#ai

ai building

Search Console's Generative AI Report: 3 Things It Hides

Google's Generative AI report went live for every property on August 11, 2026. No queries, no clicks, no API access. Here is my own 19.7K-impression report.

neurodivergent

CLAUDE.md as External Working Memory for ADHD Devs

The exact CLAUDE.md config that stops the 'what was I doing?' reset every session, with before-and-after numbers. Session memory in one file Claude reads automatically.

neurodivergent

Claude Code Skills for ADHD: 5 I Actually Use

Five Claude Code skills I built for specific ADHD deficits: task triage, session resume, time blindness. What each one closes, and how to build your own.

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.

Bing Webmaster Tools AI Performance: 1,200 Copilot Citations Were Hiding There

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

How to Audit Your Website for AI Citation Readiness (7-Site Study)

How to audit website content for AI citation readiness: a 7-site study of what actually predicts citations. Ahrefs (DA 92) gets cited 5% of the time; a DA-under-10 site hit 15%. Run the same checks on your site, free, before spending another dollar on backlinks.

ai building

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

You're building backlinks for a metric that doesn't matter to ChatGPT or Perplexity. Data from 7 site audits answers the real question, does site authority matter in AI citation rankings, and shows what to build instead: a DA-92 site got cited 5% of the time, a DA-under-10 site got cited 15%.

ai building

Claude Code Trading Bot: 36,000 Lines, 1-in-40 Error Rate

Unverified Claude Code output loses real money once it touches live capital. This claude code trading bot case study shows the two-gate system that cut errors 84% and caught 8 bugs before they cost a dollar.

neurodivergent

Claude for ADHD: There's No Plugin, Here's My Workflow

No, Claude has no built-in ADHD mode or plugin. The 5-step workflow I use instead to beat task-initiation paralysis and context-switching.

ai building

Self-Improving RAG with Claude Code: Learning 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

AI-First Product Development: 5 Products Shipped With Agents, Not IDE Plugins

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

Founders burn weeks on the idea-to-launch grind before knowing if anyone will pay. MicroSaaSBot's 4-agent system compresses that to 7 days: StatementSync went from problem statement to paying users, architecture documented.

philosophy

Human-in-the-Loop AI: Why It Beats Full Automation for Security Tools

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: What the Official Docs Don't Cover

Claude Code best practices for 2026, field-tested across 36K lines of shipped code: quality gates, multi-agent orchestration, and the workflows the official docs don't teach.

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

How to Test AI-Generated Code Before Shipping: 57 Bugs Caught

How to test AI-generated code before shipping it: the evidence-based verification gates that caught 57 bugs. Forced evaluation beats "it should work", 84% compliance vs 20% for passive checks.

ai building

Claude Code 'Compaction Failed': Why Context Loss Happens

Getting Claude context management wrong looks like 'compaction failed.' Here are the 3 fixes: plan.md, context.md, tasks.md, the files that survive compaction.

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

Yes, ChatGPT, Claude, and Perplexity can crawl your site: here are the exact crawler user-agents to allow in robots.txt and how to verify it worked.

ai building

How ChatGPT and Perplexity Decide Which Sources to Cite

The six measurable factors answer engines use to pick sources, with 2026 platform data on how ChatGPT and Perplexity actually cite, 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.