At @11x_official , we’re trying to one-shot entire software builds. It’s a play on one-shot prompting, applied to the build itself: we hand an agent a detailed spec and let it work through the implementation, tests, and fixes in one autonomous run before coming back to us for review. That’s making us rethink how we build software. We’re putting more work into the spec up front and giving agents larger builds, with fewer human handoffs along the way. To make that possible, we started an AI-native codebase. Our engineers encode what they know about building good software into guardrails, checks, and tests that agents can use to continuously verify their own work. The idea is to give AI more autonomy while maintaining control over how the software is built. We recently rebuilt a core 11x product feature in one week. The original took three months. The rebuild included a 15-hour autonomous run. Of the six days of human work that week, four went into discovery and writing the spec — before any code was written. We’re still early, but it’s changing how we think about the role of an engineer, how we structure our codebases, and even whether breaking projects into smaller tickets is always the right approach. I wrote about what we’re learning in “One shot,” the first post on our new 11x Engineering Substack: 11xengineering.substack.com/…

This is what I've been working on over the past year Let me know if you want to give it a try: thecoterie.co