<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Minbook</title><description>Practical AI execution notes — from experiments to production</description><link>https://minbook.dev/</link><language>en</language><item><title>The &apos;Europe Is Behind&apos; Illusion — EU and US AI Automation Are Nearly Identical, the Real Gap Is Elsewhere</title><link>https://minbook.dev/en/blog/ai-automation-eu-us-convergence/</link><guid isPermaLink="true">https://minbook.dev/en/blog/ai-automation-eu-us-convergence/</guid><description>McKinsey&apos;s &apos;Agents, robots, and us&apos; Europe report shows EU and US automation potential are nearly identical. Contrary to popular belief, the gap is not in technology but in adoption pace and country-level variance. The real shape of skill reshuffling revealed by 5× AI fluency demand and the Skill Change Index.</description><pubDate>Thu, 14 May 2026 00:00:00 GMT</pubDate></item><item><title>Multi-Agent Workflow — 6 Patterns from Supervisor to Swarm</title><link>https://minbook.dev/en/blog/multi-agent-workflow-patterns/</link><guid isPermaLink="true">https://minbook.dev/en/blog/multi-agent-workflow-patterns/</guid><description>Supervisor / Sequential / Hierarchical / Network / Swarm / Map-Reduce — six core multi-agent workflow patterns that LangGraph, AutoGen, and CrewAI call by different names. Each pattern&apos;s topology, fit, no-fit, and a decision framework for production use.</description><pubDate>Sat, 09 May 2026 00:00:00 GMT</pubDate></item><item><title>Multi-Agent for Korean Financial Marketing — A Phased Sketch</title><link>https://minbook.dev/en/blog/phased-financial-marketing-multi-agent/</link><guid isPermaLink="true">https://minbook.dev/en/blog/phased-financial-marketing-multi-agent/</guid><description>One way to think about progressively automating Korean financial advertising with multi-agents — components, patterns, limits, and what stays human.</description><pubDate>Fri, 08 May 2026 00:00:00 GMT</pubDate></item><item><title>Single vs Multi-Agent — Same Sources, Opposite Conclusions</title><link>https://minbook.dev/en/blog/single-vs-multi-agent/</link><guid isPermaLink="true">https://minbook.dev/en/blog/single-vs-multi-agent/</guid><description>Anthropic&apos;s Multi-Agent Research System (+90.2%, 15x tokens) and Cognition Labs&apos; &apos;Don&apos;t Build Multi-Agents&apos;. Two camps cite the same primary sources and arrive at opposite recommendations — here&apos;s the decision framework that emerges when you read them side by side.</description><pubDate>Thu, 07 May 2026 00:00:00 GMT</pubDate></item><item><title>Will AI Free or Cement Korea — Deregulation × AI Build × SI Inertia</title><link>https://minbook.dev/en/blog/korea-saas-trap-future/</link><guid isPermaLink="true">https://minbook.dev/en/blog/korea-saas-trap-future/</guid><description>Three forces are simultaneously hitting Korea&apos;s build trap. Deregulation slowly opens the SaaS market. AI build resurgence sends global back toward build. SI inertia resists change. The collision of these three forces produces three scenarios — and one real branching point.</description><pubDate>Wed, 06 May 2026 00:00:00 GMT</pubDate></item><item><title>The Cost of Being Trapped — How LINE WORKS, Younglimwon, and RSUPPORT Detour Through Japan</title><link>https://minbook.dev/en/blog/korea-saas-trap-cost/</link><guid isPermaLink="true">https://minbook.dev/en/blog/korea-saas-trap-cost/</guid><description>Korean SaaS companies that can&apos;t sell at home become market leaders in Japan. LINE WORKS holds #1 in Japan for 8 consecutive years; Younglimwon&apos;s SystemEver runs a separate Tokyo subsidiary; RSUPPORT dominates Japan&apos;s telework market. Same companies, same products, different markets — the most direct evidence of Korea&apos;s build trap.</description><pubDate>Tue, 05 May 2026 00:00:00 GMT</pubDate></item><item><title>How We Got Trapped — Government SW Pricing, Hancom, and 30 Years of SI Outsourcing</title><link>https://minbook.dev/en/blog/korea-saas-trap-history/</link><guid isPermaLink="true">https://minbook.dev/en/blog/korea-saas-trap-history/</guid><description>Korea&apos;s build trap isn&apos;t an accident. It&apos;s the cumulative result of public software pricing in the 1990s, the NIH mindset embodied by Hancom and groupware, and 30 years of IT outsourcing. Korea Build Trap Series Part 1.