Field notes on AI systems,
GTM, and revenue architecture.
Practical breakdowns from systems I build and run. Not theory: architecture, stack choices, and operator lessons from live deployments.
GPT-5.6 vs Claude 5: the first tests say the biggest shift isn't a new benchmark leader
OpenAI shipped GPT-5.6 Sol, Terra and Luna. Anthropic answered with Claude Fable 5 and Sonnet 5. After the first independent benchmarks there is no clean winner, but frontier intelligence just got cheaper and the fight moved from answering questions to finishing work.
22 articles
Claude Fable 5 found a live bug on my site on day one, so I made it compete with Opus and Sonnet
The Claude Code GTM Agent Starter Pack
A GTM agent that runs outbound, enriches CRM, and costs $2 per run
Replatforming a large B2B website without losing the pipeline
The browser bookmark is the wrong primitive
How I use Claude Code in client GTM work
The AI stack I actually run in production
Why CRM-first beats prompt-first in AI adoption
From Framer to Astro: the build vs buy decision behind this site
Cloudflare migration: what you get beyond hosting
Rebuilding my site with Claude Code, Codex, and zero frontend experience
macOS Teleprompter for MacBook Notch: building a native Swift app
What 10+ shipped micro-apps taught me about building with AI
I replaced the Google Ads UI with a dashboard that tells me what to do next
Four layers that make a GTM agent actually work in production
When to build your GTM tool and when to just buy one
Most AI adoption frameworks are built for demos, not for teams
Campaigns plateau. Systems compound. The difference matters.
Your CRM is an expensive address book. Here is how to fix that.
Building a booking engine for a market nobody else wanted
The growth system I built when founder-led sales stopped scaling
No articles in this category yet.
Try a different filter.
Newsletter
Want to know more first?
New articles on AI systems, GTM architecture, and growth operating models, delivered when they publish.