Blog
Articles on AI development, LLMO, context engineering, and harness engineering.
2026 56 posts
- AI Search Is Under 1% of My Traffic and 12% of My Signups. That's the LLMO Case I Actually Use.
- GEO's +115% From Statistics Is Domain-Dependent: It Worked for My Tech Posts and Did Nothing for My How-To Pages
- AI Reads Your Chunks, Not Your Page: I Promoted 9 Sections from H3 to H2 and Watched Which Ones Got Quoted
- I Wired Claude Code to Real Hardware Over USB Serial. The MCP Tool Was the Easy Part.
- I Checked What GPTBot Actually Sees on My JS-Rendered Pages. It Was an Empty `<div>`.
- AI Wrote 100 Passing Tests. Mutation Testing Says They Caught 58% of Real Bugs.
- AI Finds Your Page Three Ways. I Published the Same Fact in All Three and Timed Which Reached AI First.
- I Priced AI Agents Three Ways: API, Subscription, and Local. Here's Where the Break-Even Actually Sits.
- My Blog Speaks 4 Languages. AI Search Cited the Wrong One to Most of My Readers.
- I Rewrote 12 Pages to Answer the Question in the First Sentence. AI Started Quoting 7 of Them.
- I Rank #1 on Google. On Brave I'm Page 5. My Own AI Agents Can't Find Me.
- Perplexity Citations Exploded After I Changed 3 Things. Only 1 Was Schema.
- I Gave Every Page on My Site a .md Twin. The AI Fetchers Stopped Guessing
- My Best Page Went Stale in a Month: Why AI Search Rewards Freshness, Not Just Schema
- AI Search Splits Your One Question Into Six. My Pages Answered None of Them.
- I Stopped Adding Context to My Agent and Pruned Tool Outputs Instead — My 3-Hour Task Stopped Forgetting Its Own Plan
- AI Citations Have a Half-Life. I Tracked Mine for 9 Weeks and Watched Them Decay.
- I Mapped My Codebase as a Graph. The File That Broke Was Two Hops Away.
- Link-less Brand Mentions Beat Backlinks for AI Visibility — I Read the Ahrefs 75,000-Brand Study So You Don't Have To
- Your Page Rank Is Invisible to AI — Only Your Passages Get Cited
- I Crosspost to 4 Platforms with rel=canonical Pointing Home. AI Search Still Picks the Copy.
- Claude Code Skills Cost Tokens Even When They Don't Fire. I Measured 5 Skills Across 7 Hours. The Bill Was 18%.
- I Cron-Scheduled 7 AI Agents. 2 Silently Failed for 18 Days. Tracing Wouldn't Have Caught It.
- I Ran 3 Claude Code Sessions in Parallel for 8 Hours. They Overwrote Each Other's Context Twice.
- I Asked 5 AI Search Engines to Cite My Own Blog. Only 3 of 31 Articles Showed Up.
- I Added 11 JSON-LD Schemas. Three Months Later, Only 3 Showed Up in AI Citations.
- I Refactored 100 Functions With Claude. 7 Got Slower in Production.
- I Told Claude Code to Do TDD. It Wrote the Test AFTER the Code 6 Out of 10 Times.
- I Added a 4th Agent That Audits My Other Agents. It Caught My Strategist Procrastinating for 3 Weeks.
- I Translated My Blog Into 4 Languages. Portuguese Got Nearly 4× the Traffic of English.
- TRM's 8,337% LLMO Playbook on Indie Sites: Only 1 of 4 Pillars Worked
- Claude Said 'You're Absolutely Right!' 47 Times Last Week. I Was Only Right 11 Times. Claude Was Wrong 36.
- I Plugged the Same Site Into 7 AI-Citation Trackers. They Reported 7 Different Numbers.
- The 5 AI Crawlers That Hit My Sites Most in 30 Days — What Their Logs Told Me About LLMO
- I Plugged Claude into a Chaos Engineering MCP Server. It Killed Staging 4 Times Before Finding a Bug We'd Missed for 6 Months.
- I Caught Claude Hiding My Bug 3 Times in a Row. Then I Turned 10 Debugging Habits Into Prompts.
- I Gave My Strategist Agent WebSearch. 5 Topics Took 20 Minutes. Splitting It Into 3 Made It 3.
- I Benchmarked 5 Voice AI Stacks. Only 2 Stayed Under 300ms.
- 3 Claude Code Sub-agents Reviewed One PR — They Disagreed on 40%
- I Audited 30 llms.txt Files in the Wild. 5 Anti-Patterns Are Already Forming.
- OpenClaw Hit 250K Stars Faster Than React. I Spent a Day Switching From Claude Code
- I Refused to Write Specs Until Claude Code Generated Wrong Code Three Times
- I Let My Claude Code Agent Run for 24 Hours. The $400 Bill Was the Least Scary Part.
- The og:type Bug Three of My Astro Sites Quietly Shipped
- I Stacked 4 More Context Layers on Top of RAG. The Improvement Was 12%.
- arXiv's 'Natural-Language Agent Harnesses' (2603.25723): The Word I'd Been Missing
- Claude Code Skills: The Reusable Workflow That Replaced My Commands
- Your New Domain's First Week of GA4 Is a Lie: 4 Days of Raw Data from kaoriq.com's Launch
- Claude Code vs ChatGPT Codex: Two Official Agents, One Choice You Don't Have to Make
- One Question, Five AI Search Engines, Five Different Answers
- Is AI Actually Citing Your Site? How to Measure What Google Rankings Can't
- Princeton Tested 9 Ways to Get Cited by AI. Only 3 Worked.
- 9 Bugs in My AI Pipeline: None Were the AI's Fault
- The Cheap Model That Won: Why Context Beats Parameters
- llms.txt: The File That Decides Whether AI Can Find Your Site
- Building an Autonomous Content Pipeline with Claude Code