</description><pubDate>Mon, 04 May 2026 00:00:00 GMT</pubDate></item><item><title>Why Korea Doesn&apos;t Buy Software — A Build/Buy/Assemble Reframe of Korea&apos;s AI B2B Market</title><link>https://minbook.dev/en/blog/korea-saas-trap-pillar/</link><guid isPermaLink="true">https://minbook.dev/en/blog/korea-saas-trap-pillar/</guid><description>Korea ranks #1 in R&amp;D-to-GDP (5.0%) but #51 in software spending-to-GDP (0.3%) — same WIPO GII 2025 report, same page. The five &apos;peculiarities&apos; of Korea&apos;s AI B2B market reduce to one root cause: the build trap.</description><pubDate>Sun, 03 May 2026 00:00:00 GMT</pubDate></item><item><title>The Advisor Pattern Is a Price Tag, Not Architecture</title><link>https://minbook.dev/en/blog/advisor-pattern-is-pricing/</link><guid isPermaLink="true">https://minbook.dev/en/blog/advisor-pattern-is-pricing/</guid><description>Anthropic&apos;s Advisor Tool is not new architecture. It is a product of the 2026 pricing structure. Eleven Q2 2026 papers on agent orchestration share one quiet move underneath: reversal of traditional role assignments.</description><pubDate>Wed, 29 Apr 2026 00:00:00 GMT</pubDate></item><item><title>How to Organize Agents — Hierarchy, Graph, Swarm, Routing, and Skepticism</title><link>https://minbook.dev/en/blog/orchestration-structures-and-skepticism/</link><guid isPermaLink="true">https://minbook.dev/en/blog/orchestration-structures-and-skepticism/</guid><description>The four structures the 2026 agent orchestration literature uses to organize sliced agents (Hierarchy, Graph, Swarm, Routing), with three observations: capability gains drive complexity gains, the LLM swarm framing fails on its own definition, and structure choice is a dependent variable of pricing.</description><pubDate>Tue, 28 Apr 2026 00:00:00 GMT</pubDate></item><item><title>How to Slice an Agent — Five Axes from 2026 Research</title><link>https://minbook.dev/en/blog/orchestration-decomposition-5-axes/</link><guid isPermaLink="true">https://minbook.dev/en/blog/orchestration-decomposition-5-axes/</guid><description>Role, Skill, Time, Judge, Planner-Executor. The five axes 2026 agent orchestration research uses to slice an agent, walked through six papers, with three observations attached: vocabulary fragmentation, an empty time axis, and accumulating decomposition.</description><pubDate>Mon, 27 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Re-reading the Stanford AI Index 2026 — Why It Feels Weaker Than Last Year</title><link>https://minbook.dev/en/blog/stanford-ai-index-2026-is-too-slow/</link><guid isPermaLink="true">https://minbook.dev/en/blog/stanford-ai-index-2026-is-too-slow/</guid><description>The 2026 AI Index from Stanford HAI still carries plenty of data, but the insights land with less weight than last year. What the report says, what it misses, and why an annual cadence has fallen out of step with how 2026 actually moves.</description><pubDate>Sun, 26 Apr 2026 00:00:00 GMT</pubDate></item><item><title>AI Products Need a Different Playbook — 12 Counterintuitive Lessons from 20 Builders</title><link>https://minbook.dev/en/blog/ai-product-counterintuitive-lessons/</link><guid isPermaLink="true">https://minbook.dev/en/blog/ai-product-counterintuitive-lessons/</guid><description>Counterintuitive advice from builders at GitHub, Stripe, Intercom, Perplexity, and Canva. Plus the CC/CD framework and a 3-phase eval system for AI products.</description><pubDate>Fri, 24 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Build Your Own Self-Tuning Loop — Reference Implementation Guide</title><link>https://minbook.dev/en/blog/self-tuning-loop-build-your-own/</link><guid isPermaLink="true">https://minbook.dev/en/blog/self-tuning-loop-build-your-own/</guid><description>The Self-Tuning Loop pattern extracted into a modular, domain-agnostic toolkit. Supabase schema, analysis/evolution prompts, and Quick Start guide — all open source.