Explore Claude Code, MCP (Model Context Protocol), workflow automation, and AI-powered development. Practical guides and deep dives into LLM integration for developers.https://jangwook.net/enhttps://jangwook.net/en/blog/en/claude-mythos-preview-glasswing-ai-cybersecurity/https://jangwook.net/en/blog/en/claude-mythos-preview-glasswing-ai-cybersecurity/Anthropic decided not to publicly release Claude Mythos Preview, which scored 93.9% on SWE-bench. The model found a 27-year-old OpenBSD vulnerability and is only available to 12 companies through Project Glasswing. Is this genuine responsibility, or clever marketing?Thu, 09 Apr 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/prismml-bonsai-1bit-llm-edge-ai/https://jangwook.net/en/blog/en/prismml-bonsai-1bit-llm-edge-ai/PrismML Bonsai, built by a Caltech-founded team, is a 1-bit LLM that represents weights using only {-1, +1}. An 8B model fits in 1.15GB and reportedly runs 8x faster than full precision. I looked into whether any of this holds up.Wed, 08 Apr 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/gemma-4-local-agent-edge-ai/https://jangwook.net/en/blog/en/gemma-4-local-agent-edge-ai/I installed Google's Gemma 4 (Apache 2.0) via Ollama and tested Korean language, structured output, and function calling firsthand. Can a 9.6GB local model actually become a building block for agent pipelines?Mon, 06 Apr 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/claude-code-source-leak-analysis/https://jangwook.net/en/blog/en/claude-code-source-leak-analysis/Anthropic's npm packaging error exposed Claude Code's full source. Agent loops, memory systems, cost optimization — what developers can learn from 510K lines.Sun, 05 Apr 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/anthropic-emotion-concepts-llm-alignment/https://jangwook.net/en/blog/en/anthropic-emotion-concepts-llm-alignment/Anthropic's interpretability team discovered 171 emotion-like representations inside Claude and proved they causally affect model output. Practical implications for prompt engineering and AI safety.Sat, 04 Apr 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/stripe-minions-autonomous-coding-agents-1300-prs/https://jangwook.net/en/blog/en/stripe-minions-autonomous-coding-agents-1300-prs/How Stripe produces over 1,300 PRs weekly with autonomous coding agents called Minions. An analysis of the Blueprint architecture, sandboxed VMs, and 3-tier feedback loop behind the system.Fri, 03 Apr 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/effloow-side-project-ai-company/https://jangwook.net/en/blog/en/effloow-side-project-ai-company/I built a content business powered by 14 AI agents on top of Paperclip. Here is how the site runs itself using Laravel, Markdown, and Git, plus lessons learned from Day 1 of operating this experiment.Thu, 02 Apr 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/mcp-gateway-agent-traffic-control/https://jangwook.net/en/blog/en/mcp-gateway-agent-traffic-control/MCP has crossed 97 million monthly downloads and become the de facto standard, but there is no control layer governing which tools agents call and how often. The MCP Gateway pattern addresses this gap.Thu, 02 Apr 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/paperclip-zero-human-company-agent-orchestration/https://jangwook.net/en/blog/en/paperclip-zero-human-company-agent-orchestration/Using one AI agent well is easy enough. But what about running multiple agents like a company? I installed Paperclip, created a company, hired agents, and here's my honest review.Thu, 02 Apr 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/sora-shutdown-ai-video-market-reshaping-veo4/https://jangwook.net/en/blog/en/sora-shutdown-ai-video-market-reshaping-veo4/OpenAI announced the shutdown of the Sora app. With $1M daily losses and sub-500K users, we analyze the fallout alongside Google Veo 4's imminent launch and the rise of Runway and Kling, from a practical workflow perspective.Wed, 01 Apr 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/litellm-supply-chain-attack-ai-dependency-security/https://jangwook.net/en/blog/en/litellm-supply-chain-attack-ai-dependency-security/Analyzing the LiteLLM supply chain attack on PyPI and practical methods to strengthen dependency management and supply chain security in AI tool chains.Tue, 31 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/ai-coding-secrets-sprawl-mcp-config-security/https://jangwook.net/en/blog/en/ai-coding-secrets-sprawl-mcp-config-security/According to the GitGuardian 2026 report, repositories using AI coding tools leak secrets at twice the GitHub average. Over 24,000 credentials were exposed in MCP config files alone. Here is a practical guide to auditing your setup and fighting back.Mon, 30 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/mistral-voxtral-tts-open-weight-speech/https://jangwook.net/en/blog/en/mistral-voxtral-tts-open-weight-speech/Analyzing Mistral's 4B parameter open-weight TTS model Voxtral. It beat ElevenLabs in human evaluations, but the lack of Japanese support is a dealbreaker for Asia-focused projects.Sun, 29 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/gemini-31-flash-live-realtime-voice-agent/https://jangwook.net/en/blog/en/gemini-31-flash-live-realtime-voice-agent/Analyzing Google's Gemini 3.1 Flash Live for building real-time voice and vision agents. Covers API structure, tool calling, 90+ language support, and honest limitations from a developer's perspective.Sat, 28 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/github-copilot-data-policy-opt-out-guide/https://jangwook.net/en/blog/en/github-copilot-data-policy-opt-out-guide/GitHub announced on March 25 that Copilot Free/Pro/Pro+ user interaction data will be used for AI model training by default. Here is how to opt out and what it actually means.Fri, 27 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/google-turboquant-kv-cache-3bit-compression/https://jangwook.net/en/blog/en/google-turboquant-kv-cache-3bit-compression/A deep dive into Google TurboQuant's PolarQuant and QJL techniques — 6x KV cache memory reduction and 8x attention speedup, and what that actually means in practice.Thu, 26 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/anthropic-vibe-physics-ai-research-assistant/https://jangwook.net/en/blog/en/anthropic-vibe-physics-ai-research-assistant/Analyzing Anthropic's Science blog debut where Harvard physicist Matthew Schwartz supervised Claude as an 'AI grad student.' 110 drafts, 36M tokens, and a paper completed in two weeks.Wed, 25 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/dapr-agents-v1-cncf-production-ai-framework/https://jangwook.net/en/blog/en/dapr-agents-v1-cncf-production-ai-framework/Analyzing Dapr Agents v1.0 announced at KubeCon Europe 2026 — its durable workflows, automatic recovery, and scale-to-zero — and how it differs from existing agent frameworks.Tue, 24 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/nvidia-nemoclaw-openclaw-enterprise-agent-platform/https://jangwook.net/en/blog/en/nvidia-nemoclaw-openclaw-enterprise-agent-platform/Announced at GTC 2026, NVIDIA NemoClaw is an open-source reference stack for running OpenClaw safely in enterprise environments. A look at its realistic limitations and possibilities in alpha stage.Tue, 24 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/claude-code-channels-telegram-bridge/https://jangwook.net/en/blog/en/claude-code-channels-telegram-bridge/Claude Code now has a Channels feature. Send a message on Telegram, and Claude running in your local terminal executes code and replies. It borrows the channel concept from OpenClaw but takes a completely different approach to the security model — and that's what makes it interesting.Sat, 21 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/deeptune-ai-agent-training-gyms-rl-professional-workflows/https://jangwook.net/en/blog/en/deeptune-ai-agent-training-gyms-rl-professional-workflows/Deeptune raised a $43M Series A led by a16z. Their approach — training AI agents through RL environments that simulate professional workflows — signals a fundamental shift for engineering organizations.Sat, 21 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/ibm-confluent-realtime-data-ai-agents/https://jangwook.net/en/blog/en/ibm-confluent-realtime-data-ai-agents/IBM acquired Confluent for $11 billion, elevating real-time data streaming as core infrastructure for AI agents. A CTO-level analysis of what this deal means and how engineering orgs should respond.Fri, 20 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/gemini-embedding-2-multimodal-rag-pipeline/https://jangwook.net/en/blog/en/gemini-embedding-2-multimodal-rag-pipeline/A deep dive into GoogleThu, 19 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/alphaevolve-ramsey-ai-research-partner/https://jangwook.net/en/blog/en/alphaevolve-ramsey-ai-research-partner/Google DeepMind's AlphaEvolve broke five Ramsey number records held up to 20 years. What this means for AI as a research partner and engineering leadership.Wed, 18 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/hindsight-mcp-agent-memory-learning/https://jangwook.net/en/blog/en/hindsight-mcp-agent-memory-learning/Analyzing