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.
Andrew Warner and Adam review NewsJack, OpenSEO, Paperclip, Anthropic finance agents, Open Code Review, ECC, WeKnora, Agent Skills, Orca, Octop, and more. Here is the ordered repo guide with demos, licenses, cautions, and first tests.
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 stress-tests DeepSeek V4 Flash across eight builds: what worked, what failed, what $0.79 bought, and why 13B active is not laptop-small.
Why DeepSeek, Qwen, GLM, and Kimi are spreading so quickly, what the OpenRouter adoption data really says, how export controls changed the race, and what "free" costs in production.
David Ondrej calls Kimi K3 the real Claude killer. Here is the source-checked deployment guide: official API access, Kimi Code subscriptions, Claude Code and Codex setup, model routing, local hardware reality, legal-work limits, and a safety review of the shared Kimi Everywhere gist.
Kimi K3 is a 2.8T multimodal model with 1M context. Four creator tests show where it rivals GPT-5.6 and Fable 5, where it fails, and what it costs.
David Ondrej interviews 0xSero about GLM-5.2, custom compression, LM Studio, rented GPUs, local tokens, and why open-weight models need better distribution and tooling.
NVIDIA Nemotron 3 Ultra is a 550B open MoE model for long-running agents, while Nemotron 3 Super is the 120B efficient workhorse. Here is what builders should know about architecture, licensing, deployment, and local experiments.
Pat Simmons shows three ways to reduce dependence on gated frontier models: local Ollama, free NVIDIA NIM endpoints, and cheap OpenRouter model routing. Here is the practical builder version.
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