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.
Check Portuguese and English brand claims for location, service area, language, delivery, and enquiry conditions using an explicit regional evidence matrix.
Peter Yang tests Grok Bot with X research, an agent email address, proactive reports, creative work, and paid-community support. Here are ten workflows, two visible limits, and the access and approval details that matter.
Matthew Berman tests Meta Muse Wonder and Wonder Full on a Rubik's Cube, a game, and 3D scenes. Compare the actual demos, early quota trouble, official access and prices, and independent benchmark context.
Build a claim-to-source map for third-party AI citations, separating observed evidence, independent judgment, outdated facts, and correction priorities.
Define the facts, uncertainty states, and approval boundaries an AI-assisted service enquiry needs before it becomes a useful human handoff.
Paul Bakaus shows Andrew Warner how Impeccable critiques AI-made sites, explores visual worlds, and edits a live local page. Follow the workflow, source links, setup caveats, and a testable design-service idea.
NetworkChuck connects Checkmk to Linux, Windows, SNMP devices, Docker, Proxmox, websites, and AI agents. Follow the actual setup path, see what it detected, and add alerts without handing an agent unrestricted control.
Duncan Rogoff tours seven open-source ArtCraft apps inspired by Photoshop, Lightroom, Premiere, After Effects, Illustrator, InDesign, and Acrobat. Compare current uses, file-format risks, project claims, and a safer switch test.
Parker Prompts builds four Jev apps with Claude Code: support triage, an image and video prompt checker, podcast clip ranking, and YC company matching. Explore the decision logic, costs, caveats, and adapted copy-ready prompts.
Track incorrect brand facts in Google AI Overviews with claim-level evidence, repair owners, severity rules, and a dated recheck trail.
Use repeated observations, stable questions, and explicit action thresholds to decide when an AI-search change deserves a source investigation or content repair.
Nate Herk tours Claude-friendly GitHub projects for video, Workspace, research, sites, apps, testing, security, and SEO. Here are all 12 source links across his 10 numbered picks, plus first tests and cost checks.
Nick Saraev asks two agents to recreate Mac Preview, one with REA and one without. See what finished first, what appeared closer, and why this is a useful demo rather than a controlled benchmark.
Riley Brown surveys Claude Motion, redesigned Projects, Haiku 5.5, Codex, Intelligent UI, Grok Bot, Google image tools, and personal agents. Here are the direct sources, access limits, demos, and rumors worth separating.
Rob Shocks tests REA against a stripped app he built. See what the agent inferred, what it did not recover, the DX-Ball evidence, and the legal and security boundaries before trying it.
Matt Wolfe reviews a crowded week of AI releases. This guide separates available tools from betas and previews, with official links, video chapters, and a practical business-idea prompt.
Andrew Warner and Corey Ganim review eight AI releases and four revenue-generating products. Here are the direct links, useful first tests, access limits, and numbers worth checking again.
Andrew Warner and Adam tour ten GitHub repos, from AnyPS5 and OpenRig to HyperFrames, text-to-CAD, and openGym. Explore direct links, useful demos, young community projects, and the limits to check before installing.
Greg Isenberg reviews Brag, Agent Reach, VoiceStudio, PPT Master, OpenRig, Free Tools, Grill Me, and Impeccable. Compare the original repos, first tests, business angles, costs, and safety checks.
Meng To uses ThreeUI, Shape, and Angle to explain his paid-app workflow: find a missing tool in daily work, build a distinct product, add APIs and payments safely, then demo it to real buyers. Includes prompts and a validation plan.
Pat Simmons tests OpenAI's Decisions API on a focus timer, Mac voice control, X feed, private-video blur, Wikipedia race, food tracker, and video edits. Here are the results, code, prompts, Jev comparison, and limits.
Duncan Rogoff shows how his scheduled Claude Code agents make an artifact, compare it with benchmarks, and record one evidence-backed lesson for the next run. Here is the guide, the three-night result, and the limits that matter.
Barry Schwartz explains why Google scraping defenses are unsettling rank trackers, what the September 2026 spam update did and did not confirm, and how to report SEO results without false precision.
Rehan-fal's MiniMax H3 LoRA turns video prompts into monoscopic 360-degree equirectangular clips. Explore a sample, the real packaging workflow, the separate Turbo Space, and the license limits that matter.
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