Claude Code Isn't About Code | Vlad Temian - Centrist Tech Optimist<br>BackClaude Code isn’t a coding tool. The people using it best right now barely touch code. They run factory floors, legal teams, HR, finance, operations. They don’t think of it as software. They think of it as the thing that does the work.<br>That took me two months to see. In April I wrote that I’d shipped 20+ tools, made zero revenue, and watched the value move from tools humans use to tools agents use. I ended on three words: I don’t have the answer.<br>Then YC published theirs.<br>YC stopped building tools<br>In “Inside YC’s AI Playbook”, Pete Koomen, Garry Tan, and Jared walk through how YC rebuilt itself internally. YC has always run on its own software, sitting on a single Postgres database that holds everything that matters: every company, every founder, every financial transaction, every note in their internal CRM.<br>A year ago, the loop looked like every company you’ve worked at. The finance team would describe a workflow (booking journal entries, logging priced rounds) to software engineers. The engineers would go build purpose-built, deterministic software encoding that workflow. Then they’d hand it back. Koomen’s word for it: inefficient.<br>So they killed the loop. Instead of building finance software, they gave the finance team agents and a registry of tools. The first tool that changed everything was almost embarrassingly simple: read-only SQL access to the production database. Jared built it, felt like he was breaking the rules, and pushed it out late at night. It worked extremely well.<br>// the loop they killed<br>FINANCE<br>→<br>ENGINEERS<br>→<br>PURPOSE-BUILT APP<br>describe, build, hand back. repeat for every change.
// what replaced it<br>ANYONE<br>→<br>AGENT<br>→<br>TOOL REGISTRY20 → 20<br>no engineers in the loop. build what you need, now.
They started with about 20 tools. At the time of the talk, there were more than 350. Every team adds their own. Finance books journal entries. Others manage office hours and events. And the same registry feeds both YC’s internal agents and Claude Code running on individual laptops.<br>The effect was a textbook case of Jevons paradox. When asking a complex question stopped costing several hours of someone else’s SQL time, people didn’t just answer the old questions faster. They asked far more questions, and far harder ones, because asking became cheap.<br>The inversion that makes it work<br>The reason this is a real shift and not just internal tooling is captured in Koomen’s earlier essay, “AI Horseless Carriages”. His critique was of AI bolted onto existing software as a feature, like Gmail’s email writer, where the developer keeps all the control and hides it from the user.<br>The crux is one sentence, and it’s worth reading slowly. AI-native software is the agent wrapping deterministic tools, not deterministic software wrapping an AI. Control shifts from the developer to the user.<br>// horseless carriage<br>DETERMINISTIC SOFTWAREAI
software wraps the AI
↓<br>// ai-native<br>AGENTTOOL<br>TOOL<br>TOOL
agent wraps the tools
control moves from developer → user<br>Flip that around and the strategy falls out of it. You stop building the interface. You stop building another finance SaaS, another ERP screen, another internal operations dashboard with its carefully designed flows. Those are horseless carriages: the old shape, with an engine bolted on.<br>Instead you build small, deterministic, well-scoped tools, you put them in a registry, and you let humans drive the agent that composes them. The plant manager, the lawyer, the HR lead. They get to build whatever they need in the moment, in plain language, without waiting on an engineering backlog. The interface was the constraint. Removing it is the product.<br>This is the answer I was groping for in April. The environment where disposable tools thrive is not hosting and previews and billing dashboards, or not only that. It’s a layer of unified context plus a shared tool registry plus a harness that lets agents compose them. The tools inside that layer are disposable by design. The registry and the context are the durable thing. YC built a private one and called it raising the floor: a new hire absorbs the institutional knowledge of the best people in the org through the tools and transcripts, instead of six months of ramp.<br>There’s a price of admission, and the talk is honest about it. You have to be willing to spend somewhere between $10,000 and $100,000 a year on tokens, sometimes more. Garry Tan’s framing is that this buys you a one-time time warp: you get to live in 2028 now, and in two years it costs a hundredth as much and everyone does it. That’s the optimistic read. Now for the other one.<br>Why your economy won’t feel this for a decade<br>If software is this transformative, where’s the growth? A talk that dropped the same week, from a very...