the architecture, core capabilities, and production deployment strategies of the Hindsight MCP memory system that solves the memory problem for AI agents.Tue, 17 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/morgan-stanley-ai-leap-2026-cto-strategy/https://jangwook.net/en/blog/en/morgan-stanley-ai-leap-2026-cto-strategy/Morgan Stanley predicts a non-linear AI capability leap in early 2026. Here are 5 strategies engineering leaders should execute right now to stay ahead.Mon, 16 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/perplexity-computer-always-on-ai-agent/https://jangwook.net/en/blog/en/perplexity-computer-always-on-ai-agent/Analyzing Perplexity Personal Computer and Enterprise. A 24/7 always-on AI agent completed 3.25 years of work in 4 weeks — with EM adoption strategies.Sun, 15 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/ai-agent-identity-dark-matter-enterprise/https://jangwook.net/en/blog/en/ai-agent-identity-dark-matter-enterprise/70% of enterprises already run AI agents in production, yet 80% can't track their real-time behavior. Explore the Identity Dark Matter concept, the governance gap, and a 5-step action plan for engineering managers and CTOs.Sat, 14 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/glm-5-mit-opensource-frontier-enterprise/https://jangwook.net/en/blog/en/glm-5-mit-opensource-frontier-enterprise/Zhipu AI released GLM-5 with 744B MoE trained on Huawei Ascend without NVIDIA. A cost-effective MIT-licensed alternative for enterprise deployments.Sat, 14 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/microsoft-agent-framework-ga-production-strategy/https://jangwook.net/en/blog/en/microsoft-agent-framework-ga-production-strategy/Microsoft Agent Framework, unifying AutoGen and Semantic Kernel, is approaching Q1 2026 GA. From an EM/CTO perspective, this post covers key features, migration strategy, and a production adoption roadmap.Sat, 14 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/openai-promptfoo-ai-agent-devsecops/https://jangwook.net/en/blog/en/openai-promptfoo-ai-agent-devsecops/OpenAI has acquired Promptfoo, the AI security testing platform used by 25% of the Fortune 500. As it integrates into the Frontier platform, a new standard for AI agent DevSecOps is taking shape.Sat, 14 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/agent-washing-detection-em-checklist/https://jangwook.net/en/blog/en/agent-washing-detection-em-checklist/Only ~130 of thousands of AI agent vendors build genuinely agentic systems. This practical 7-point checklist helps Engineering Managers distinguish real agentic AI from marketing buzzwords.Fri, 13 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/anthropic-institute-partner-network/https://jangwook.net/en/blog/en/anthropic-institute-partner-network/Anthropic Institute launch, $100M Claude Partner Network, and Claude Certified Architect. A CTO-level analysis of AI vendor ecosystem maturity in 2026.Fri, 13 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/gpt54-computer-use-1m-context-engineering-impact/https://jangwook.net/en/blog/en/gpt54-computer-use-1m-context-engineering-impact/OpenAI released GPT-5.4 on March 5, 2026. Computer use surpassing humans (75% vs 72.4% on OSWorld), 1M token context window, 47% token savings via tool search — here's what engineering managers need to know.Fri, 13 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/production-grade-ai-agent-design-principles/https://jangwook.net/en/blog/en/production-grade-ai-agent-design-principles/Solve the core challenges of deploying AI agents to production in 2026 with 9 battle-tested design principles from arXiv research, presented from an Engineering Manager perspective.Fri, 13 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/ai-agent-observability-production-guide/https://jangwook.net/en/blog/en/ai-agent-observability-production-guide/A practical guide for Engineering Managers on monitoring multi-agent LLM systems in production. Covers distributed tracing, metrics, logging, OpenTelemetry, and a comparison of Langfuse, LangSmith, and Braintrust.Thu, 12 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/mcp-apps-interactive-ui-agent-ux/https://jangwook.net/en/blog/en/mcp-apps-interactive-ui-agent-ux/How MCP Apps transform AI agent UX—from sandboxed iframe and JSON-RPC bidirectional communication architecture to real implementation code. A complete guide from an Engineering Manager perspective.Thu, 12 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/mcp2cli-token-cost-optimization/https://jangwook.net/en/blog/en/mcp2cli-token-cost-optimization/Connecting MCP servers injects all tool schemas into context every turn—362,000 tokens wasted for 120 tools over 25 turns. mcp2cli solves this with CLI-based on-demand discovery, cutting costs by 96–99%. Here's how it works and when to use it.Thu, 12 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/openai-open-responses-agentic-standard/https://jangwook.net/en/blog/en/openai-open-responses-agentic-standard/OpenAI Open Responses spec standardizes agentic AI workflows. We analyze its core concepts, ecosystem support, and adoption strategies from an EM/CTO perspective.Thu, 12 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/claude-code-review-multi-agent-pr/https://jangwook.net/en/blog/en/claude-code-review-multi-agent-pr/Complete breakdown of Anthropic's new Code Review feature for Claude Code: parallel multi-agent architecture, $15–25 per-PR cost structure, and everything Engineering Managers need to know before adoptingWed, 11 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/context-engineering-production-ai-agents/https://jangwook.net/en/blog/en/context-engineering-production-ai-agents/Why context engineering has become the defining skill for production AI agents in 2026 — 4 critical failure patterns and 5 core techniques, from an Engineering Manager perspective.Wed, 11 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/karpathy-autoresearch-overnight-ml-experiments/https://jangwook.net/en/blog/en/karpathy-autoresearch-overnight-ml-experiments/Andrej Karpathy's autoresearch is a 630-line open-source tool that lets AI agents autonomously iterate ML experiments overnight. We analyze R&D team adoption strategies from an EM perspective.Wed, 11 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/llm-deanonymization-privacy-risk-defense/https://jangwook.net/en/blog/en/llm-deanonymization-privacy-risk-defense/Analyzing large-scale online deanonymization research using LLMs and presenting organizational security defense strategies for engineering leaders.Wed, 11 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/ai-reliability-engineer-centaur-pod-2026/https://jangwook.net/en/blog/en/ai-reliability-engineer-centaur-pod-2026/Junior developer roles are evolving into AI Reliability Engineers (AREs). From Centaur Pod team structures to Code Audit hiring and Defect Capture Rate metrics — the AI-native team design strategy every Engineering Manager needs to act on nowTue, 10 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/claude-firefox-22-cves-ai-security-audit/https://jangwook.net/en/blog/en/claude-firefox-22-cves-ai-security-audit/Anthropic Claude Opus 4.6 discovered 22 CVEs in Firefox in just two weeks. We break down how AI-driven security audits work and what engineering leaders should do next.Tue, 10 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/google-agent-scaling-science-multiagent-limits/https://jangwook.net/en/blog/en/google-agent-scaling-science-multiagent-limits/Google Research's 180-configuration quantitative experiment exposes the multi-agent paradox: 39–70% performance degradation on sequential tasks, 17.2× error amplification, and what 87% predictive accuracy means for your architecture decisions.Tue, 10 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/roguepilot-copilot-prompt-injection-security/https://jangwook.net/en/blog/en/roguepilot-copilot-prompt-injection-security/Analysis of the RoguePilot vulnerability found in GitHub Codespaces, passive prompt injection risks in AI coding tools, and security guidelines for engineering teams.Tue, 10 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/a2a-mcp-hybrid-architecture-production-guide/https://jangwook.net/en/blog/en/a2a-mcp-hybrid-architecture-production-guide/Google A2A and Anthropic MCP are complementary, not competing. From an EM/CTO perspective, understand the role differences between the two protocols and learn strategies for safely operating multi-agent systems in production.Mon, 09 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/cursor-agent-trace-ai-code-attribution/https://jangwook.net/en/blog/en/cursor-agent-trace-ai-code-attribution/Analyze Cursor Agent Trace 0.1.0 specification and discover why AI code attribution tracking is critical for engineering leaders and CTOs beyond git blame.Mon, 09 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/heterogeneous-llm-agent-fleet-cost-optimization/https://jangwook.net/en/blog/en/heterogeneous-llm-agent-fleet-cost-optimization/The