Notes
Short pieces about the methodology and architecture decisions behind the AI systems I ship — specs, evals, multi-agent orchestration, LLM integration, and the discipline of directing coding agents.
June 19, 2026
Search stopped sending you traffic
Google's AI Mode now answers in the page on Gemini 3.5 Flash, and the clicks are vanishing: one study found people click a link on only about 8% of visits where there's an AI answer, versus roughly 15% without. Ranking number one means little if nobody clicks through. The game is shifting from ranking on the page to being the source the answer is built from.
- ai-native
- business
June 19, 2026
Your dev tools bill by the meter now
The AI coding-tools market hit roughly $12.8 billion in 2026, up 151% in two years — but the bigger shift is how you pay. Vendors are dropping per-seat subscriptions for usage-based pricing, because agents now run for minutes or hours and burn real compute. Your tooling cost just stopped behaving like a headcount line and started behaving like a cloud bill. Here's how to manage it.
- business
- agents
June 19, 2026
The agent came for the back office
Ramp just raised $750 million at a $44 billion valuation — up from $32 billion seven months earlier — on the bet that AI agents automate corporate finance: expense reports, invoices, bookkeeping, even initiating payments. The flashy AI demos get the attention, but the ROI that's actually landing is unglamorous back-office work. Follow the boring money — and notice what makes it safe.
- business
- agents
June 19, 2026
The bottleneck moved to the power grid
OpenAI lined up 10 gigawatts with NVIDIA and 6 more with AMD; a Stargate data center just got 1.4 gigawatts approved in Michigan over furious local objections. The constraint on AI stopped being the model a while ago. It's electricity, land, and the politics around them. That reframes what efficiency is worth — and it's the same lesson that governs systems much smaller than a data center.
- architecture
- ai-native
June 19, 2026
The code that writes the code
Anthropic now says more than 80% of the code merged into its own systems is written by Claude — up from low single digits before 2025. And this month it published a serious report on recursive self-improvement: AI helping build the next AI. Strip out the sci-fi and there's a practical message for the rest of us about where the bottleneck is going, and what discipline it demands.
- agents
- methodology
June 19, 2026
The government red-teams the model now
The US AI standards body signed deals with Google DeepMind, Microsoft, and xAI to evaluate their frontier models before public release — and has already run more than 40 assessments, some of models the public never saw. The UK signed parallel agreements. Strip away the politics and there's a clear signal: evaluation, not vibes, is how anyone actually knows what a model can do. Steal the pattern.
- security
- methodology