</description><pubDate>Fri, 24 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Cron + Telegram + Claude: Anatomy of a Self-Improving System at $0</title><link>https://minbook.dev/en/blog/self-tuning-loop-system-anatomy/</link><guid isPermaLink="true">https://minbook.dev/en/blog/self-tuning-loop-system-anatomy/</guid><description>35 sources auto-collected, AI-curated, feedback loops, auto-evolving prompts. Full architecture of a Self-Tuning Loop system running in production at $0 additional cost.</description><pubDate>Tue, 21 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Railway + Supabase Operational Review</title><link>https://minbook.dev/en/blog/railway-supabase-review/</link><guid isPermaLink="true">https://minbook.dev/en/blog/railway-supabase-review/</guid><description>Operational experience running WICHI&apos;s backend on Railway and Supabase — strengths, pitfalls, and when to migrate away.</description><pubDate>Mon, 20 Apr 2026 00:00:00 GMT</pubDate></item><item><title>GEO Score 4-Layer Metric Design</title><link>https://minbook.dev/en/blog/geo-score-4-layer-design/</link><guid isPermaLink="true">https://minbook.dev/en/blog/geo-score-4-layer-design/</guid><description>Design philosophy behind WICHI&apos;s 4-layer GEO Score architecture — Inclusion, Prominence, Quality, and Stability — and why a single number fails to capture AI search visibility.</description><pubDate>Sun, 19 Apr 2026 00:00:00 GMT</pubDate></item><item><title>The Wasted Learning Signal — The Gap Between AI Drafts and What You Actually Publish</title><link>https://minbook.dev/en/blog/self-tuning-loop-wasted-signal/</link><guid isPermaLink="true">https://minbook.dev/en/blog/self-tuning-loop-wasted-signal/</guid><description>Every time you edit an AI draft, you&apos;re generating a learning signal that gets thrown away. Self-Tuning Loop captures edit diffs to automatically evolve your prompts — no fine-tuning required.</description><pubDate>Sat, 18 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Designing the 9-Bucket Query Framework</title><link>https://minbook.dev/en/blog/9-bucket-query-framework/</link><guid isPermaLink="true">https://minbook.dev/en/blog/9-bucket-query-framework/</guid><description>How and why WICHI classifies AI search queries into 9 buckets across 3 zones, using brand presence rather than search intent as the primary axis.</description><pubDate>Fri, 17 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Multi-Engine Architecture — Parallel Collection from 3 AI Search Engines</title><link>https://minbook.dev/en/blog/multi-engine-architecture/</link><guid isPermaLink="true">https://minbook.dev/en/blog/multi-engine-architecture/</guid><description>Why WICHI chose to query multiple AI search engines simultaneously, and how cross-engine response variance became the core analytical signal for measuring brand visibility.</description><pubDate>Thu, 16 Apr 2026 00:00:00 GMT</pubDate></item><item><title>What Happens When You Launch Without Monitoring</title><link>https://minbook.dev/en/blog/monitoring-before-launch/</link><guid isPermaLink="true">https://minbook.dev/en/blog/monitoring-before-launch/</guid><description>How WICHI discovered errors through user reports averaging 15 hours after occurrence. Setting up Sentry and Betterstack for minimum monitoring at zero cost, and why monitoring should come before features.</description><pubDate>Wed, 15 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Why the Share Feature Comes First in PLG — Designing mmu share</title><link>https://minbook.dev/en/blog/plg-mmu-share-design/</link><guid isPermaLink="true">https://minbook.dev/en/blog/plg-mmu-share-design/</guid><description>In Product-Led Growth, why the share feature must be built before anything else. The rationale behind plain text cards, the gated progression system, and the principle of &apos;if the numbers don&apos;t work, don&apos;t move to the next stage.&apos;</description><pubDate>Mon, 13 Apr 2026 00:00:00 GMT</pubDate></item><item><title>GEO Paper Review: Evaluation Systems and Manipulation Risks</title><link>https://minbook.dev/en/blog/paper-review-geo-evaluation-risks/</link><guid isPermaLink="true">https://minbook.dev/en/blog/paper-review-geo-evaluation-risks/</guid><description>Review of SAGEO Arena (unified evaluation framework) and CORE (ranking manipulation research) — GEO&apos;s measurement methodology and adversarial vulnerabilities.