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 342 posts across 39 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 (72), AI Agent Architecture (51), AI Tools (27), and AI Coding Agents (20). 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.
Futurepedia demonstrates how Claude Design can turn prompts, reference images, design systems, and timestamped transcripts into editable motion graphics. Here is the practical workflow, prompt, QA process, and beta caveats.
Theo traced T3 Code's idle GPU load to infinite status animations interacting with a fixed noise overlay. Here is why Fable and GPT-5.6 guessed wrong, what the final patch changed, and a better AI-assisted debugging workflow.
Vaibhav Sisinty routes free model tiers through OmniRoute and Claude Code. Here is what is truly free, what leaves your laptop, which routes raise terms concerns, and a safer setup.
Andrew Warner and Mike Bradley install ODS on Windows. Here is what the local AI stack includes, what stays private, the real hardware tiers, and a safer setup path.
Bijan Bowen pairs Fable 5 with local Qwen3.6 27B in Traycer. Here is what improved, failed, and the solo baseline revealed about multi-agent orchestration.
Chris Do's live niche coaching turned into a practical decision system: define an ICP, verify demand and budget, distinguish a productive Dip from a dead end, and run a 30-day market test.
Jonathan Courtney's Strategy Signal funnel rebuilt as a transparent case study: 19K opt-ins, 8,423 buyers, $405K front-end revenue, $1.2M backend sales, hidden advantages, and a responsible six-week build plan.
Wes Roth's Qwen3.8 Max roundup rebuilt as an evidence audit: long-horizon agent results, benchmark limits, the confirmed COLDCARD RNG flaw, and the unproven AI-attribution claim.
Malva AI's Vheer tutorial rebuilt as a current guide to the real zero-credit image and video routes, prompt patterns, limits, commercial rights, privacy, and the paid Higgsfield alternative.
Greg Isenberg's framework rebuilt as a practical guide to jobs, arrows, shared state, parallel research, checks, loops, and human approvals.
Mads Lorentzen turned Claude Code into a structured job-search workflow for fit scoring, tailored applications, independent review, interview preparation, and tracking.
Ahrefs' five-part AEO framework, rebuilt with current evidence on query fan-out, brand gaps, citations, YouTube, crawler controls, and measurement.
Qwen's official Qwen3.8 Max release explained: 2.4T MoE architecture, agentic coding, cowork benchmarks, multimodal feedback, API setup, and open-weight status.
Bijan Bowen tests Qwen3.8 Max across C++, CAD, games, writing, and multimodal coding. See what worked, what failed, what $32 bought, and its open-weight status.
Charles Broomfield connects an AWS layoff, an eight-hour app build, and AI-generated motion graphics to a warning about knowledge work. Here is what is personal testimony, what current evidence supports, and how to prepare without panic.
A source-checked guide to Daniel Kokotajlo's Diary of a CEO interview: the real meaning of his 70% estimate, the OpenAI equity dispute, his 2029 forecast, AI 2027, jobs, and AI 2040 Plan A.
Josh Pocock stress-tests Buzz and exposes the gap between a shared agent workspace and dependable orchestration. Here is what Buzz really solves, what the demo broke, and the controls a production agent team still needs.
Google now reports more AI-search performance, but query detail, citation logic, and conversion influence remain incomplete. Here is a decision-safe measurement model.
For many local service queries, the first useful summary now appears before a website visit. Here is how to make your business understandable, verifiable, and worth choosing.
The best first format depends on the missing evidence in your discovery journey. Use this practical sequence to choose between articles, video, and third-party proof.
AI systems cannot represent a brand reliably when its basic facts conflict. Build a small, maintainable verification layer across the site and trusted external sources.
AI citations vary by model, prompt, location, and run. This weekly review system separates stable evidence from dashboard noise and turns findings into one useful action.
AI assistance is not the quality problem. Publishing generic, unverified text is. Use this human-led workflow to create content with evidence, judgment, and practical value.
Answer engines may create the shortlist, but people still judge the brand. Distinctive, consistent design turns machine-mediated discovery into recognition, trust, and conversion.
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.
Thanks for your voice message. I listen to every one myself and I will get back to you within one business day.