus on production software teams.
Practical guidance on openclaw performance optimization with a focus on production software teams.
Practical guidance on claude agent team performance optimization with a focus on production software teams.
Practical guidance on codex performance optimization with a focus on production software teams.
Practical guidance on fine-tuning cost control tactics with a focus on production software teams.
Practical guidance on openllm cost control tactics with a focus on production software teams.
Practical guidance on skills cost control tactics with a focus on production software teams.
Practical guidance on openclaw cost control tactics with a focus on production software teams.
Practical guidance on claude agent team cost control tactics with a focus on production software teams.
Practical guidance on codex cost control tactics with a focus on production software teams.
Practical guidance on fine-tuning security guardrails with a focus on production software teams.
Practical guidance on openllm security guardrails with a focus on production software teams.
Practical guidance on skills security guardrails with a focus on production software teams.
Practical guidance on openclaw security guardrails with a focus on production software teams.
Practical guidance on claude agent team security guardrails with a focus on production software teams.
Practical guidance on codex security guardrails with a focus on production software teams.
Practical guidance on fine-tuning observability setup with a focus on production software teams.
A detailed guide to the Humanizer skill, the writing patterns it catches, why AI prose often feels off, and how to use the skill without flattening your voice.
A practical guide to installing Superpowers for Codex, what native skill discovery changes, and why reusable skills beat stuffing every rule into one giant prompt.
A practical guide to the UI UX Pro Max skill, why it matters, how its design-system workflow works, and how to use it to get better interfaces from AI.
Practical guidance on openllm observability setup with a focus on production software teams.
A detailed guide to understanding, running, and extending karpathy/autoresearch with architecture diagrams, code walkthroughs, references, and implementation tips.
Practical guidance on skills observability setup with a focus on production software teams.
Practical guidance on openclaw observability setup with a focus on production software teams.
Practical guidance on claude agent team observability setup with a focus on production software teams.
Practical guidance on codex observability setup with a focus on production software teams.
Practical guidance on fine-tuning testing and validation with a focus on production software teams.
Practical guidance on openllm testing and validation with a focus on production software teams.
Practical guidance on skills testing and validation with a focus on production software teams.
Practical guidance on openclaw testing and validation with a focus on production software teams.
Practical guidance on claude agent team testing and validation with a focus on production software teams.
A practical deep-dive on how a next-generation multimodal NanoBanana model could expand real-world service opportunities, why those opportunities become technically feasible, and how to prompt for reliable outcomes.
A practical, engineering-focused comparison of Nano Banana and Nano Banana 2, including prompt design patterns, quality differences, and how to choose the right model for each task.
Practical guidance on codex testing and validation with a focus on production software teams.
A practical rewrite of an agent workflow prompt with sentence-level rationale, implementation notes, diagrams, and ready-to-use templates.
A practical compatibility and troubleshooting guide for serving modern open models with vLLM and OpenLLM, including NVIDIA GPU/driver baselines, CUDA alignment, and real-world failure patterns.
Practical guidance on fine-tuning task routing strategies with a focus on production software teams.
A deeply practical, field-tested guide to the tools, workflows, and habits that make Claude Code dramatically more useful in real projects.
A practical research guide to review-driven AI/ML in e-commerce, including KPI frameworks, offline evaluation, formulas, and implementation patterns.
A practical, evidence-backed field guide to the most impactful AI/ML use cases in commerce, including architectures, methods, equations, implementation patterns, and reported outcomes from major companies.
An end-to-end methodology for owning tokenizer and embedding capabilities in Korean food commerce: model strategy, data flywheel, evaluation metrics, platform delivery, and sustainability through feedback loops.
A practical, step-by-step roadmap for non-majors to go from zero to building and operating an AI agent-powered service.
An engineer-friendly guide to understanding how open LLM model size maps to GPU memory, hardware choices, and cost trade-offs for both training and inference.
An easy-to-understand guide to post-training with equations, code, charts, and workflow diagrams for real-world engineering teams.
Practical guidance on openllm task routing strategies with a focus on production software teams.
Practical guidance on skills task routing strategies with a focus on production software teams.
Practical guidance on openclaw task routing strategies with a focus on production software teams.
Practical guidance on claude agent team task routing strategies with a focus on production software teams.
Practical guidance on codex task routing strategies with a focus on production software teams.
Practical guidance on fine-tuning workflow design with a focus on production software teams.
Practical guidance on openllm workflow design with a focus on production software teams.
A practical deep-dive into GPU architecture, memory behavior, inference scheduling, and optimization techniques for serving Open LLMs effectively.
Practical guidance on skills workflow design with a focus on production software teams.
Practical guidance on openclaw workflow design with a focus on production software teams.
Practical guidance on claude agent team workflow design with a focus on production software teams.
Practical guidance on codex workflow design with a focus on production software teams.
Practical guidance on fine-tuning architecture patterns with a focus on production software teams.
Practical guidance on openllm architecture patterns with a focus on production software teams.
Practical guidance on skills architecture patterns with a focus on production software teams.
Practical guidance on openclaw architecture patterns with a focus on production software teams.
Practical guidance on claude agent team architecture patterns with a focus on production software teams.