</description><pubDate>Sun, 12 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Using Feature Flags to Fix CLI Score Accuracy — Solving the False-Pass Problem</title><link>https://minbook.dev/en/blog/feature-flag-false-pass/</link><guid isPermaLink="true">https://minbook.dev/en/blog/feature-flag-false-pass/</guid><description>Stripe isn&apos;t even used, but billing items fail. How MMU&apos;s checklist false-fail problem was solved with a condition marker system: 17 feature flags, 48 regression tests, and a score accuracy improvement from 58% to 85%.</description><pubDate>Sat, 11 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Anthropic&apos;s 96 Hours — Access, Capability, Execution Across Three Layers</title><link>https://minbook.dev/en/blog/anthropic-96h-3-layer/</link><guid isPermaLink="true">https://minbook.dev/en/blog/anthropic-96h-3-layer/</guid><description>Three Anthropic announcements between April 4 and April 8, 2026 — the third-party harness cutoff, Claude Mythos Preview, and Claude Managed Agents — analyzed through a three-layer AI stack frame.</description><pubDate>Fri, 10 Apr 2026 00:00:00 GMT</pubDate></item><item><title>GEO Paper Review: Optimization Approaches and Vertical Applications</title><link>https://minbook.dev/en/blog/paper-review-geo-optimization/</link><guid isPermaLink="true">https://minbook.dev/en/blog/paper-review-geo-optimization/</guid><description>Comparative review of AutoGEO (quality-preserving optimization) and E-GEO (e-commerce benchmark) — two divergent approaches to GEO engineering.</description><pubDate>Thu, 09 Apr 2026 00:00:00 GMT</pubDate></item><item><title>GEO Paper Review: Definition and Foundational Frameworks</title><link>https://minbook.dev/en/blog/paper-review-geo-foundation/</link><guid isPermaLink="true">https://minbook.dev/en/blog/paper-review-geo-foundation/</guid><description>Academic review of the KDD 2024 GEO paper and Chen et al. 2025 — GEO-Bench, PAWC metric, and earned media preference patterns in AI search.</description><pubDate>Wed, 08 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Solo Builder OSS Monetization — Is It Possible Without Enterprise Sales?</title><link>https://minbook.dev/en/blog/solo-builder-oss-monetization/</link><guid isPermaLink="true">https://minbook.dev/en/blog/solo-builder-oss-monetization/</guid><description>Synthesizing the OSS monetization strategies of 8 companies analyzed across G4a-G5, reframed for the solo builder. A 5-stage execution framework for generating revenue from open source without enterprise sales or managed infrastructure.</description><pubDate>Tue, 07 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Six GEO Business Opportunities and WICHI&apos;s Choice</title><link>https://minbook.dev/en/blog/geo-opportunities-wichi-choice/</link><guid isPermaLink="true">https://minbook.dev/en/blog/geo-opportunities-wichi-choice/</guid><description>A comprehensive analysis of six business opportunities in the GEO market — SaaS, agency, education, data infrastructure, vertical specialization, and GEO+PR — and the strategic reasoning behind WICHI&apos;s decision to pursue SaaS targeting the Asian market.</description><pubDate>Sun, 05 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Monetizing AI Infrastructure — Hugging Face, Qdrant, Weaviate</title><link>https://minbook.dev/en/blog/ai-infrastructure-monetization/</link><guid isPermaLink="true">https://minbook.dev/en/blog/ai-infrastructure-monetization/</guid><description>Hugging Face, Qdrant, and Weaviate open-source their core infrastructure — model hubs and vector databases anyone can self-host. How they generate revenue from managed cloud services, and what patterns solo builders can borrow.</description><pubDate>Sat, 04 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Agent System Design Canvas — 12 Production Patterns Proven by the Claude Code Leak</title><link>https://minbook.dev/en/blog/agent-system-design-canvas/</link><guid isPermaLink="true">https://minbook.dev/en/blog/agent-system-design-canvas/</guid><description>A 6-layer design framework and 12 core patterns for agent systems, extracted from 512,000 lines of leaked TypeScript source.