#ai

neurodivergent

The ADHD Developer's Guide to CLAUDE.md

CLAUDE.md is external working memory for ADHD brains. The exact config I use to stop re-asking 'what was I doing?' every session, with real before-and-after numbers.

neurodivergent

5 Claude Code Skills Every ADHD Developer Needs

Five Claude Code skills that fill specific ADHD executive-function gaps: energy-based triage, the positive-discounting counter, session resume, time-blindness scheduling, and codebase navigation.

ai building

Why Isn't ChatGPT Citing Your Website? I Tested 5 Axes on a DR 25 Site and Got 1,500 Citations

1,500 AI citations on a DR 25 site in 90 days. The 5 checks (schema, llms.txt, OpenGraph, semantic HTML, robots.txt) that decide whether ChatGPT cites you.

I Found 1,200 AI Citations Hiding in Bing Webmaster Tools

A freeCodeCamp guest post and one overlooked Bing dashboard surfaced ~1,200 Microsoft Copilot citations to my DR-25 site. Here is how to read your own.

ai building

I Audited 7 Websites for AI Citability. Here Is What Actually Predicts Citations.

I audited 7 websites for AI citability. The three predictors that actually matter: answer-first content, dateModified schema, and original data.

ai building

Why Domain Authority Is Irrelevant for AI Search (And What to Build Instead)

Domain authority has zero correlation with AI citation rates. Data from 7 audits shows why DA is the wrong metric for AI search and what to build instead.

ai building

How I Built a Claude Code Trading Bot: 36,000 Lines

I built Polyphemus with Claude Code, 4,000 lines in 6 weeks, 36,000 in 4 months. 5 principles that cut errors 84% and kept 8 bugs from losing money.

neurodivergent

Claude for ADHD: The Coding Workflow I Built for My Brain

Claude for ADHD: the 5-step coding workflow I use to beat task-initiation paralysis and context-switching every day, and how the whole system fits together.

ai building

I Made Claude Code Learn From Its Own Debugging Mistakes

Build a self-improving RAG system where Claude learns from your debugging sessions, captures insights automatically, and reflects to fix issues faster.

philosophy

I Shipped 5 Products With AI Agents. IDE Plugins Are Dead.

AI agents will replace IDE plugins in product development. Here's how I built MicroSaaSBot to prove it, and what it means for your workflow.

ai building

Build SaaS With AI Agents: 7 Days to Paying Users

How I build SaaS with AI agents in 7 days: MicroSaaSBot's 4-agent system shipped StatementSync from idea to paying users, architecture documented.

philosophy

Why Human-in-the-Loop Beats Automation

Keep humans in control when building AI security tools. Full automation sounds impressive until your reputation tanks from false positives.

ai building

Claude Code Best Practices 2026: A Field Guide

Field-tested Claude Code workflows from 36K lines of shipped production code: quality gates, multi-agent orchestration, and the patterns that actually work.

neurodivergent

I Have 73 Browser Tabs Open. ADHD Made Me a Better Architect.

Five ADHD cognitive traits mapped to real systems architecture patterns: pattern recognition, parallel processing, novelty seeking, and chaos resilience.

ai building

57 Bugs in AI-Generated Code: How I Verify Before Shipping

Verify AI code with forced evaluation and build-test-proof. Stop trusting confidence, use evidence-based completion instead.

ai building

Claude Context Management: 3-File System to Beat Compaction

Claude context management: the plan.md + context.md + tasks.md system that persists task state across compaction so Claude resumes where you left off.

ai building

My Two-Gate System for Claude Code Cut Errors 84%

Build safer Claude Code projects with a two-gate quality system. Learn the mandatory checks that catch bugs before deployment.

ai building

Reduce Claude Token Usage 60%: Progressive Disclosure

3-tier progressive disclosure cuts Claude API costs 40-60%. The exact system: tier 1 triage, tier 2 context, tier 3 full pass.

ai building

llms.txt for AI Crawlers: Why robots.txt Is Not Enough

robots.txt was built for search engines, not AI crawlers. llms.txt gives LLMs structured context about your site that robots.txt can never provide.

ai building

Get Cited by ChatGPT and Perplexity: 5 Concrete Steps

Five steps to get cited by ChatGPT and Perplexity: crawler access, llms.txt, schema markup, answer-first structure, and how to verify each worked.

ai building

Why ChatGPT Isn't Citing Your Site: 6 AEO Factors

ChatGPT and Perplexity skip most sites for six measurable reasons. The 6 AEO factors that decide which sources get cited, and how to fix each one.

ai building

RAG Explained: How to Stop LLMs From Making Things Up

RAG retrieves live data to fix LLM hallucinations. Build accurate AI apps with up-to-date knowledge sources without retraining or fine-tuning models.