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 819 posts across 65 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 (139), AI Agent Architecture (73), AI News (48), and AI Business Ideas (46). 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.
Alejandro AO explains why DeepSeek Harness treats the agent loop, tools and prompts as plugins. Learn the Cordis model, reproduce a small web plugin and understand the trust boundary.
NetworkChuck shows Herdr panes, tabs, agent notifications, remote SSH sessions and cross-agent work. Choose the right Herdr edition, install it safely and understand what survives a restart.
Duncan Rogoff ranks seven Claude Desktop updates. See why split view, side chats, nested sessions and a cross-session check are his four to use now, with access and usage limits checked against Anthropic.
Paul J Lipsky shows how a non-coder can set up Google Antigravity, build a small app and try games and motion. Follow a safer first-project path, with official settings and a copyable visual-quality brief.
Futurepedia tours Claude Desktop’s new Home and Code layout, artifacts, session rail, Remote Control, parallel work and mods. Use this practical map to choose a workflow and check the rollout limits.
Jordan Urbs cancelled a $200 Claude plan and tested OpenCode with Venice. Separate his estimated token bill from actual costs, examine privacy modes, and run a small portability test before switching.
ByteGrad tests Cline Desktop with Kimi and DeepSeek. Follow a source-checked setup for ClinePass, Kimi K3.1 Pro and DeepSeek V4.1 Flash, then try Git worktrees, review and schedules safely.
David Ondrej explains his high-volume AI coding workflow: one task per thread, risk-based review, selective sub-agents, cloud workspaces and agent loops. Here is what to borrow and what to verify before shipping.
Vaibhav Sisinty tours 14 Claude features for non-coders, from research, Projects and artifacts to the Code tab, mods, commands and parallel sessions. Start here and check plan limits first.
Paul J Lipsky shows Claude Code as a practical workspace for non-developers. Start with one small app, then understand Projects, local data, phone access and the permissions that matter.
AI Labs tests Google's open-source Elephant-Goldfish Model on a fashion app. Learn the real Claude Code and Codex install commands, the five-stage workflow, the drift bug it found, and when this much review is worth the cost.
Ben AI tours Claude Code Desktop projects, side chats, split view, artifacts, slash commands and mods. See the seven demos, official access rules, chapter links and three deeper videos.
DevOps trainer Rob Bos explains why coding agents need sound prompts, tests, review capacity and systems thinking. Check the six-month learning claim, developer survey and token-footprint limits.
AI engineer Florian Buetow tests whether fast feedback, Semgrep rules, architecture tests, and agent hooks can ease code-review pressure without surrendering human ownership of software.
At Rails World 2026, DHH explains why 37signals went pencils down, shows agent-built HEY experiments, makes the case for Rails conventions and app CLIs, and argues for optimism with eyes open to production risks.
Carlos Kelkboom explains why he scaffolds architecture before delegating code, keeps his main agent read-only, compares parallel implementations in worktrees, and discards code he cannot explain.
The scripts and routine behind this site's jump from 38 to 116 Google clicks a day: Search Console and GA4 in Claude Code, IndexNow, sitemap checks, and checkpoints.
AI Search surveys passthrough game mods, Rust engine recreations, and mechanics ports. This guide checks the 99.2% benchmark claim, maps the real tools, and separates demos from playable, publishable work.
Ray Amjad explores Jev as a fast decision layer for Claude Code and Codex: skill suggestions, browser checks, comment triage, code review, and a measured build-test-fix loop.
Dubibubi reports up to 91.75% lower Codex usage and demonstrates a 33.3% reduction. Here are the eleven rules, what they change, and how to test them fairly.
Andrew Warner and Matt Pocock explain how Grill Me, specs, tickets, implementation, and review make coding-agent work portable and reliable.
Greg Isenberg's sponsored Claude Code workflow rebuilt with repo context, Plan Mode, tickets, preview, layered review, routines, worktrees, and permission tiers.
Matt Wolfe built a 3D roguelite with Claude Code, then refined it with Codex. The useful lesson is where AI compressed implementation and where design, testing, balance, and judgment still dominated.
Muse Code and Muse Spark 1.2 are exceptionally fast and cheap. Theo's test reveals the data tradeoff, rate limits, strong PR triage, and weak long tasks.
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