</description><pubDate>Fri, 03 Apr 2026 00:00:00 GMT</pubDate></item><item><title>HubSpot, Semrush, Adobe, and Conductor Enter GEO — How Incumbents Are Moving</title><link>https://minbook.dev/en/blog/big-players-entering-geo/</link><guid isPermaLink="true">https://minbook.dev/en/blog/big-players-entering-geo/</guid><description>A detailed analysis of how major marketing and SEO incumbents are entering the GEO market, covering their products, pricing, strategies, and the structural implications for the ecosystem.</description><pubDate>Fri, 03 Apr 2026 00:00:00 GMT</pubDate></item><item><title>What the Claude Code Leak Revealed: Anatomy of an AI Agent</title><link>https://minbook.dev/en/blog/claude-code-anatomy-architecture/</link><guid isPermaLink="true">https://minbook.dev/en/blog/claude-code-anatomy-architecture/</guid><description>512,000 lines of TypeScript, 1,884 files. The anatomy of a production agent system: 4-phase execution, 7 modes, and the 11-step agent loop.</description><pubDate>Fri, 03 Apr 2026 00:00:00 GMT</pubDate></item><item><title>KAIROS, Auto-Dream, Coordinator: What Unreleased Features Reveal About AI&apos;s Future</title><link>https://minbook.dev/en/blog/claude-code-anatomy-hidden-features/</link><guid isPermaLink="true">https://minbook.dev/en/blog/claude-code-anatomy-hidden-features/</guid><description>8 hidden features found in Claude Code&apos;s source. Autonomous agents, memory consolidation, and multi-agent orchestration designed but not shipped.</description><pubDate>Fri, 03 Apr 2026 00:00:00 GMT</pubDate></item><item><title>The Memory System I Built Looked Like Claude Code&apos;s Internal Design</title><link>https://minbook.dev/en/blog/claude-code-anatomy-my-memory-system/</link><guid isPermaLink="true">https://minbook.dev/en/blog/claude-code-anatomy-my-memory-system/</guid><description>Comparing Claude Code&apos;s Auto-Dream and Memory System with an independently built 3-layer memory architecture. Where they converge, where they diverge.</description><pubDate>Fri, 03 Apr 2026 00:00:00 GMT</pubDate></item><item><title>52 Tools, 23-Step Security: Inside an Agent&apos;s Tool System</title><link>https://minbook.dev/en/blog/claude-code-anatomy-tools/</link><guid isPermaLink="true">https://minbook.dev/en/blog/claude-code-anatomy-tools/</guid><description>How Claude Code manages 52 tools. The 10-step execution pipeline, parallel/sequential concurrency model, and 888KB Tree-sitter AST security.</description><pubDate>Fri, 03 Apr 2026 00:00:00 GMT</pubDate></item><item><title>How AI Observability Platforms Make Money -- Langfuse and Dify</title><link>https://minbook.dev/en/blog/ai-observability-monetization/</link><guid isPermaLink="true">https://minbook.dev/en/blog/ai-observability-monetization/</guid><description>Langfuse and Dify monetize at the observation and operations layer above AI frameworks. An analysis of MIT+EE models, self-hosting strategies, community expansion, and why the observability layer is structurally better for revenue than frameworks.</description><pubDate>Wed, 01 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Beyond Ralph Loop — Self-Evolving Agents and the Shifting Role of AI Developers</title><link>https://minbook.dev/en/blog/ralph-loop-beyond-self-evolving/</link><guid isPermaLink="true">https://minbook.dev/en/blog/ralph-loop-beyond-self-evolving/</guid><description>From ALAS to Self-Evolving Agents to Multi-Agent Swarms. What comes after Ralph Loop, and what it means for the people building with AI.</description><pubDate>Tue, 31 Mar 2026 00:00:00 GMT</pubDate></item><item><title>The Ralph Loop Implementation Guide — From a Bash One-Liner to Cross-Model Review</title><link>https://minbook.dev/en/blog/ralph-loop-implementation-guide/</link><guid isPermaLink="true">https://minbook.dev/en/blog/ralph-loop-implementation-guide/</guid><description>Technical breakdown of the Ralph Loop&apos;s internals: file-based state persistence, stop hooks, cross-model worker-reviewer architecture, and three practical examples beyond just coding.