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.
Vaibhav Sisinty covers a wild AI week: Hermes Mixture of Agents, Z.ai ZCode, GLM 5.2, Meta Claude Code and Codex restrictions, Fable 5 returning, NotebookLM videos, Claude Science, Notion HTML blocks, and more. Here is the practical builder version.
As AI agents move from retrieving information to acting on a user's behalf, identity, accountability, and trust become part of the discovery infrastructure.
The Stack Overflow rebrand for the AI era points at a broader shift: in an answer-engine world, human-validated knowledge becomes part of a brand's strategic asset base.
FluidVoice runs speech models on-device: free, open source, macOS only. Setup, privacy trade-offs, how it compares to Wispr Flow, and where Windows stands.
Theo argues the Fable 5 backlash is mostly wrong. Here is the practical builder version: Fable was not simply nerfed, but routing, safety classifiers, usage limits, and cost discipline now matter more.
Albert Olgaard shows how to use Google Cloud trial credits, Gemini CLI, Vertex AI, free outreach tools, Vercel, OpenWhispr, Cap, and Stripe credits to start a tiny AI service business without heavy subscriptions.
Nate Herk shows how to turn YouTube transcripts, PDFs, URLs, meetings, and notes into a cross-linked LLM wiki that Claude Code, Fable 5, Codex, Hermes, and other agents can reason over.
Riley Brown connects Claude Fable 5 returning, OpenAI GPT-5.6 entering limited preview, Sonnet 5, Cursor for iOS, model rerouting, and the shift from selling apps to selling agents. Here is the practical builder read.
Brand assets and design systems are not only visual deliverables anymore. They help AI systems connect identity signals, content surfaces, and machine-readable consistency across the web.
A practical JQ AI SYSTEMS roundup of The Next New Thing's July 3 GitHub Hot Repos report: AI Berkshire, SimpleX Chat, OpenMontage, design.md, codebase-memory-mcp, no-mistakes, ai-website-cloner-template, lingbot-map, free-for-dev, Orca, plus our own GitHub picks.
Andrew Warner and Corey Ganim break down 16 AI launches from The Next New Thing: NotebookLM Short Video Overviews, June, xAI Voice Agent Builder, BoringMarketing, open Slack agents, Arena42, Fable 5, Cursor iOS, OpenClaw mobile, Gemini Spark, Hermes context usage, and more.
Ras Mic breaks down how he thinks about system design when building AI-generated apps. Here is the practical JQ AI SYSTEMS version: monorepos, client-server boundaries, durable workflows, service isolation, observability, auth, payments, and agent-friendly infrastructure.
Google and Bing now expose first-party AI visibility data, but they do not measure the same thing. Here is how to read the conflict without over-trusting either platform.
Robert Greene tells Calum Johnson that AI changes the tools, but not the power game. Here is the practical JQ AI SYSTEMS version: create dependence, build rare judgment, use AI as leverage, and stay useful when work gets automated.
Chris Camillo and The Calum Johnson Show make the case for social arbitrage in the AI era. Here is the practical, non-hype version: use AI to spot behavior change, map it to companies or business ideas, and validate before you bet.
Fable 5 is back with limits, credits, and stronger safeguards. Here is the practical playbook: code review, UX walks, business strategy, security loops, MCPs, and prompts worth spending Fable on.
A practical digital PR operating system for reactive commentary, proactive data campaigns, journalist research, responsible outreach, survey methodology, measurement, and AI-assisted work with human judgment.
The useful question is no longer whether AI bots exist. It is which ones create discovery value, which ones help users act, and which ones mostly extract value from your site.
Anthropic says export controls on Claude Fable 5 and Mythos 5 were lifted, and Fable 5 returns globally on July 1. Here is what changed, what builders should test, and why fallback handling still matters.
The strongest AI-era brands are not the ones that perform machine-made effortlessness. They are the ones that use AI carefully while keeping human taste, judgment, and strategic authorship visible.
Andrew Warner interviews Matt Symes of Levership on AI outreach workflows that use Perplexity Computer, Model Council, OSINT dossiers, warm collisions, and meeting prep to find better prospects without generic cold email.
Ras Mic and The Calum Johnson Show walk through the fastest practical way to use AI agents in business and content: connect the right tools, coach one useful run, turn it into a skill, and automate the repeat.
A plain walkthrough of the free 30-minute AI consultation: what it is, what it is not, how to prepare, what happens minute by minute, and what you walk away with, whether or not you ever hire anyone.
Chris Koerner interviews Caleb Panza on how Post For Me crossed $10K MRR with no big audience: transparent MRR updates, customer-question SEO, AI-search visibility, pricing, churn, and the lean SaaS stack behind it.
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