Practical guidance on codex architecture patterns with a focus on production software teams.
Practical guidance on fine-tuning keyword map and planning system with a focus on production software teams.
Practical guidance on openllm keyword map and planning system with a focus on production software teams.
Practical guidance on skills keyword map and planning system with a focus on production software teams.
Practical guidance on openclaw keyword map and planning system with a focus on production software teams.
Practical guidance on claude agent team keyword map and planning system with a focus on production software teams.
Practical guidance on codex keyword map and planning system with a focus on production software teams.
A practical keyword map covering Codex, Claude agent teams, OpenClaw, skills, OpenLLM, fine-tuning, and adjacent topics developers should track.
Search wasn't showing results. Turned out frontend expected an array but got an object wrapper.
Switched from a modal dialog to an expandable search bar in the header. Less clicks, better UX.
The default 0.25 works, but understanding why matters for production apps.
Made a CLI tool to run parallel Claude Code sessions with auto permission skipping.
My tmux kept scrolling up while typing. Turns out the status bar was refreshing too often.
Added project detection so iOS hooks don't run in Python projects anymore.
Used Astro's dynamic routing to add multilingual share buttons to all game pages by editing just one file.
Created /commit and /pr skills for a seamless development cycle.
Learn from others' mistakes to use Claude Code more effectively.
Master the /compact command to manage context and save tokens in long sessions.
How to maintain consistent code style, patterns, and architecture with CLAUDE.md and hooks.
Everything you need to know to start using Claude Code effectively.
How to fix the ANTHROPIC_API_KEY environment variable not set error in Claude Code.
How to fix context window limit errors and manage long sessions in Claude Code.
How to handle rate limiting errors and optimize your Claude Code usage.
Diagnose and fix slow response times in Claude Code sessions.
How to handle and prevent tool execution timeout errors in Claude Code.
Why starting fresh sessions often produces better results than continuing long ones.
How to use Claude Code for commits, branches, PRs, and code review.
Set up Claude Code in CI/CD pipelines for automated code review, fixes, and PR management.
Run Claude Code without interaction for automation, scripts, and pipelines.
Complete installation guide for Claude Code across all major operating systems.
Essential keyboard shortcuts to speed up your Claude Code workflow.
Set up hooks to auto-format, lint, test, and validate code after Claude makes changes.
Understanding the boundaries of Claude Code to set realistic expectations.
How to set up MCP servers to connect Claude Code with databases, APIs, and other tools.
How to choose between Haiku, Sonnet, and Opus for different tasks.
How to use subagents and multiple sessions to work on several things simultaneously.
How Claude Code permissions work and how to configure them for your workflow.
Use bash scripts to reduce Claude Code token usage and automate repetitive tasks.
Build project-specific commands to speed up repetitive workflows.
How to use subagents for faster codebase exploration and parallel task execution.
Why skills reduce token usage and how to leverage on-demand loading.
Automate test creation, execution, and fixing with Claude Code hooks and scripts.
How Claude Code token usage works and how to estimate your costs.
An honest comparison of Claude Code and Cursor for real-world development workflows.
Comparing Claude Code and GitHub Copilot for different development needs.
Create effective project context files that make Claude Code understand your codebase.
Google wasn't indexing my sitemap properly. Turned out I had redirect URLs polluting it.
The background removal tool was breaking in production. Turns out Vite was the culprit.
Went from 58% to targeting 80% mAP by switching to YOLOv8s-P2 and tuning augmentations.
Got tired of Claude asking permission for every command. Here's how I fixed it.
Switched my blog deploy script from direct push to PR-based workflow.
Higher resolution should mean better detection, right? Not always.
Chat stopped connecting after adding language prefixes to URLs. Turned out to be a Vite cache issue.
Why Google couldn't fetch my sitemap and how I fixed it.
Made language switching actually change the URL, plus split sitemaps for better SEO.
Cut my skill token usage by 80% by switching from prompt-heavy to script-based approach.
Set up Git worktree and custom skills to run parallel Claude sessions on the same project.
Switched my Claude Code skills from prompt-heavy to script-based. Huge token savings.
Built a tool that turns my coding sessions into blog posts automatically. No more manual writing.
Updated my git-sync command to create branches and PRs instead of pushing to main.
개발자, 디자이너, 마케터를 위한 무료 온라인 도구 모음. QR 코드 생성, 비밀번호 생성, JSON 포매팅, 이미지 변환 등 다양한 도구를 브라우저에서 바로 사용하세요.
Next.js에서 Astro로 전환하며 배운 것들
Claude와 함께하는 새로운 개발 방식, Vibe Coding을 시작합니다.
Jekyll 블로그 시스템과 정적 사이트 생성기에 대한 소개입니다.
GitHub이 왜 개발자들에게 필수적인 도구인지, 그리고 어떻게 활용할 수 있는지 알아봅니다.
개발자와 창작자들을 위한 영감을 주는 명언들을 모았습니다.
Abbott과 Costello의 전설적인 야구 코미디 'Who's on First'에 대한 이야기
블로그 글을 작성할 때 사용하는 표준 형식과 마크다운 문법에 대해 알아봅니다.
202 posts