</description><pubDate>Tue, 31 Mar 2026 00:00:00 GMT</pubDate></item><item><title>The Evolution of AI Agent Loops — From RLHF to Ralph Loop</title><link>https://minbook.dev/en/blog/ralph-loop-why-context-rot/</link><guid isPermaLink="true">https://minbook.dev/en/blog/ralph-loop-why-context-rot/</guid><description>Tracing the lineage of autonomous agent loop architectures: from reinforcement learning and RLHF, through ReAct and Reflexion, to the Ralph Loop — and the context rot problem that made each transition necessary.</description><pubDate>Tue, 31 Mar 2026 00:00:00 GMT</pubDate></item><item><title>2027 AI Market Scenarios — Where Does the $660B Go?</title><link>https://minbook.dev/en/blog/ai-market-2027-scenarios/</link><guid isPermaLink="true">https://minbook.dev/en/blog/ai-market-2027-scenarios/</guid><description>We analyze three possible futures (Bull, Base, Bear) from the hyperscalers&apos; $660B CapEx and present survival strategies for each scenario.</description><pubDate>Mon, 30 Mar 2026 00:00:00 GMT</pubDate></item><item><title>The Structural Problem of AI SaaS -- What a 40% GRR Really Means</title><link>https://minbook.dev/en/blog/ai-saas-grr-crisis/</link><guid isPermaLink="true">https://minbook.dev/en/blog/ai-saas-grr-crisis/</guid><description>AI-native SaaS GRR is less than half that of traditional SaaS. A structural analysis of why, and the common patterns of companies that have beaten the churn curve.</description><pubDate>Mon, 30 Mar 2026 00:00:00 GMT</pubDate></item><item><title>GEO Agency and Consulting Market Overview</title><link>https://minbook.dev/en/blog/geo-agency-consulting-market/</link><guid isPermaLink="true">https://minbook.dev/en/blog/geo-agency-consulting-market/</guid><description>Key players, specializations, and service models in the GEO agency and consulting market.</description><pubDate>Mon, 30 Mar 2026 00:00:00 GMT</pubDate></item><item><title>South Korea&apos;s AI Market Today — Where to Double Down, Where to Rethink</title><link>https://minbook.dev/en/blog/korea-ai-market-diagnosis/</link><guid isPermaLink="true">https://minbook.dev/en/blog/korea-ai-market-diagnosis/</guid><description>Two months after the AI Basic Act took effect, we analyze the structural strengths and weaknesses of South Korea&apos;s AI market — identifying the areas with real competitive edge and the traps to avoid.</description><pubDate>Mon, 30 Mar 2026 00:00:00 GMT</pubDate></item><item><title>How AI Frameworks Make Money -- LangChain, LlamaIndex, CrewAI</title><link>https://minbook.dev/en/blog/ai-framework-monetization/</link><guid isPermaLink="true">https://minbook.dev/en/blog/ai-framework-monetization/</guid><description>LangChain, LlamaIndex, and CrewAI are all free. So where does the money come from? A comparison of three open-source AI framework monetization strategies, why frameworks can&apos;t charge directly, and patterns solo builders can learn from.</description><pubDate>Sun, 29 Mar 2026 00:00:00 GMT</pubDate></item><item><title>NVIDIA Tax — How GPUs Capture Most of AI&apos;s Profits</title><link>https://minbook.dev/en/blog/nvidia-tax-gpu-profit-structure/</link><guid isPermaLink="true">https://minbook.dev/en/blog/nvidia-tax-gpu-profit-structure/</guid><description>Dissecting the $24,680 profit per H100 GPU, analyzing how NVIDIA&apos;s monopoly impacts the AI ecosystem, and exploring scenarios that could break the dominance.</description><pubDate>Sun, 29 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Before and After OpenClaw: How AI Market Outlook Shifted in 8 Weeks (feat. Lex Fridman Podcast vs. Noh Jungseok YouTube)</title><link>https://minbook.dev/en/blog/openclaw-before-after-ai-outlook/</link><guid isPermaLink="true">https://minbook.dev/en/blog/openclaw-before-after-ai-outlook/</guid><description>In early 2026, AI researchers said &apos;Computer use? They all suck.&apos; Two months later, the tone was completely different. A cross-analysis of two videos recorded before and after OpenClaw.</description><pubDate>Sun, 29 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Anatomy of the AI Market in 3 Layers — What the $660B Really Looks Like</title><link>https://minbook.dev/en/blog/ai-market-3-layer-anatomy/</link><guid isPermaLink="true">https://minbook.dev/en/blog/ai-market-3-layer-anatomy/</guid><description>Breaking down the AI market into infrastructure, platform, and application layers. A data-driven analysis of actual market size, revenue structures, and key players in each layer.