Plan-Execute pattern: large models plan, small models execute. A practical guide for EMs and CTOs on heterogeneous LLM architecture strategies to dramatically reduce agent fleet costs without sacrificing quality.Mon, 09 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/tool-r0-zero-data-agent-training/https://jangwook.net/en/blog/en/tool-r0-zero-data-agent-training/The arXiv paper Tool-R0 achieves 92.5% improvement in LLM tool-calling via Self-Play RL alone, with no training data. We analyze its Generator-Solver co-evolution and practical implications.Mon, 09 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/bayesian-teaching-llm-probabilistic-reasoning/https://jangwook.net/en/blog/en/bayesian-teaching-llm-probabilistic-reasoning/Google's Bayesian Teaching research, published in Nature Communications, introduces a training methodology that enables LLMs to probabilistically update their beliefs when receiving new information. This post analyzes its implications for AI agents and enterprise systems from an engineering leadership perspective.Sun, 08 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/deloitte-agentic-ai-operations-2026/https://jangwook.net/en/blog/en/deloitte-agentic-ai-operations-2026/Only 11% of enterprises run Agentic AI in production. The barrier isn't technology—it's operational model. Here's the Delegate-Review-Own framework for EM/VPoE.Sun, 08 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/mcp-security-crisis-30-cves-enterprise-hardening/https://jangwook.net/en/blog/en/mcp-security-crisis-30-cves-enterprise-hardening/The MCP attack surface is expanding fast. Here's an analysis of 30 CVEs, a three-layer attack model, and an enterprise security hardening checklist for engineering leaders.Sun, 08 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/adl-agent-definition-language-governance/https://jangwook.net/en/blog/en/adl-agent-definition-language-governance/Explore ADL for declarative agent definition and standardization, with governance strategies for engineering leaders and CTOs.Sat, 07 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/cognitive-debt-agentic-coding-2026/https://jangwook.net/en/blog/en/cognitive-debt-agentic-coding-2026/Anthropic's 2026 Agentic Coding Trends Report heralds a productivity revolution — but a parallel research thread warns of "Cognitive Debt." As AI writes more code, teams quietly lose their shared understanding of their own systems. Here's what Engineering Managers must do now.Sat, 07 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/elite-ai-engineering-culture-2026/https://jangwook.net/en/blog/en/elite-ai-engineering-culture-2026/Analysis of the elite AI engineering culture that topped Hacker News. Understanding the 5.7x gap between $3.48M vs $610K revenue per employee, and the Taste × Discipline × Leverage formula every EM should practiceSat, 07 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/olmo-hybrid-transformer-rnn-data-efficiency/https://jangwook.net/en/blog/en/olmo-hybrid-transformer-rnn-data-efficiency/AI2's Olmo Hybrid combines Transformer and DeltaNet layers in a 3:1 ratio, achieving the same accuracy with 49% fewer tokens. We analyze the architectural innovation and its practical implications.Sat, 07 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/ai-convenience-loop-reshaping-language-choices/https://jangwook.net/en/blog/en/ai-convenience-loop-reshaping-language-choices/GitHub Octoverse data reveals the convenience loop effect of AI coding tools. Explore why TypeScript surged 66% and what it means for tech stack strategy from an EM/CTO perspective.Fri, 06 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/llama4-maverick-scout-enterprise-strategy/https://jangwook.net/en/blog/en/llama4-maverick-scout-enterprise-strategy/A technical and strategic analysis of Meta Llama 4 Maverick (400B MoE) and Scout (10M context window): architecture, benchmarks, cost structure, and what engineering leaders need to know to update their open-source AI strategy.Fri, 06 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/nist-ai-agent-security-standards/https://jangwook.net/en/blog/en/nist-ai-agent-security-standards/Understanding NIST AI Agent Standards Initiative and an actionable security checklist for Engineering Managers to strengthen AI agent security within their teams.Fri, 06 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/agentic-workflow-meta-tools-optimization/https://jangwook.net/en/blog/en/agentic-workflow-meta-tools-optimization/Analyze the Agent Workflow Optimization (AWO) framework from arXiv research. Compile repetitive tool call patterns into meta-tools to reduce LLM calls by 12% and improve success rates by 4%.Thu, 05 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/claude-cowork-enterprise-productivity-platform/https://jangwook.net/en/blog/en/claude-cowork-enterprise-productivity-platform/Analysis of Anthropic Claude Cowork enterprise features. Plugin Marketplace, MCP connectors, Excel and PowerPoint integration — a CTO strategy guide for org-wide AI adoption.Thu, 05 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/deep-thinking-ratio-llm-cost-optimization/https://jangwook.net/en/blog/en/deep-thinking-ratio-llm-cost-optimization/Google & UVA research overturns the "longer = better" assumption for LLM reasoning. The Deep-Thinking Ratio (DTR) can cut inference costs in half while improving accuracy. Essential insights for Engineering Managers and VPoEs managing AI infrastructure.Thu, 05 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/mcp-open-standard-linux-foundation-engineering-guide/https://jangwook.net/en/blog/en/mcp-open-standard-linux-foundation-engineering-guide/Anthropic donated MCP to the Linux Foundation, with OpenAI, Google, and Microsoft on board. With 76% of companies exploring adoption, here is a practical strategy guide for EMs and VPoEs.Wed, 04 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/mit-encompass-agent-search-reliability/https://jangwook.net/en/blog/en/mit-encompass-agent-search-reliability/Discover how MIT CSAIL's EnCompass framework applies search strategies to AI agent execution paths, dramatically improving reliability and accuracy in production.Wed, 04 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/jira-ai-agents-mcp-engineering-management/https://jangwook.net/en/blog/en/jira-ai-agents-mcp-engineering-management/Atlassian has officially launched AI agents in Jira and adopted MCP platform-wide. Here's what engineering managers need to prepare for organizational change.Tue, 03 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/llm-coding-harness-optimization/https://jangwook.net/en/blog/en/llm-coding-harness-optimization/Harness optimization (edit formats, tool interfaces) yields 5-14% gains over model selection in LLM coding tools. A practical guide to harness engineering strategies.Tue, 03 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/ai-distillation-attacks-enterprise-defense/https://jangwook.net/en/blog/en/ai-distillation-attacks-enterprise-defense/Analyzing Anthropic's detection of large-scale AI model distillation attacks and presenting practical strategies for enterprises to protect intellectual property when using AI APIs.Mon, 02 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/anthropic-pentagon-ai-governance-cto-lessons/https://jangwook.net/en/blog/en/anthropic-pentagon-ai-governance-cto-lessons/Analyzing Anthropic's refusal of Pentagon military AI demands and providing practical guidance for CTOs/VPoEs on establishing AI vendor dependency risk and governance strategies.Mon, 02 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/github-agentic-workflows-cicd-ai/https://jangwook.net/en/blog/en/github-agentic-workflows-cicd-ai/Analyzing GitHub Agentic Workflows technical preview. Define automation in Markdown, and AI agents perform issue triage, code reviews, and test generation in Continuous AI paradigm.Sun, 01 Mar 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/mit-tlt-adaptive-drafter-reasoning-training/https://jangwook.net/en/blog/en/mit-tlt-adaptive-drafter-reasoning-training/MIT researchers introduced TLT, accelerating reasoning LLM RL training by 70-210% through adaptive drafters and speculative decoding. Reduces training costs without additional hardware.Sat, 28 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/claude-code-remote-control-guide/https://jangwook.net/en/blog/en/claude-code-remote-control-guide/A complete guide to setting up and using Claude Code Remote Control. Learn how to monitor and control desktop tasks from your phone with practical workflow examples.Thu, 26 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/openclaw-openai-codex-migration/https://jangwook.net/en/blog/en/openclaw-openai-codex-migration/A step-by-step guide for OpenClaw users migrating to OpenAI Codex after the Claude and Gemini ToS changes. Covers backup, model switching, and per-agent configuration.Sun, 22 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/dont-trust-the-salt-multilingual-llm-safety/https://jangwook.net/en/blog/en/dont-trust-the-salt-multilingual-llm-safety/An