Every case study, system breakdown, and field note, newest first and filterable by topic. No theory, no demos. Only systems that run in production and what it took to get them there.
This is the complete archive: all 478 posts across 52 topics, newest first, filterable by category. It holds the case studies, the model and tool comparisons, and the field notes from systems I built and run. For the curated view, where the writing sits alongside the free Claude Code skills, start at the Library instead.
The archive leans in four directions: AI Search Visibility (95), AI Agent Architecture (58), AI Tools (38), and AI Coding Agents (26). Those four account for most of what I publish, because they are where most of the client questions land.
Three places to start. The AI search visibility guide is the hub for the largest cluster and links out to every spoke in it. Grok Imagine vs Midjourney is the image model comparison, rebuilt against live leaderboard data rather than left to go stale. OutreachIQ is the longest running system breakdown here, from first prototype through to a public repo.
The current branding backlash is not anti-AI. It is anti-defaults. Here is why AI-assisted brand refreshes need stronger constraints if they want to stay distinctive.
The reaction videos around Anthropic disabling Fable 5 and Mythos 5 are useful, but they mix confirmed facts, capability shock, and speculation. Here is the practical builder read.
Anthropic says a U.S. directive forced it to disable Fable 5 and Mythos 5 for all customers. Here is what builders should learn about fallback plans, governance, and model access risk.
A practical JQ AI SYSTEMS roundup of The Next New Thing's June 11 GitHub Hot Repos report: last30days-skill, headroom, Open Notebook, Codex plugins, Agent-Reach, Cosmos, taste-skill, Apple container, MarkItDown, and more.
Fresh June 2026 data suggests the answer is yes, but unevenly. The better question is which users click, and what kind of page they expect when they do.
Google has now said the quiet part out loud: most AI-search “optimization†tricks are still just SEO myths with new names. Here is what actually matters.
OpenAI’s richer shopping and product-discovery experiences are an early signal: offers that are easier to compare will become easier to recommend.
A practical look at Claude Fable 5 build demos, from Lovable-style app builders and 3D games to custom productivity tools, plus the prompting patterns that make expensive agents worth using.
Content Credentials are not a direct ranking switch, but provenance is becoming more relevant as brands need traceable assets, stable facts, and better trust signals across AI-mediated surfaces.
Claude Fable 5 brings Mythos-class capability to general users with safeguards, Opus 4.8 fallbacks, higher pricing, long-horizon agentic work, and new questions for builders.
Google has launched dedicated generative AI reporting in Search Console for a subset of sites. Here is what the new report actually reveals, what it still hides, and how a small brand should use it.
Google says the average AI Mode search is triple the length of a traditional query. Here is why that changes service page strategy, and how to rewrite pages so they answer better, prove more, and convert cleanly.
Codex Sites, Cursor Canvases, DeepSeek V4 pricing, Poke in Apple Messages, Microsoft Scout, and Hermes Desktop point to the same shift: agent work is moving into super-apps and shareable work surfaces.
Which Hermes Desktop surfaces actually matter, why profiles are not security sandboxes, and what to get right before you schedule anything. Judgment, not docs.
Google has deprecated FAQ rich results for most sites. Here is what to replace old FAQ-page SEO with if you still want answer-ready pages that help humans and AI search.
Longer AI queries need fuller answers, but not bloated ones. Here is how to write for planning-style AI search without turning your pages into mush.
A public-safe prompt for building a local-first AI agent control center with Codex, Claude Code, Cursor, or another coding LLM, without exposing private data.
Google’s “Highly Cited†label is a reminder that original service content can become source material, not just marketing. Here is what that means for expert-led businesses.
Codex Sites is not just a one-prompt app builder. The real pattern is memory, safe actions, skills, save-gates, and proof loops that let agents operate internal tools.
A practical JQ AI SYSTEMS roundup of this week's hot GitHub repos suggested by The Next New Thing: MoneyPrinterTurbo, headroom, MarkItDown, Supermemory, ECC, taste-skill, VoxCPM, and more.
OpenAI's Codex role-specific plugins, Sites, and annotations show the next agent shift: packaged workflows for sales, data, creative, product, finance, and internal apps.
OpenAI is pushing Codex beyond coding with role-specific plugins, Sites, annotations, and a deeper ChatGPT path. Here is what builders and operators should understand.
Codex is now Windows-native with PowerShell and a real sandbox. What changes for sysadmins, developers, security labs, and anyone letting an agent touch a PC.
Clearer answers help AI retrieval, but brands still lose if every page sounds and looks the same. Here is how to stay machine-legible without becoming forgettable.
Every post here is about a system that actually shipped. Book a free call and let's talk about what could ship for you.
Book Free 30-min CallAdd your name and email to unlock recording.
Thanks for your voice message. I listen to every one myself and I will get back to you within one business day.