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.
More than 1,300 frontier-lab employees asked the US government to build an international option for pacing automated AI R&D. The statement is not an immediate pause, and its hardest questions remain unanswered.
fal's five-day Workmander build shows a practical pattern for agentic filmmaking: Voice coordinates, one Codex thread builds, a restricted operator uses MCP, and every generation stays visible and reviewable.
A source-checked guide to AI 2040: Plan A, separating recommendation, scenario, projection, and evidence across the five paths, the US-China compute deal, verification, citizen dividends, and the assumptions behind the $13 million headline.
Andrew Warner curates the strongest Codex Voice demos across email, browser work, screen guidance, files, remote access, and iOS development. Here is the accurate product map, safer permission model, and practical setup.
Matt Wolfe reviews Claude Opus 5's split personality, Buzz's agent-native workspace, Nano Banana inside Google Earth, Meta's action-taking assistant, new creative tools, and the shift toward physical AI.
A source-checked guide to rebuilding site exploration, keyword research, content gaps, technical audits, and AI visibility with Claude Opus 5 and DataForSEO, including an organized prompt pack and the limits Semrush and Ahrefs still cover better.
Theo unpacks the NVIDIA-led open-weights letter and Anthropic's refusal to sign. Here is what the coalition actually argues, where Dario Amodei agrees, where he objects, and what builders should test before deploying open models.
AI Edge demonstrates the new ChatGPT Voice across research, local files, website iteration, screen context, and paired phone control. Here is the safer beginner setup, copy-ready brief, and seven-day rollout.
Greg Isenberg responds to the claim that software is dead. The practical answer: building is cheaper, search distribution is less dependable, and durable value has moved to niches, proprietary data, maintenance, audience, community, and agent-native outcomes.
Riley Brown and Vince Canger show how to build a practical Buzz agent team with Codex as the lead, Claude Code and other runtimes as specialists, scoped channels, review loops, mobile access, and safer recurring workflows.
Andrew Warner and Vince Canger test Buzz across agent runtimes, Wasp and Railway deployment, mobile access, Git projects, workflow triggers, shared compute, and multi-agent routing. Here is the practical operator guide.
Vaibhav Sisinty tests ChatGPT Work and Claude Cowork across projects, scheduled tasks, connectors, recorded skills, Slack, Sites, Artifacts, and local work. Here is the current, source-checked comparison.
A practical backlink strategy built around relevance, editorial value, qualified traffic, relationships, search intent, and Google-compliant paid-link handling instead of raw link counts.
The practical AEO essentials: query fan-out, brand gaps, keyword and prompt research, citation-ready content, credible mentions, YouTube, crawler policy, and measurement.
Nick Saraev combines Nano Banana Pro, Seedance 2.0, Claude Code, and Vercel to turn a short AI video into an animated dithered hero. Here is the complete pipeline, a safer build prompt, performance limits, and deployment checklist.
Greg Isenberg and Vinny tour Buzz, Block's open agent workspace. The real opportunity is portable team context across Claude Code, Codex, Goose, Git worktrees, workflows, and local compute, with important early-preview limits.
AI Search pushed Claude Opus 5 through browser software, 3D reconstruction, financial video, Blender, music, vision, medical images, and research. Here is what the tests actually prove, where the model failed, and when its cost is justified.
Anthropic's official Opus 5 prompting guidance as five practical rules: effort routing, reusable templates, verification boundaries, and a better way to test.
Alex Finn demonstrates ChatGPT Voice coordinating Work and Codex across projects, delegated threads, approvals, and paired phone access. Here is the grounded ambient-AI workflow, reusable prompts, permission model, and seven-day pilot.
Zubair Trabzada shows Claude Opus 5 orchestrating research, scripts, editorial collage visuals, charts, voice, music, and rendering through Higgsfield MCP. Here is the source-checked workflow, an original production prompt, cost controls, and the human review gates it still needs.
Theo argues that Kimi K3 has frontier labs and Washington panicking. Here is the evidence: released open weights, competitive benchmarks, distillation allegations, cyber testing, policy risk, and what builders should do next.
Cody Schneider and Greg Isenberg map a real Meta Ads agent: unified business data, research and creative pipelines, bounded API actions, and a feedback loop tied to revenue.
OpenAI Codex DevEx engineer Jason Liu runs work through durable threads, a reviewable memory vault, bounded heartbeats, reusable skills, and goals with explicit verification.
Claude can turn a narrated screen recording into a reusable skill. Here is what that changes, what Opus 5 adds, and a source-checked guide to the week's major AI releases.
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