analysis of how LLM guardrails fail in multilingual environments. We examine the structural issues causing safety verification failures in non-English languages and practical countermeasures.Sat, 21 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/ggml-llamacpp-huggingface/https://jangwook.net/en/blog/en/ggml-llamacpp-huggingface/The ggml.ai team joins Hugging Face to secure the long-term sustainability of llama.cpp. We analyze the structural changes and technical implications for the local AI inference ecosystem.Sat, 21 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/asic-llm-inference-16k-tps/https://jangwook.net/en/blog/en/asic-llm-inference-16k-tps/Startup Taalas achieves 16,000 tok/s on Llama 3.1 8B using custom ASIC chips without GPUs. We analyze the shift away from GPU dependency and the inference cost revolution.Fri, 20 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/consistency-diffusion-lm/https://jangwook.net/en/blog/en/consistency-diffusion-lm/Together AI introduces CDLM, boosting diffusion language model inference up to 14x faster while maintaining quality. Block-wise parallel generation with KV caching is the key breakthrough.Fri, 20 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/gemini-31-pro-release/https://jangwook.net/en/blog/en/gemini-31-pro-release/Google releases Gemini 3.1 Pro with 77.1% on ARC-AGI-2, doubling reasoning performance. We analyze benchmarks, compare with Claude, and explore multimodal evolution.Fri, 20 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/llama-cpp-iq-quantization-merge/https://jangwook.net/en/blog/en/llama-cpp-iq-quantization-merge/IQ-series quantization methods developed in ik_llama.cpp are being merged into llama.cpp mainline. Learn about IQ2_K through IQ4_KS precision improvements and local LLM inference optimization.Fri, 20 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/qwen3-coder-next-llama-cpp-graph-optimization/https://jangwook.net/en/blog/en/qwen3-coder-next-llama-cpp-graph-optimization/ggerganov restructures the llama.cpp compute graph to achieve up to 38% inference speedup for the Qwen3 Coder Next 80B model. Detailed benchmark analysis and technical breakdown.Fri, 20 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/ddr5-rdimm-vs-rtx3090-local-llm/https://jangwook.net/en/blog/en/ddr5-rdimm-vs-rtx3090-local-llm/DDR5 RDIMM pricing has dropped below RTX 3090 VRAM per GB, marking a turning point in local LLM hardware decisions. We analyze CPU vs GPU inference cost structures.Thu, 19 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/devstral-qwen3-coder-small-models/https://jangwook.net/en/blog/en/devstral-qwen3-coder-small-models/Mistral Devstral Small 2 24B and Qwen3 Coder 30B arrive simultaneously. A comparative analysis of small coding models that run on Raspberry Pi and the future of local AI coding.Thu, 19 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/kitten-tts-v08-tiny-sota/https://jangwook.net/en/blog/en/kitten-tts-v08-tiny-sota/A deep dive into Kitten TTS V0.8 — a 14M parameter, sub-25MB text-to-speech model matching cloud TTS quality. Analysis of edge deployment potential and the local voice AI trend.Thu, 19 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/local-ai-radio-smart-home/https://jangwook.net/en/blog/en/local-ai-radio-smart-home/Analyzing a real-world project that achieves voice control and smart home automation without internet using just a Mac mini and a $30 LoRa radio. A deep dive into local AI × IoT implementation and costs.Thu, 19 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/barracuda-cuda-amd-compiler/https://jangwook.net/en/blog/en/barracuda-cuda-amd-compiler/Explore BarraCUDA, an open-source compiler that compiles CUDA .cu files directly to AMD GPU machine code without LLVM, challenging NVIDIA's GPU computing monopoly.Wed, 18 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/claude-sonnet-46-release/https://jangwook.net/en/blog/en/claude-sonnet-46-release/A comprehensive analysis of Claude Sonnet 4.6's updates, model versioning strategy, performance benchmarks, and cost efficiency.Wed, 18 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/deepseek-v4-release/https://jangwook.net/en/blog/en/deepseek-v4-release/As DeepSeek V4's release draws near, Chinese AI companies continue their model rush with Qwen3.5 and GLM-5. We analyze performance comparisons and the open model competition landscape.Wed, 18 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/kanitts2-voice-cloning/https://jangwook.net/en/blog/en/kanitts2-voice-cloning/KaniTTS2, a lightweight 400M-parameter TTS model, has been open-sourced with voice cloning capabilities requiring only 3GB VRAM. With full pretraining code released, it marks a milestone in voice AI democratization.Wed, 18 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/matmulfree-cpu-llm-training/https://jangwook.net/en/blog/en/matmulfree-cpu-llm-training/Explore how MatMul-Free architecture with ternary weights enables language model training on CPU alone, and its implications for edge AI and low-cost learning.Wed, 18 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/agents-md-effectiveness/https://jangwook.net/en/blog/en/agents-md-effectiveness/The first empirical study evaluating AGENTS.md effectiveness has been published. We analyze its impact on coding agent success rates and inference costs.Tue, 17 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/ai-self-generated-skills-myth/https://jangwook.net/en/blog/en/ai-self-generated-skills-myth/SkillsBench proves AI agents cannot author useful skills for themselves. Across 7,308 trajectories, self-generated skills showed zero benefit while human-curated skills improved performance by 16.2pp.Tue, 17 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/functiongemma-270m-tool-calling/https://jangwook.net/en/blog/en/functiongemma-270m-tool-calling/Analysis of how fine-tuning FunctionGemma 270M improved multi-turn tool calling accuracy from 10-39% to 90-97%, matching a 120B teacher model. More evidence that scaling isn't everything.Tue, 17 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/openrouter-oss-dominance/https://jangwook.net/en/blog/en/openrouter-oss-dominance/Four of the top five most-used models on OpenRouter are open source (Qwen3-Coder, DeepSeek R2, MiniMax M2.5, etc.). We analyze the end of proprietary model dominance and why open-source models are winning in real-world usage.Tue, 17 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/qwen35-vending-bench-bankruptcy/https://jangwook.net/en/blog/en/qwen35-vending-bench-bankruptcy/Qwen 3.5, a top performer on standard benchmarks, goes bankrupt on Vending-Bench 2's vending machine simulation. Exploring the blind spots of benchmark-driven AI evaluation.Tue, 17 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/claude-code-local-model-inefficiency/https://jangwook.net/en/blog/en/claude-code-local-model-inefficiency/Analyzing the full prompt reprocessing issue when running Claude Code with local LLMs. Learn about KV cache invalidation mechanics and developer tool design lessons.Mon, 16 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/heretic-12-vram-reduction/https://jangwook.net/en/blog/en/heretic-12-vram-reduction/Heretic 1.2 is here with 4-bit quantization cutting VRAM usage by up to 70% and MPOA delivering higher-quality abliteration. A deep dive into the latest cost-saving techniques for local LLM operations.Mon, 16 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/karpathy-ai-training-cost-deflation/https://jangwook.net/en/blog/en/karpathy-ai-training-cost-deflation/Karpathy's analysis reveals AI model training costs fall 40% annually. We examine the structural factors — hardware evolution, algorithm efficiency, and data pipeline optimization — and their industry impact.Mon, 16 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/qwen3-coder-8gb-vram/https://jangwook.net/en/blog/en/qwen3-coder-8gb-vram/Analyzing quantization and lazy loading techniques to run an 80B parameter coding AI model on consumer 8GB VRAM GPUs. Exploring the practicality and limitations of local LLM coding.Mon, 16 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/sqlite-ai-swarm-build/https://jangwook.net/en/blog/en/sqlite-ai-swarm-build/Six AI agents (Claude, Codex, Gemini) built a 19,000-line Rust SQLite clone in parallel. Analyzing the real costs of multi-agent coordination and task division.Mon, 16 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/gpt-oss-120b-uncensored/https://jangwook.net/en/blog/en/gpt-oss-120b-uncensored/Analyzing the technical features of GPT-OSS 120B Uncensored and the safety guardrail debate sparked by uncensored open-source LLMs from both technical and ethical perspectives.Sun, 15 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/ibm-gen-z-hiring-ai-limits/https://jangwook.net/en/blog/en/ibm-gen-z-hiring-ai-limits/IBM is tripling Gen Z entry-level hiring after realizing AI's limits. An EM's analysis of AI replacement reality, enterprise workforce planning, and organizational design shifts.Sun, 15 