</description><pubDate>Sat, 28 Mar 2026 00:00:00 GMT</pubDate></item><item><title>GEO SaaS Landscape — Profound, Scrunch, Peec and 10 More Players</title><link>https://minbook.dev/en/blog/geo-saas-landscape/</link><guid isPermaLink="true">https://minbook.dev/en/blog/geo-saas-landscape/</guid><description>A comprehensive comparison of major GEO (Generative Engine Optimization) SaaS players by funding, features, and positioning.</description><pubDate>Fri, 27 Mar 2026 00:00:00 GMT</pubDate></item><item><title>SEO Ecosystem vs GEO Ecosystem — Value Chain Comparison</title><link>https://minbook.dev/en/blog/seo-geo-ecosystem-value-chain/</link><guid isPermaLink="true">https://minbook.dev/en/blog/seo-geo-ecosystem-value-chain/</guid><description>Comparing SEO and GEO ecosystems across six layers: infrastructure, analytics, optimization tools, agencies, education, and media.</description><pubDate>Thu, 26 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Why We Made It Open Source -- The Case Against Closing a Checklist</title><link>https://minbook.dev/en/blog/why-open-source/</link><guid isPermaLink="true">https://minbook.dev/en/blog/why-open-source/</guid><description>Why we released the SaaS launch checklist as an MIT open-source CLI instead of a paid web dashboard. The comparison of 3 alternatives, the What/How/Auto revenue model design, and the explicit validation criteria we set.</description><pubDate>Wed, 25 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Where the 534 Items Came From</title><link>https://minbook.dev/en/blog/where-534-items-came-from/</link><guid isPermaLink="true">https://minbook.dev/en/blog/where-534-items-came-from/</guid><description>How 7 bullet points from WICHI&apos;s launch delays grew into a 534-item, 15-category SaaS launch checklist. The full story of collection sources, classification criteria, category design principles, and why the number settled at 534.</description><pubDate>Tue, 24 Mar 2026 00:00:00 GMT</pubDate></item><item><title>The Code Was Done, But Everything Else Wasn&apos;t</title><link>https://minbook.dev/en/blog/code-done-rest-not/</link><guid isPermaLink="true">https://minbook.dev/en/blog/code-done-rest-not/</guid><description>We built an MVP in 3 days with AI coding tools, but launch took 3 more weeks. Here&apos;s the full list of everything we missed outside the code, and how it led to an open-source checklist project.</description><pubDate>Sat, 21 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Prototype to Production — The Complete Change List</title><link>https://minbook.dev/en/blog/prototype-to-production-changes/</link><guid isPermaLink="true">https://minbook.dev/en/blog/prototype-to-production-changes/</guid><description>Ten categories of changes when transitioning a GEO SaaS from a 3-day hackathon MVP to a commercial product.</description><pubDate>Thu, 19 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Jocoding Hackathon Build Log — Building a GEO SaaS in 3 Days</title><link>https://minbook.dev/en/blog/jocoding-hackathon-geo-saas/</link><guid isPermaLink="true">https://minbook.dev/en/blog/jocoding-hackathon-geo-saas/</guid><description>Timeline record of building the WICHI GEO SaaS MVP during the Jocoding Hackathon — tech stack decisions, daily progress, and submission.</description><pubDate>Tue, 17 Mar 2026 00:00:00 GMT</pubDate></item><item><title>AI Search Engine Comparison: ChatGPT Search, Perplexity, AI Overviews</title><link>https://minbook.dev/en/blog/ai-search-engine-comparison/</link><guid isPermaLink="true">https://minbook.dev/en/blog/ai-search-engine-comparison/</guid><description>A data-driven comparison of ChatGPT Search, Perplexity, and Google AI Overviews — examining search mechanisms, citation formats, and brand exposure patterns.</description><pubDate>Sun, 15 Mar 2026 00:00:00 GMT</pubDate></item><item><title>GEO Definition and Structural Differences from SEO</title><link>https://minbook.dev/en/blog/geo-definition-seo-difference/</link><guid isPermaLink="true">https://minbook.dev/en/blog/geo-definition-seo-difference/</guid><description>What is GEO (Generative Engine Optimization), and how does it structurally differ from traditional SEO? A six-dimensional comparison analysis.