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 781 posts across 63 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 (137), AI Agent Architecture (72), AI Business Ideas (41), and Open Source (41). 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.
Ryan Vogel tests TypeSafe Jev on batches of 100 and 1,000 exported emails. The dashboard reports about 200 ms average latency, but quality and cost need a closer reading.
Ryan Vogel combines Grok speech-to-text with TypeSafe Jev to rank video highlights. The demo finds 11 candidates in about two seconds; here is the useful workflow and what still needs human review.
Eric Michaud tests Postiz, ChatbotX, Orca, Paperless-ngx, and God's Eye View. Here is what each project solves, what was actually demonstrated, and where self-hosting adds work.
Jay E shows how to turn raw talking-head footage into branded motion graphics with GPT-6 Astra, HyperFrames, transcription, reusable assets, and a skill that improves through review.
OpenSEO combines a self-hosted SEO dashboard, DataForSEO, MCP, and agent skills. This guide explains the real costs, Docker setup, Claude Code workflow, and security limits.
Dario Amodei proposes pacing frontier AI with embedded evaluators and coordinated safeguards. Matthew Berman asks what rival CEOs actually agree on, and who could be left out.
Andrew Warner and Michael Galpert test Meta Muse across Instagram, Messenger, WhatsApp, a cloud browser, connectors, approvals, and personalized ideas.
A ten-app stress test shows where GPT-6 Astra computer use saves real effort, where direct tools win, and how to delegate visual software safely.
Align AI product names, status labels, approval screens, and completion messages with what the system actually does and what still needs a person.
A practical software-factory blueprint for parallel coding agents: isolate work, build to explicit architecture, prove behavior with evidence, and ship through review loops.
FreeLLMAPI combines provider free tiers behind one local endpoint, with model routing, failover, coding-agent setup, media APIs, and important production limits.
Repurpose technical claims across a website, LinkedIn, email, short video, and a sales deck while preserving source context, limitations, and correction history.
Build an evidence-first testimonial workflow that checks review origin, incentives, visible text, entity identity, and Google eligibility before generating schema.
Five AI safety cases explain agentic misalignment, reward hacking, alignment faking, unintended coordination, and the controls that reduce real-world risk.
Eight creator tests show where GPT-6 Astra is useful now: app building, browser and iPhone control, video editing, meeting analysis, writing, and presentations.
Compare a short case-study video with a full walkthrough using consistent claims, separate discovery measures, production effort, and qualified enquiry evidence.
ChatGPT Images 2.5, Meta Muse, DeepSeek V4.1 Flash, new Apple hardware, data agents, creative tools, and the safety warnings behind the week's biggest debate.
A practical guide to I Have ADHD, ECC, Ponytail, HumanLayer, Codex plugins, Archify, Context Mode, Matt Pocock skills, Humanizer, and four audience projects.
Ten GPT-6 Astra workflows show what computer-using AI can do across robotics, Figma, presentations, research, mobile apps, Blender, Sheets, and product analysis.
A practical guide to Meta Muse, screen context, interview prep, Astra demos, prompt portability, agent monitoring, Omi, Apple Live Rewind, and Granola.
NetworkChuck explains why CCNA networking knowledge still matters when AI drafts configurations. Cisco confirms the v1.1 and v2.0 exam dates; here is a practical study path and the current status of Fall Into CCNA.
Steve Toth turned documented client results, public teaching, a weekly newsletter, disciplined pricing, and deliberate delegation into an inbound growth system for Notebook Agency.
Evaluate an AI-written creative brief against founder evidence, realistic scope, and unresolved decisions, with a worked example and a practical review rubric.
Prevent stale SEO advice with claim-level review dates, conflict handling, source snapshots, and clear rules for when a research agent must withhold a conclusion.
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