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/minimax-m25-open-weight-vs-proprietary/https://jangwook.net/en/blog/en/minimax-m25-open-weight-vs-proprietary/MiniMax M2.5 achieves 80.2% on SWE-Bench Verified, surpassing Claude Opus 4.6. We analyze how the performance gap between open-weight and proprietary models is rapidly closing, with comprehensive benchmark data.Sun, 15 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/nvidia-dgx-spark-cuda-compatibility/https://jangwook.net/en/blog/en/nvidia-dgx-spark-cuda-compatibility/A technical analysis of NVIDIA DGX Spark's sm121 architecture CUDA software compatibility problems and suspected handheld gaming chip repurposing.Sun, 15 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/nvidia-llm-inference-cost-reduction/https://jangwook.net/en/blog/en/nvidia-llm-inference-cost-reduction/How NVIDIA's NVFP4 quantization technology reduces LLM inference costs to 1/8 while preserving accuracy. We analyze the cost structure transformation from FP32 to FP4 with real-world benchmarks.Sun, 15 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/gpt52-theoretical-physics-discovery/https://jangwook.net/en/blog/en/gpt52-theoretical-physics-discovery/OpenAI's GPT-5.2 derived and proved a new formula for gluon scattering amplitudes. We analyze this historic turning point where AI transitions from tool to scientific discoverer.Sat, 14 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/icml-prompt-injection-academic-review/https://jangwook.net/en/blog/en/icml-prompt-injection-academic-review/Prompt injection text was discovered embedded in ICML submission PDFs. We analyze the security risks of AI-dependent academic peer review systems.Sat, 14 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/moltbook-ai-theater-human-control/https://jangwook.net/en/blog/en/moltbook-ai-theater-human-control/Moltbook's AI autonomous society was revealed to be controlled by human operators. We analyze the AI Theater phenomenon and its implications for engineering leaders.Sat, 14 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/openclaw-update-doctor-error-fix/https://jangwook.net/en/blog/en/openclaw-update-doctor-error-fix/How to fix the error: unknown command 'doctor' error when running openclaw update on the dev version. A step-by-step troubleshooting guide with 3 approaches tried.Sat, 14 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/gpt4o-retirement-model-dependency-risk/https://jangwook.net/en/blog/en/gpt4o-retirement-model-dependency-risk/GPT-4o retires in February 2026. We analyze model dependency risks, how Claude overtook OpenAI in enterprise market share, and why multi-model strategy is essential.Fri, 13 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/mit-soar-self-curriculum-reasoning/https://jangwook.net/en/blog/en/mit-soar-self-curriculum-reasoning/MIT's SOAR framework enables LLMs to self-generate training curricula, solving the learning plateau problem in reinforcement learning. Explore the core principles of this meta-RL self-improvement approach and its experimental results.Fri, 13 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/openai-atlas-ai-app-hub/https://jangwook.net/en/blog/en/openai-atlas-ai-app-hub/Analyzing OpenAI Atlas, the unified AI app hub in development, and what it means for the future of web browsers. Will AI-native platforms replace the browser?Fri, 13 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/webmcp-chrome-146-ai-tool-server/https://jangwook.net/en/blog/en/webmcp-chrome-146-ai-tool-server/Chrome 146 embeds MCP server capabilities directly into the browser. Learn how WebMCP works, how AI agents interact with it, and what it means for web development.Fri, 13 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/windsurf-arena-mode-speed-over-accuracy/https://jangwook.net/en/blog/en/windsurf-arena-mode-speed-over-accuracy/Windsurf's Arena Mode voting with over 40,000 votes reveals developers prioritize speed over accuracy. We analyze what this means for the future of AI coding tools.Fri, 13 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/multi-agent-swe-bench-verdent/https://jangwook.net/en/blog/en/multi-agent-swe-bench-verdent/Verdent AI achieves 76.1% on SWE-bench Verified using multi-agent parallel execution architecture, not a single large model. A new paradigm for software engineering automation.Thu, 12 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/patent-strategy-llm-era/https://jangwook.net/en/blog/en/patent-strategy-llm-era/Mark Cuban warns that published patents become LLM training material. As AI absorbs patent knowledge at scale, how should companies rethink their intellectual property strategies?Thu, 12 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/rlm-recursive-language-model-coding-agent/https://jangwook.net/en/blog/en/rlm-recursive-language-model-coding-agent/Analyzing a real implementation of MIT's RLM paper in coding agents. Learn how recursive self-invocation overcomes context limits and boosts single model performance by 91% from an engineering perspective.Thu, 12 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/ai-agent-kpi-ethics/https://jangwook.net/en/blog/en/ai-agent-kpi-ethics/Analyzing research showing LLM agents violate ethics 30-50% of the time under KPI pressure, and discussing governance design for AI agents from an EM perspective.Wed, 11 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/ai-model-rush-february-2026/https://jangwook.net/en/blog/en/ai-model-rush-february-2026/Gemini 3 Pro GA, Sonnet 5, GPT-5.3, Qwen 3.5, GLM 5, Deepseek v4, and Grok 4.20 are all scheduled for February 2026. An analysis of the largest AI model rush in history.Wed, 11 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/dena-perl-go-migration-ai-agents/https://jangwook.net/en/blog/en/dena-perl-go-migration-ai-agents/How DeNA migrated 6,000 lines of Perl to Go using two specialized AI agents — one for conversion, one for verification — completing a 6-month project in just 1 month.Wed, 11 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/gpt53-codex-rollout-pause/https://jangwook.net/en/blog/en/gpt53-codex-rollout-pause/Analyzing GitHub's temporary rollback of GPT-5.3-based Codex. Explores platform reliability, AI model upgrade risks, and countermeasures from an EM perspective.Wed, 11 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/accounting-ai-transformation-real-data/https://jangwook.net/en/blog/en/accounting-ai-transformation-real-data/Analyzing 6 months of real data from an accounting firm's AI agent deployment. Behind the 97% cost reduction and 80%→98% accuracy improvement lies a realistic journey of adoption challenges and organizational transformation.Tue, 10 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/meta-ai-agent-platform-sierra-avocado/https://jangwook.net/en/blog/en/meta-ai-agent-platform-sierra-avocado/Meta is evolving into an AI agent platform. We analyze the Sierra partnership, Avocado model, and Big Brain reasoning engine at the core of this transformation.Tue, 10 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/software-factory-zero-code-development/https://jangwook.net/en/blog/en/software-factory-zero-code-development/The factory model where humans neither write nor review code is becoming reality. We analyze scenario-based probabilistic testing, $1,000/day compute costs, and the fundamental transformation of the EM role.Tue, 10 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/ai-agent-cost-reality/https://jangwook.net/en/blog/en/ai-agent-cost-reality/AI agent autonomous moderation can cost more than human moderators. A data-driven cost structure analysis from someone actually running 8 AI agents in production.Mon, 09 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/ccc-vs-gcc-ai-compiled-c-compiler/https://jangwook.net/en/blog/en/ccc-vs-gcc-ai-compiled-c-compiler/Claude Opus 4.6 auto-generated a Rust-based C compiler with 16 parallel agents. It builds the Linux kernel, but how does it stack up against GCC? Analyzing the 80% quality at lightning speed paradigm.Mon, 09 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/multi-agent-orchestration-routing/https://jangwook.net/en/blog/en/multi-agent-orchestration-routing/When running multiple AI agents like Claude and Codex, task routing is the hardest challenge — and it mirrors delegation in engineering management.Mon, 09 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/openclaw-e2e-test-automation-guide/https://jangwook.net/en/blog/en/openclaw-e2e-test-automation-guide/A hands-on guide to building natural-language E2E tests using OpenClaw's browser automation, node device management, cron scheduling, and multi-agent orchestration.Sun, 08 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/adsense-low-value-content-technical-fix/https://jangwook.net/en/blog/en/adsense-low-value-content-technical-fix/A hands-on guide to diagnosing and fixing the technical issues behind AdSense rejections on a multilingual Astro blog—ads.txt conflicts, 996 ghost pages, and sitewide sitemap 404s.Sat, 07 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/claude-agent-teams-guide/https://jangwook.net/en/blog/en/claude-agent-teams-guide/A