Blog/Engineering
Engineering
Building AI-native software in practice: the stack that compounds, shipping solo at speed, and rebuilding systems from first principles.
Engineering · Aug 2026 · 10 min read
AI Builds AI. I Found the Ceiling.
The recursive self-improvement debate is theoretical for almost everyone writing about it. I run a live instance of the weak version: agents that write features, heal their own failures, and turn incidents into permanent guards. Here is exactly where the loop closes, and the harder half, where it stops.
Engineering · Aug 2026 · 9 min read
391 Yeses and Not One No.
This is a threat model, not an incident report. Nothing was breached. What I found when I audited my own agent permissions was worse in a quieter way: 391 allow rules, zero deny rules, zero ask rules, every one of them added by saying yes while busy. Here is the blast radius and the model I moved to.
Engineering · Aug 2026 · 13 min read
84 Ways to Tell Me I'm Wrong.
No human reads 532,000 lines of code, so the reading has to be delegated to something deterministic. I run an 84-dimension audit harness across eight projects. Here is how each dimension was earned, three of them walked through with real failing output, and what it still cannot see.
Engineering · Aug 2026 · 11 min read
Codex Accuses. Claude Convicts.
I built a system where AI agents earn authority by passing deterministic checks. It took an outside model one afternoon to point out that the agents can edit the checks. Eighty-eight audit dimensions and 19,949 tests could not see it, because every one of them reads the same repository the code lives in.
Engineering · Aug 2026 · 6 min read
Loop Engineering: How Orbyt Builds Itself
Loop engineering is how software gets built when you stop prompting and start running systems. On Orbyt, autonomous agents build features, run the tests, heal their own failures, and write what they learn back into the repo. My job is designing the loop and judging the output. Here is the machine, end to end.
Engineering · Aug 2026 · 9 min read
Long Horizon Agents Don't Fail. They Pass.
Long-horizon agent tasks do not fail loudly. They fail green. On Orbyt, a live function wrote to a database table that did not exist, and every test passed the whole time. The horizon of an autonomous system is not model stamina. It is time to detection, and only an oracle grounded outside the code shortens it.
Engineering · Aug 2026 · 7 min read
AI-Native Development, By the Numbers
The first-party dataset behind AI-native development. 243,000 lines in 32 days for $400, now over 425,000 lines and 11,372 tests. Measured, dated, citable.
Engineering · Aug 2026 · 8 min read
Your Tests Are the Spec Now.
Your tests are the spec now. When AI writes the code, a planning document goes stale the moment the first agent ships. Executable tests do not. Orbyt's 11,372-test suite is the real specification, the part of vibe coding nobody can vibe, and the only reason a vibe-built product survives production.
Engineering · Jul 2026 · 8 min read
I Ran 830 Agents in One Long Horizon Session.
One working session on Orbyt spawned 830 AI agents across seven days. At its busiest instant, nine were running. The interesting number is the gap, and what it tells you about where the real constraint in long horizon agent work has moved. It is not compute. It is verification.
Engineering · Jul 2026 · 7 min read
The Prompt Is Dead. Long Live the Loop.
Prompt engineering optimized one answer from one model call. That era is over. The unit of AI work is now the loop: spec, context, action, feedback, verification, repeated until the gate is green. The prompt became one turn inside a machine. Loop engineering is the discipline that builds the machine, and it is the skill that ships.
Engineering · Jul 2026 · 8 min read
Verification Is the New Literacy
When AI writes the code, the scarce skill is no longer authorship. It is verification. I cannot read all 425,000 lines of Orbyt by hand. The 11,372 tests and the 35-dimension audit harness read it for me, and they are the new literacy.
Engineering · Jun 2026 · 7 min read
Claude Code Is Like No One Saying No to You
The real unlock of Claude Code is not speed. It is the disappearance of "no." No budget, no capacity, no sprint room, no free designer. The gatekeepers are gone. When nothing tells you no, your taste, your judgment, and your test suite have to become the no.
Engineering · Jun 2026 · 10 min read
I Cannot Read My Own Codebase. I Ship to It Daily.
No human can read 425,000 lines. I ship into mine every day. What makes that safe is not memory. It is 11,372 tests.
Engineering · Apr 2026 · 10 min read
The AI-Native Stack You Pick Decides Whether AI Compounds or Stalls
Every AI coding agent was trained on a corpus dominated by React. Choose Next.js or pay a 1.5x to 2x velocity tax on every feature, every quarter.
Engineering · Mar 2026 · 7 min read
The Rise of Claude Code. The Death of Figma.
I replaced Figma, Sketch, and Adobe with Claude Code for every UI and UX decision. Design now happens directly in the codebase, with no mockups, no handoff, and no translation layer. AI-native design has arrived, design systems are optional, and traditional design tooling is dead. Taste survives. The process does not.
Engineering · Dec 2025 · 5 min read
How I Rebuilt ERP as a True Operating System
You fix broken enterprise software by redesigning how truth moves through an organization, not by adding features. ERP OS replaced ledger-with-a-UI systems with a unified temporal model, a semantic operational graph, and a context-aware interface. Across eight industries it cut operational friction 40 to 60 percent and restored trust.
Engineering · Dec 2025 · 7 min read
How CRM OS Reimagined Eight Industries
CRM OS started as Elements CRM and Gro CRM, two Apple-native startups, then grew into a multi-vertical operating system. We rebuilt object models, relationship graphs, and AI from first principles for HealthTech, FinTech, PropTech, Retail, Insurance, Professional Services, and Wealth Management. One architecture, eight industries, zero generic abstraction.