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.
What stops your agent? Claude, ChatGPT, Grok, Gemini and Hercules compared on the part the launch posts skip
Laptop or cloud, schedule or event, hard cap or none: what Claude, ChatGPT, Grok, Gemini and Hercules agents do when nobody is watching.
Read the article →October 2026 in AI models: Gemini 4 Carbon takes first, Haiku 5.5 falls to a tenth of the price, and the index changes scale
01 Nov 2026 · 4 min readClaude Haiku 5.5 scores one point above Grok 4.7 at a fifteenth of the cost per task
01 Nov 2026 · 5 min readGemini 4 Carbon scores one point above Claude Opus 5.5 and costs 23% less per task, if you can get it
34 articles
No articles in this category yet.
Try a different filter.
Latest model comparisons
Price, independent score, and which one I would put in the loop.
Agents and coding tools
What runs unattended, what it costs and what stops it.
I built a custom AI content studio in 3 hours. Then I tried to break it
A custom AI content studio for a small team: one sentence in, two voices, SEO and GEO scores, a named approver. Built in about 3 hours, then attacked.
AI Systems · 7 min readClaude Code and Codex tie at 62 on the Coding Agent Index. Codex gets there for 40% less per task.
Fable 5.1 in Claude Code and GPT-6 Astra in Codex both score 62. Per task, Codex costs $7.47 against $12.39 and uses 3.3M tokens against 5.7M. Where each leads.
AI Marketing · 11 min readAn AI CMO without a plan is just a very fast intern
What an AI marketing stack really takes off a CMO, and what it cannot. The open source Claude Code plugin I built, and the two files it needs first.
AI Systems · 6 min readHow I use Claude Code in client GTM work
Beyond the outbound agent stack: how Claude Code runs content operations, CRM hygiene, and research inside real client engagements: what the delivery model looks like from the outside.
AI Systems · 7 min readThe AI stack I actually run in production
A complete tour of every AI tool in active use across my client work and products: what earned its place, what got cut, and what the operating logic looks like across the stack.
AI Systems · 5 min readFour layers that make a GTM agent actually work in production
Operator identity, MCP tools, client memory, reusable skills. Here is what the architecture looks like when the agent runs real GTM work, not a demo.
Playbooks
Longer pieces about systems rather than models.
Fable 5 scored 60 in July and 49.7 today. The model did not change. The index did.
What v4.3 measures, what changed on 7 September, the current ranking to two decimals, and why AI model scores from July cannot be compared with today's.
AI Systems · 6 min readAdd 50,000 tokens to a GPT-6 Astra prompt and the bill more than doubles. The 272K line, explained.
Above 272K input tokens, OpenAI bills the whole request at 2x input and 1.5x output. Claude keeps one rate to 1M. Worked costs for every current model.
Operator Playbooks · 5 min readReplatforming a large B2B website without losing the pipeline
The website rebuild I ran at Symfonia, treated as a revenue system: protect the SEO equity, keep the lead paths, tie the new site to pipeline.
Products · 5 min readThe browser bookmark is the wrong primitive
Why I built Kade as a local-first link vault: not another bookmark list, but a private queue for links that need context before they are opened again.
GTM Architecture · 8 min readWhy CRM-first beats prompt-first in AI adoption
Most B2B AI adoption starts with prompts and ends in chaos. The entry point isn't the tool: it's the data layer. Here's why CRM hygiene is the most important AI project most companies aren't running.
Operator Playbooks · 9 min readFrom Framer to Astro: the build vs buy decision behind this site
The honest trade-offs behind rebuilding wojciech.io: why I moved from a visual builder to Astro, what MDX and i18n changed, and which debt I accepted on purpose.
Newsletter
Want to know more first?
New articles on AI systems, GTM architecture, and growth operating models, delivered when they publish.