hands-on guide to enabling Claude Code's Agent Teams in an OpenClaw environment, configuring 5 specialized teams, and running them in production.Sat, 07 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/banana-x-image-prompt-guide/https://jangwook.net/en/blog/en/banana-x-image-prompt-guide/A systematic YAML 7-Part Structure for AI image prompts, derived from analyzing 300+ infographic design evaluations in Banana X. Includes high-scoring patterns and domain-specific templates.Fri, 06 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/openclaw-cron-fix-guide/https://jangwook.net/en/blog/en/openclaw-cron-fix-guide/Emergency guide to fix OpenClaw stable/beta (2026.2.3-1) cron job execution failures and missing reminders.Fri, 06 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/openclaw-opus-4-6-setup-guide/https://jangwook.net/en/blog/en/openclaw-opus-4-6-setup-guide/Configure Claude Opus 4.6 on OpenClaw with copy-paste settings. Unlock 1M token context and 128K output for your AI assistant.Fri, 06 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/claude-code-insights-usage-analysis/https://jangwook.net/en/blog/en/claude-code-insights-usage-analysis/I analyzed my real project usage patterns with Claude Code /insights. Discover what 1,042 sessions and 6,267 file modifications reveal about effective AI coding workflows and practical improvements.Thu, 05 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/openclaw-advanced-usage/https://jangwook.net/en/blog/en/openclaw-advanced-usage/Cron automation, webhook integration, MCP servers, multi-agent systems, browser automation, and more — 8 production-level OpenClaw use cases.Thu, 05 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/openclaw-installation-tutorial/https://jangwook.net/en/blog/en/openclaw-installation-tutorial/Step-by-step guide to installing OpenClaw, connecting Telegram, and having your first AI conversation. From Node.js setup to workspace configuration.Wed, 04 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/openclaw-introduction-guide/https://jangwook.net/en/blog/en/openclaw-introduction-guide/Discover OpenClaw, the open-source AI assistant platform. Multi-channel, multi-model, node system, and more — your complete guide to self-hosted AI.Tue, 03 Feb 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/tauri-ios-admob-rewarded-ads/https://jangwook.net/en/blog/en/tauri-ios-admob-rewarded-ads/A complete guide to integrating Google AdMob rewarded ads into Tauri v2 iOS apps. Learn how to develop a custom Swift plugin since no official plugin exists.Fri, 30 Jan 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/tauri-pixijs-ios-game-development/https://jangwook.net/en/blog/en/tauri-pixijs-ios-game-development/A complete guide to developing iOS games using Tauri 2.x and PixiJS 8, from environment setup to App Store deployment, with real project code examples.Mon, 26 Jan 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/tailwind-layoffs-opensource-ai-crisis/https://jangwook.net/en/blog/en/tailwind-layoffs-opensource-ai-crisis/Analyzing how AI is destroying documentation-based revenue models through the Tailwind Labs layoffs, the worsening unpaid labor problem for open source contributors, and sustainable monetization strategies.Mon, 12 Jan 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/claude-code-plugins-complete-guide/https://jangwook.net/en/blog/en/claude-code-plugins-complete-guide/A deep dive into the Claude Code plugin system. Explore 13 official plugins in detail, 100+ community marketplace plugins, actual plugin.json structure and installation methods with practical examples.Sun, 11 Jan 2026 00:00:00 GMThttps://jangwook.net/en/blog/en/anthropic-agent-skills-practical-guide/https://jangwook.net/en/blog/en/anthropic-agent-skills-practical-guide/Learn practical applications of Anthropic Agent Skills through tutorials and code examples, analyze ROI for business value, and maximize AI agent efficiency.Fri, 26 Dec 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/anthropic-agent-skills-standard/https://jangwook.net/en/blog/en/anthropic-agent-skills-standard/Anthropic's Agent Skills standard provides a universal method for AI agents to acquire and utilize new capabilities, fostering innovation and accelerating AI development across the industry.Thu, 25 Dec 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/monthly-analytics-2025-12/https://jangwook.net/en/blog/en/monthly-analytics-2025-12/75 days post-launch GA4 analysis - 85 daily visitors, 56.5% organic search, Google Code Wiki Guide as new top performer, China market surgeWed, 24 Dec 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/greptile-ai-coding-report-2025-review/https://jangwook.net/en/blog/en/greptile-ai-coding-report-2025-review/Analyzing Greptile's State of AI Coding 2025 report and examining the real productivity changes AI has brought to development, combined with personal experience.Fri, 19 Dec 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/ux-psychology-implementation-case-study/https://jangwook.net/en/blog/en/ux-psychology-implementation-case-study/A detailed look at implementing UX psychology principles including BlogCard reading time, card hover effects, Back to Top button, and reading progress bar with code examples.Sun, 14 Dec 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/ux-psychology-frontend-design-skill/https://jangwook.net/en/blog/en/ux-psychology-frontend-design-skill/Learn how to integrate 40 UX psychology concepts and 30 Laws of UX into Claude Code frontend-design skill to create beautiful and effective interfaces.Sat, 13 Dec 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/dena-llm-study-part5-agent-design/https://jangwook.net/en/blog/en/dena-llm-study-part5-agent-design/DeNA LLM Study Series finale. Practical guide to n8n workflows, agent design principles, multi-agent orchestration patterns, and memory management strategies.Fri, 12 Dec 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/dena-llm-study-part4-rag/https://jangwook.net/en/blog/en/dena-llm-study-part4-rag/Exploring RAG from core concepts to GraphRAG and Agentic RAG through DeNA LLM Study Series Part 4, covering cutting-edge retrieval-augmented generation techniques.Thu, 11 Dec 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/dena-llm-study-part3-model-training/https://jangwook.net/en/blog/en/dena-llm-study-part3-model-training/Deep dive into pre-training, fine-tuning, and reinforcement learning based on DeNA LLM study materials Part 3, exploring efficient techniques like LoRA, QLoRA, and DPO.Wed, 10 Dec 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/dena-llm-study-part2-structured-output/https://jangwook.net/en/blog/en/dena-llm-study-part2-structured-output/From structured outputs using JSON Schema and Pydantic to practical Multi-LLM pipeline design patterns like Sequential, Parallel, and Cascade for production applicationsTue, 09 Dec 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/dena-llm-study-part1-fundamentals/https://jangwook.net/en/blog/en/dena-llm-study-part1-fundamentals/DeNA LLM Study series begins. Comparing GPT-4, Claude, and Gemini, covering Next Token Prediction, Instruction Tuning, Reasoning models, and prompt engineering basics.Mon, 08 Dec 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/agent-effi-flow-pivot-omotenashi-bot/https://jangwook.net/en/blog/en/agent-effi-flow-pivot-omotenashi-bot/A strategic transition from AI efficiency tools to the Japanese inbound tourism market. Sharing market analysis and the OmotenashiBot service development journey of a solo developer finding blue ocean opportunities.Sun, 07 Dec 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/iterative-review-cycle-methodology/https://jangwook.net/en/blog/en/iterative-review-cycle-methodology/오케스트레이션 에이전트 중심의 반복적 리뷰 사이클을 통해 복잡한 개발 작업의 에러율을 40-90% 감소시키는 체계적 방법론을 소개합니다.Sat, 06 Dec 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/aeo-implementation-experience/https://jangwook.net/en/blog/en/aeo-implementation-experience/A practical guide to implementing AEO strategies for AI search engines like ChatGPT and Perplexity, with real-world implementation examples from a B2B SaaS platform.Fri, 05 Dec 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/multi-agent-orchestration-improvement/https://jangwook.net/en/blog/en/multi-agent-orchestration-improvement/A comprehensive guide to analyzing 48 files and fixing 61 issues using Claude Codes multi-agent orchestration pattern for large-scale system improvementsThu, 04 Dec 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/adsense-rejection-ai-analysis-improvement/https://jangwook.net/en/blog/en/adsense-rejection-ai-analysis-improvement/After Google AdSense rejected my site for "Low Value Content", I used ChatGPT, Claude, and Gemini to analyze the issues and improved approval probability from 5.5 to 8.5 out of 10. Here is my experience.Wed, 03 Dec 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/ai-era-career-advice-for-juniors/https://jangwook.net/en/blog/en/ai-era-career-advice-for-juniors/Career advice from years of SMB experience. How domain knowledge and