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 699 posts across 62 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 (132), AI Agent Architecture (65), AI Tools (38), and Open Source (37). 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.
Three hands-on creator tests compare GPT-5.6 Sol with Claude Fable 5 across coding, creative builds, API reliability, speed, and cost. Here is the practical model-routing guide.
OpenAI introduced ChatGPT Work, an agentic work surface for apps, files, local projects, browser use, Computer Use, Sites, Appshots, scheduled tasks, and GPT-5.6-powered deliverables.
OpenAI launched GPT-5.6 for Codex and ChatGPT Work. Here is the builder read on Sol, Terra, Luna, max and ultra reasoning, Programmatic Tool Calling, subagents, and the new Codex work operating system.
An AI mention can start discovery, but buyers still need factual consistency, independent proof, risk clarity, human accountability, and a safe next step.
Structured data can describe a page, but it cannot repair a brand whose copy, images, video, proof, and profiles tell different stories. Use this consistency workflow.
OpenAI introduced GPT-Live, a full-duplex voice model now powering ChatGPT Voice. Here is what changed, what builders should test, where the limits are, and how it connects to voice agents.
Griffin Wooldridge shows how to connect Mobbin MCP to Claude Code so AI agents can research real shipped UI screens before designing. Here is the practical workflow for Claude, Cursor, Codex, and AI web design.
Grok 4.5 for coding and agentic work: benchmarks, pricing, token efficiency, Grok Build, Cursor support, EU availability, and when it beats Fable, Opus or GLM.
Andrew Warner and Cathryn Lavery test Paper, an agent-native design canvas controlled by Claude Code, Fable 5, Codex, and MCP. Here is what works, what still needs taste, and when Paper beats chat-only design.
Dan Martell ranks 14 ways to make money with AI in 2026. Here is the practical JQ AI SYSTEMS version: which models are durable, which are crowded, which are risky, and how to validate an AI chief-of-staff offer before building it.
Nate Herk gave Claude Fable 5 one goal prompt and got a product, landing page, videos, business plan, market research, and brand package. Here is the practical builder lesson: goal design, subagents, verification, and human validation.
Nate Herk shows how to keep Fable 5-style process after access changes: turn good runs into skills, use effort levels deliberately, and route cheaper models to the work they can handle.
A practical architecture for turning one niche into vetted keywords, SERP-based decisions, topic clusters, content briefs, and an internal-link map with Agent A and Ahrefs data.
AI can multiply drafts, but useful authority still comes from evidence, experience, boundaries, and judgment. Here is a repeatable expert-POV publishing workflow.
Andrew Warner and Jon Cheney react to Dan Martell's AI business list. Here is the practical JQ AI SYSTEMS version: what is worth building, what is hype, and where beginners should be careful.
Fable 5 generating 25 visual websites with sub-agents, tools, deployment, and review loops. The practical version: design the prompt, then sell the human layer.
Crawl access, index eligibility, citations, mentions, referrals, branded demand, and conversions answer different questions. Use this diagnostic metric model.
Calum Johnson interviews John Hu of Stan on building an audience that buys, creator monetization, Stanley AI, digital products, and the practical path from posting consistently to making the first online sale.
A client AI mockup can reveal taste and ambition, but it has not solved the audience, brand, feasibility, accessibility, budget, content, or conversion problem.
Cloudflare now lets site owners separate Search, Agent, and Training traffic. Here is how a small brand should use that split without accidentally cutting off discovery.
Natalie Dawson interviews JD Ross on Opendoor, WithCoverage, AI, insurance, and why operators with real domain expertise may have the best shot at building useful AI businesses.
Dan Martell shares 40 AI productivity truths. Here is the practical JQ AI SYSTEMS version: tighter context, better examples, voice input, review loops, finished workflows, owned agents, and AI adoption that actually moves business metrics.
AI visibility is no longer only a rankings question. Here is the weekly operating system small brands can use to track citations, branded demand, proof pages, and assisted conversions.
AI agents are hitting websites in larger volumes, but many businesses still cannot tell whether that traffic helps discovery, extracts value, or impersonates trusted names.
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.
Your recording is emailed to me and kept on this site's server for 12 months, then deleted. Privacy policy.
Thanks for your voice message. I listen to every one myself and I will get back to you within one business day.
Explore João's services and public work, or arrange a free 30-minute consultation.
Choose a time with Cal.com. Your booking status is shown there. No calendar details are shared with this assistant.
Open booking in a new tabWhen enabled, each question is processed by Cloudflare AI and checked for abuse with Turnstile. No chat history is stored by this app. Please leave out private information.
Prepared answers · Public information