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.
Nate Herk argues that Claude skills only matter if you can diagnose business constraints, tie work to KPIs, and prove results. Here is the practical JQ AI SYSTEMS playbook.
An integrity graph is the layer that connects your brand facts, services, proof, and entity relationships into something AI systems can understand without guessing. Here is why that now matters for AI search visibility.
A practical JQ AI SYSTEMS roundup of this month's GitHub Trending repos: MoneyPrinterTurbo, Understand Anything, MarkItDown, CodeGraph, Agent-Reach, DeepSeek-Reasonix, and more.
AI search often expands one query into many sub-queries before it decides what to cite. Here is how to plan a service page around query fan-out instead of only one keyword.
A practical JQ AI SYSTEMS roundup of this week's GitHub Trending repos: codebase-memory-mcp, Agent-Reach, OpenMontage, SkillSpector, agent-skills, TimesFM, Flue, Penpot, Plane, and more.
Google's Preferred Sources and Highly Cited signals push in the same direction: the brands that win will be the ones worth citing first, not the ones publishing the most generic content.
A practical JQ AI SYSTEMS roundup inspired by David Blank: Framer 3.0 agents, BuildVision, Ploy, Palmier, shadcn, AI SDK, Prime Intellect, EmbedPDF, and the workflow-design stack behind useful AI products.
A practical JQ AI SYSTEMS weekly radar on Fable/Mythos access risk, GLM 5.2, Facebook AI tools, Midjourney Medical, Codex Record & Replay, Claude Design, Perplexity Brain, Adobe, Google Ad Manager, and AI adoption data.
OpenAI Codex Record & Replay lets you show Codex a repeated workflow and turn it into a reusable skill. Here is what it changes, where it works, and what builders should record first.
Andrew Warner and Hiten Shah reviewed real AI businesses making money. The lesson is clear: AI makes products easier to build, but distribution, margins, churn, and deployment still decide who wins.
A practical JQ AI SYSTEMS guide to 12 Claude skills for vibe coders, with credit to Lead Gen Man, plus five GitHub trending repos for agentic video, voice, cybersecurity, memory, and coding workflows.
ChatGPT and Google AI Overviews do not seem to use the same third-party sources in the same way. Here is why your proof strategy should reflect that difference.
A practical builder roundup of Claude Code ads, Firecrawl web access, NewsJack PR agents, Midjourney Medical, Headroom token compression, Grok Imagine, and GLM 5.2.
GLM 5.2 can be routed into Claude Code through Z.AI. Here is what changed, the config to use, where it may beat Opus on cost, and what builders should test first.
SpaceX reportedly buying Cursor is less about one code editor and more about the race to own the general agent workspace. Here is what builders should watch, test, and migrate carefully.
As AI agents merge public pages with private documents and connected tools, your website is no longer competing only against other websites. It is also competing with the user’s own context.
A practical JQ AI SYSTEMS roundup of The Next New Thing's June 18 GitHub Hot Repos report: OpenCut, Apple container, SkillSpector, agent-skills, pm-skills, Agent-Reach, Headroom, system prompt leaks, and more.
Reviews are no longer only a reputation asset. As AI systems summarize and recommend businesses, review freshness, detail, and consistency are becoming part of the visibility layer too.
Anthropic studied 400,000 Claude Code sessions and found that domain expertise matters more than traditional coding experience. Here is what builders and small teams should learn.
If brand is the new backlink for AI search, the real work is not vague awareness. It is clearer identity, stronger proof, better entity consistency, and more distinctive pages.
AI can speed up branding work, but weak briefs often produce machine-made identity mush. Here is how to brief an AI-assisted rebrand without flattening the brand.
Your website now has a second audience: AI agents acting on behalf of buyers. Here is how to make a site easier for agents to interpret without flattening the brand for humans.
Once AI visibility becomes reportable, the strategic question changes. Not “are we visible?†but “which pages deserve that visibility first?â€
The Fable 5 access pause is a reminder that cloud AI is rented intelligence. Local models give builders a private, offline, resilient fallback layer for everyday work.
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.