T-shaped growth can help you thrive in the AI era.Tue, 02 Dec 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/enterprise-ai-adoption-topdown/https://jangwook.net/en/blog/en/enterprise-ai-adoption-topdown/Limits of bottom-up AI adoption and organizational change management strategies. A systematic approach through workflow documentation and standardization.Mon, 01 Dec 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/vertex-ai-search-site-implementation/https://jangwook.net/en/blog/en/vertex-ai-search-site-implementation/Learn how to implement AI-powered search on your website using Google Vertex AI Search. This guide covers Cloud Functions API server setup to shell script automated deployment step by step.Sun, 30 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/gcloud-mcp-infrastructure-audit/https://jangwook.net/en/blog/en/gcloud-mcp-infrastructure-audit/Learn how to automatically detect security vulnerabilities and configuration issues in GCP infrastructure using AI agents and gcloud MCP.Sat, 29 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/llm-seo-aeo-practical-implementation/https://jangwook.net/en/blog/en/llm-seo-aeo-practical-implementation/From SEO foundation to AEO strategy: real implementation case study with measurable results from the Agent Effi Flow projectFri, 28 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/individual-developer-ai-saas-journey/https://jangwook.net/en/blog/en/individual-developer-ai-saas-journey/Real-world experience building a B2B AI OCR service with SvelteKit, Supabase, and Google Gemini API. Tech stack rationale, implementation details, and business strategy from a solo developer's perspective.Thu, 27 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/terraform-ai-batch-infrastructure/https://jangwook.net/en/blog/en/terraform-ai-batch-infrastructure/A practical guide to building cost-effective AI batch processing infrastructure using API Gateway, Lambda, and ECS FargateWed, 26 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/e2e-page-test-automation-claude-code/https://jangwook.net/en/blog/en/e2e-page-test-automation-claude-code/Build an automated page quality verification system for web publishers. Test 8 quality items with a single command and receive improvement suggestions.Tue, 25 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/google-code-wiki-guide/https://jangwook.net/en/blog/en/google-code-wiki-guide/Explore Google Code Wiki features, usage guide, and Gemini-based automatic documentation system in detail.Mon, 24 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/mcp-servers-toolkit-introduction/https://jangwook.net/en/blog/en/mcp-servers-toolkit-introduction/Maximize Claude Code productivity with 7 essential MCP servers. Learn Serena, Context7, Sequential Thinking setup and real-world usage patternsSun, 23 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/deep-agents-architecture-optimization/https://jangwook.net/en/blog/en/deep-agents-architecture-optimization/A practical guide to analyzing Deep Agents concepts from LangChain and Philipp Schmid and optimizing agent architectureSat, 22 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/claude-code-cli-migration-guide/https://jangwook.net/en/blog/en/claude-code-cli-migration-guide/Learn how to migrate from Claude Code to GitHub Copilot CLI, Gemini CLI, or Codex CLI with practical guidance on choosing the right tool for your situationFri, 21 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/45-day-analytics-report-2025-11/https://jangwook.net/en/blog/en/45-day-analytics-report-2025-11/Comprehensive GA4 analysis of blog's first 45 days - 44.3% organic search achieved, SEO optimization ROI proven, traffic spike investigation, 91% bounce rate crisis on English homepageThu, 20 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/mcp-code-execution-practical-implementation/https://jangwook.net/en/blog/en/mcp-code-execution-practical-implementation/Learn how to apply Anthropic's MCP Code Execution patterns to real projects with practical examples of directory structure improvements and security configurations.Wed, 19 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/anthropic-code-execution-mcp/https://jangwook.net/en/blog/en/anthropic-code-execution-mcp/Explore how Anthropic's Code Execution with MCP achieves 98.7% token reduction and 60% faster execution through sandboxed code-based tool orchestration.Tue, 18 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/adding-chinese-support/https://jangwook.net/en/blog/en/adding-chinese-support/Experience report on adding Chinese support to 40 posts. Parallel agent processing to update 120 files, SEO optimization, automation strategies - everything about expanding an Astro multilingual blogMon, 17 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/effiflow-automation-analysis-part3/https://jangwook.net/en/blog/en/effiflow-automation-analysis-part3/Practical implementation of Top 3 Quick Wins. Achieving 100% completion and 99% stability with 38 minutes of investment and ROI analysisSun, 16 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/effiflow-automation-analysis-part2/https://jangwook.net/en/blog/en/effiflow-automation-analysis-part2/Skills auto-discovery mechanism and Commands integration. Achieving 58% token reduction through caching strategySat, 15 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/effiflow-automation-analysis-part1/https://jangwook.net/en/blog/en/effiflow-automation-analysis-part1/Blog automation with 17 Agents and metadata-first architecture. Case study achieving 60-70% token reduction and full automationFri, 14 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/google-gemini-file-search-rag-tutorial/https://jangwook.net/en/blog/en/google-gemini-file-search-rag-tutorial/A practical guide to building document search and Q&A systems using Gemini File Search Tool announced in November 2025, without complex RAG pipelines. Dramatically reduce development time with fully-managed RAG.Thu, 13 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/prompt-engineering-agent-improvements/https://jangwook.net/en/blog/en/prompt-engineering-agent-improvements/Research-backed prompt engineering techniques applied to 17 Claude Code agents, with measurable results and practical implementation guide.Wed, 12 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/n8n-rss-automation/https://jangwook.net/en/blog/en/n8n-rss-automation/Learn how to build a complete automation pipeline from blog publishing to social media with GitHub Actions, RSS feeds, and n8n workflows powered by AI.Tue, 11 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/figma-mcp-web-components-sync/https://jangwook.net/en/blog/en/figma-mcp-web-components-sync/Comprehensive guide on generating web components from Figma using MCP and implementing continuous design-to-code synchronization with vanilla JavaScript.Mon, 10 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/claude-code-verbalized-sampling/https://jangwook.net/en/blog/en/claude-code-verbalized-sampling/A practical guide to applying Verbalized Sampling technique to Claude Code agents, achieving 2.0x prompt diversity, 1.8x content diversity, and 1.6x writing style diversity. Complete with 4 agent modification histories, parameter tuning, and cost analysis.Sun, 09 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/verbalized-sampling-llm-diversity/https://jangwook.net/en/blog/en/verbalized-sampling-llm-diversity/Verbalized Sampling tackles mode collapse after alignment by prompting models to verbalize probability distributions, achieving 1.6-2.1x diversity gains without retrainingSat, 08 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/three-week-analytics-2025-11-04/https://jangwook.net/en/blog/en/three-week-analytics-2025-11-04/2025-10-15〜11-04 GA4 analysis, organic search leap from 4.3% to 54.4%, 20 new posts published, South Korea emerges as #1 country - transparently sharing blog growth journeyThu, 06 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/data-driven-pm-framework/https://jangwook.net/en/blog/en/data-driven-pm-framework/Master data-driven product decisions using analytics frameworks, key metrics, and A/B testing best practices. Learn from top PMs at Netflix, Spotify, and Amazon.Wed, 05 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/slack-mcp-team-communication/https://jangwook.net/en/blog/en/slack-mcp-team-communication/Learn how to leverage Slack MCP for automated team communication analysis, sentiment tracking, and actionable insights using Claude AI and Model Context Protocol.Tue, 04 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/notion-backlog-slack-claude-project-management/https://jangwook.net/en/blog/en/notion-backlog-slack-claude-project-management/Learn how to standardize project management with Notion, Backlog, Slack, and Claude Code to boost team productivity by 50% and project success rates by 80%.Mon, 03 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/recommendation-system-v3/https://jangwook.net/en/blog/en/recommendation-system-v3/Removing the bloated recommendations.json and embedding recommendation