</description><pubDate>Sat, 14 Mar 2026 00:00:00 GMT</pubDate></item><item><title>LLM-as-Judge — Evaluating AI Responses with AI</title><link>https://minbook.dev/en/blog/llm-as-judge-pattern/</link><guid isPermaLink="true">https://minbook.dev/en/blog/llm-as-judge-pattern/</guid><description>Practical experience applying the LLM-as-Judge pattern to evaluate AI search responses: evaluation dimensions, bias mitigation, judge reliability, and where the pattern fails.</description><pubDate>Fri, 13 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Lemon Squeezy vs Stripe — A Korean Solo SaaS Builder&apos;s Comparison</title><link>https://minbook.dev/en/blog/lemonsqueezy-vs-stripe-korea/</link><guid isPermaLink="true">https://minbook.dev/en/blog/lemonsqueezy-vs-stripe-korea/</guid><description>Comparing Lemon Squeezy and Stripe from the perspective of a Korean solo operator building a global SaaS product.</description><pubDate>Thu, 12 Mar 2026 00:00:00 GMT</pubDate></item><item><title>After Hackathon Rejection — Pivoting to Independent SaaS</title><link>https://minbook.dev/en/blog/hackathon-rejection-saas-pivot/</link><guid isPermaLink="true">https://minbook.dev/en/blog/hackathon-rejection-saas-pivot/</guid><description>Decision-making process after Jocoding Hackathon elimination: analyzing rejection causes, evaluating options, and executing same-day pivot to independent SaaS.</description><pubDate>Wed, 11 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Lovable to Vercel — Frontend Migration Record</title><link>https://minbook.dev/en/blog/lovable-to-vercel-migration/</link><guid isPermaLink="true">https://minbook.dev/en/blog/lovable-to-vercel-migration/</guid><description>How and why we migrated WICHI&apos;s frontend hosting from Lovable to Vercel in 2.5 hours, gaining Git-first workflow and production-grade deployment control.</description><pubDate>Tue, 10 Mar 2026 00:00:00 GMT</pubDate></item><item><title>n8n&apos;s Fair-code Experiment — Neither Open Source Nor Proprietary</title><link>https://minbook.dev/en/blog/n8n-fair-code-experiment/</link><guid isPermaLink="true">https://minbook.dev/en/blog/n8n-fair-code-experiment/</guid><description>n8n publicly shares its source code while restricting commercial resale through Fair-code licensing. How does it differ from MIT, why did n8n make this choice, and what can we learn from the license-change histories of Elastic, MongoDB, and HashiCorp? A full spectrum analysis of open source licensing strategy.</description><pubDate>Mon, 09 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Open Source License Selection Guide — MIT vs Apache vs Fair-code vs Additional Clauses</title><link>https://minbook.dev/en/blog/oss-license-selection-guide/</link><guid isPermaLink="true">https://minbook.dev/en/blog/oss-license-selection-guide/</guid><description>MIT, Apache 2.0, AGPL, BSL, Fair-code, SSPL: comparing what each open source license permits and restricts, then presenting a decision framework based on project scale and business model. Includes the decision process behind MMU&apos;s choice of MIT.</description><pubDate>Sun, 08 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Solo SaaS Security — The Minimum You Must Do</title><link>https://minbook.dev/en/blog/solo-saas-security/</link><guid isPermaLink="true">https://minbook.dev/en/blog/solo-saas-security/</guid><description>Five OWASP Top 10 vulnerabilities relevant to solo SaaS, environment variable management, dependency auditing, rate limiting, CORS, and CSP. A minimum security checklist built from items missed during WICHI&apos;s launch.</description><pubDate>Sat, 07 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Build, Document, Share — The Minbook Manifesto</title><link>https://minbook.dev/en/blog/hello-minbook/</link><guid isPermaLink="true">https://minbook.dev/en/blog/hello-minbook/</guid><description>Personal execution notes from a non-tech AI builder. Why another blog, what&apos;s covered, and who gets the most out of these notes.</description><pubDate>Wed, 04 Mar 2026 00:00:00 GMT</pubDate></item></channel></rss>