data directly in frontmatter eliminates runtime file I/O by 100%. Here is our V3 system journey and results.Sun, 02 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/llm-pm-workflow-automation/https://jangwook.net/en/blog/en/llm-pm-workflow-automation/A practical guide to automating project management tasks and maximizing productivity using cutting-edge LLM tools like ChatGPT, Claude, and Gemini. Step-by-step walkthrough from daily task automation to ROI measurement.Sat, 01 Nov 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/claude-code-parallel-testing/https://jangwook.net/en/blog/en/claude-code-parallel-testing/Practical guide to running web page migration tests 5-8x faster with Claude Code agents and Playwright parallel executionFri, 31 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/llm-page-migration-standardization/https://jangwook.net/en/blog/en/llm-page-migration-standardization/Learn how to automate web page migration using LLMs, Web Components, and comprehensive testing frameworks. Discover proven strategies from Google, Airbnb, and industry leaders.Thu, 30 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/claude-code-hooks-workflow/https://jangwook.net/en/blog/en/claude-code-hooks-workflow/Complete guide from hook-based coding rule configuration to CI/CD integration for production-ready automated review processesWed, 29 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/bigquery-mcp-prefix-filtering/https://jangwook.net/en/blog/en/bigquery-mcp-prefix-filtering/Learn how to build a Model Context Protocol server for BigQuery with dataset prefix filtering, including architecture, implementation, and security best practices.Tue, 28 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/jules-autocoding/https://jangwook.net/en/blog/en/jules-autocoding/Learn how to automate GitHub issue resolution and PR creation with Jules, Google's groundbreaking AI coding agent powered by Gemini 2.5 ProMon, 27 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/langgraph-multi-agent/https://jangwook.net/en/blog/en/langgraph-multi-agent/Build stateful multi-agent AI systems with LangGraph. Learn graph-based orchestration, deployment patterns, and real-world use cases from LinkedIn and Uber.Sun, 26 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/playwright-ai-testing/https://jangwook.net/en/blog/en/playwright-ai-testing/Complete guide to E2E test automation with Playwright and AI Codegen. TypeScript implementation, GitHub Actions integration, and visual regression testing for production-ready test suitesSat, 25 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/ssr-survey-analysis/https://jangwook.net/en/blog/en/ssr-survey-analysis/Experimental results and statistical analysis of 225 evaluations using LLM-based Semantic Similarity Rating. Validated high reliability with ICC 0.83 and visualizations.Fri, 24 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/llm-consumer-research-ssr/https://jangwook.net/en/blog/en/llm-consumer-research-ssr/Revolutionary LLM-based synthetic consumer research achieves 90% human reliability using SSR methodologyThu, 23 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/claude-skills-implementation-guide/https://jangwook.net/en/blog/en/claude-skills-implementation-guide/A practical guide documenting the journey from introducing Claude Agent Skills to real-world implementation, including trials, errors, and achievements. Learn how to specialize AI agents through folder-based modularization.Wed, 22 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/openai-agentkit-tutorial-part2/https://jangwook.net/en/blog/en/openai-agentkit-tutorial-part2/From enterprise-grade multi-agent system design to production deployment, master AgentKit implementation in real-world scenariosTue, 21 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/openai-agentkit-tutorial-part1/https://jangwook.net/en/blog/en/openai-agentkit-tutorial-part1/From core concepts to hands-on tutorials: everything you need to know about OpenAI AgentKit announced in October 2025Mon, 20 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/ai-agent-persona-analysis/https://jangwook.net/en/blog/en/ai-agent-persona-analysis/Psychological effects and optimal design strategies for AI agent personas revealed through 120+ research studies and industry best practicesSun, 19 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/metadata-based-recommendation-optimization/https://jangwook.net/en/blog/en/metadata-based-recommendation-optimization/How we eliminated 100% of token usage and reduced execution time by 99% in our content recommendation system through metadata-based algorithmic optimization.Sat, 18 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/self-healing-ai-systems/https://jangwook.net/en/blog/en/self-healing-ai-systems/Complete guide to Self-Healing Systems deployed by GitHub, Google, and Netflix. Full implementation from error detection to automatic patching with LangGraphFri, 17 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/ai-agent-collaboration-patterns/https://jangwook.net/en/blog/en/ai-agent-collaboration-patterns/Orchestrate Architecture, Coding, Testing, Security, and DevOps agents to build production-grade applicationsThu, 16 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/specification-driven-development/https://jangwook.net/en/blog/en/specification-driven-development/Complete guide to systematic AI development with GitHub Spec Kit. Move beyond "Vibe Coding" to build scalable, maintainable production code that truly works.Wed, 15 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/weekly-analytics-2025-10-14/https://jangwook.net/en/blog/en/weekly-analytics-2025-10-14/GA4 data analysis, content performance, and improvement impact one week after blog launch - transparently sharing our blog growth journey (2025-10-07~10-14)Tue, 14 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/astro-scheduled-publishing/https://jangwook.net/en/blog/en/astro-scheduled-publishing/A practical guide to implementing WordPress-like scheduled post publishing on static blogs using Astro and GitHub Pages. Complete automation with pubDate filtering and scheduled workflowsMon, 13 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/ai-content-recommendation-system/https://jangwook.net/en/blog/en/ai-content-recommendation-system/A comprehensive guide to building an AI-powered blog recommendation system that goes beyond simple tag matching with semantic understandingSun, 12 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/chrome-devtools-mcp-performance/https://jangwook.net/en/blog/en/chrome-devtools-mcp-performance/Complete guide to Chrome DevTools MCP: AI assistants measure and optimize performance with real browser data. From Core Web Vitals automation to practical workflows.Sat, 11 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/ai-agent-notion-mcp-automation/https://jangwook.net/en/blog/en/ai-agent-notion-mcp-automation/Complete guide to building production-ready AI agent automation systems using Model Context Protocol (MCP) and Claude Code with Notion integration. Expert-verified tutorial covering capabilities, limitations, benefits, and best practices from SEO and content management perspectives.Fri, 10 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/ai-presentation-automation/https://jangwook.net/en/blog/en/ai-presentation-automation/Learn how we reduced semi-annual reporting preparation from over 60 hours to just 10 hours using AI agent systems and automation tools in this practical implementation guide.Thu, 09 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/claude-code-web-automation/https://jangwook.net/en/blog/en/claude-code-web-automation/A practical case study of auto-generating 31 HTML pages using a parts library-based approach. Complete guide covering CSV metadata management, SubAgent parallel processing, and two-phase quality validation.Wed, 08 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/claude-code-best-practices/https://jangwook.net/en/blog/en/claude-code-best-practices/A comprehensive guide to optimizing Claude Code setup based on Anthropic official best practices, with real-world implementation insights.Tue, 07 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/blog-launch-analysis-report/https://jangwook.net/en/blog/en/blog-launch-analysis-report/Blog launch GA4 data analysis, practical MCP query examples, and 3-month growth strategy - transparently sharing the journey of starting a technical blogMon, 06 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/google-analytics-mcp-automation/https://jangwook.net/en/blog/en/google-analytics-mcp-automation/Learn how to automate blog analytics and make data-driven decisions using MCP and AI agentsSun, 05 Oct 2025 00:00:00 GMThttps://jangwook.net/en/blog/en/llm-blog-automation/https://jangwook.net/en/blog/en/llm-blog-automation/Complete guide to automating your blog with Claude Code and 11 specialized AI agents. From prompt engineering to MCP integration, multi-language support, and image generation - a practical tutorial anyone can follow.Sat, 04 Oct 2025 00:00:00 GMT