--- title: "Thinking in Systems, Shipping in Loops" description: "Software engineering has evolved into systems architecture. 37signals, Artemis \u0026 SpaceXAI all report the same shift : agents write the code, engineers design the systems that decide whether it is right. The scarce resource was never the talent, it was the foundation to verify against." categories: ["AI","engineering"] keywords: ["systems thinking","software architecture AI","agentic engineering","DHH Rails World keynote","PRs per engineer","verification loop","thinking in systems","Donella Meadows","system resilience self-organization hierarchy","Lauren Tan pstack"] ai_summary: "AI has removed the typing from software engineering \u0026 left the system design. DHH told Rails World that writing code by hand is no longer economically productive ; Artemis engineers merged 16 pull requests per day by August, \u0026 Lauren Tan ships 2,000 a month. The craft of fitting code together by hand is over ; what remains is designing the loop that decides whether the output is right. Donella Meadows's three properties of great system design, resilience, self-organization \u0026 hierarchy, describe how those loops are built. The architect's drafting table was always scarce because the foundation was scarce, not the talent." date: 2026-09-24 lastmod: 2026-09-24 canonical_url: https://tomtunguz.com/thinking-in-systems/ author: "Tomasz Tunguz" --- > "Writing code by hand is no longer an economically productive enterprise for the vast majority of programmers working at the vast majority of companies. That's today. By the end of the year, it will be virtually all domains, virtually all programmers, virtually all companies." > > *David Heinemeier Hansson, CTO of 37signals · Rails World, Austin · 23 September 2026* Software engineering have evolved to systems architecture. That was always the destination. This is the new software engineering : designing the systems that let AI write code correctly at scale. We see this in our portfolio companies. Artemis engineers merged 2 pull requests per day in January, 6 by May & 16 by August, 30,000 in eight months.[^2] Dan Shiebler, their CTO, describes the division of labor plainly : every line of the platform is written by agents, & the engineers design systems, set constraints & review outputs.[^3] Great design scales. Lauren Tan, an engineer on SpaceXAI's Grok team, ships 2,000 pull requests a month to production, nearly one hundred a working day.[^4] Asked what makes that possible, she does not name a model but verification, loops that enable AI to validate its work. {{< email_image src="ohk2dhmgoor6hkqxrye7" alt="A three-step numbered cycle drawn on graph paper" width="378" height="213" float="right" >}} Dartmouth professor Donella Meadows argued that the most powerful places to intervene in a system are the least intuitive, & that people reliably find them & then turn them the wrong way.[^5] Three properties define great system design : resilience, self-organization & hierarchy. Resilience is AI checking its own work, robustly, through tests, a reviewer agent & production observability rather than one gate. Self-organization is the loop learning, so a class of failure becomes a new skill the agent applies next time. Hierarchy is the layering of skills, tools & sandboxes into composable components that are reused once verified to work. This work isn't easy. Systems architecture never has been. It was my goal in 2005 as a Java software engineer just as much as it is today as we build out our agentic systems.[^6]
"A new career as a professional maker of things. Yes, you will no longer be chiseling that code by hand, but you will be making amazing things. You will be steering intelligence."[^1] [^1]: [Rails World 2026 Opening Keynote](https://youtu.be/vDjW_dRyKXY), David Heinemeier Hansson, Austin, 23 September 2026. He is co-owner & chief technology officer of 37signals. [^2]: [Artemis Security](https://www.linkedin.com/posts/goartemis_this-week-artemis-passed-30000-prs-in-eight-activity-7496210981040279553-QsNz) : 30,000 pull requests in eight months, an average of 16 merged per engineer per day in August 2026, up from 6 in May & 2 in January. [^3]: [Dan Shiebler](https://www.linkedin.com/posts/dan-shiebler-10219b42_this-week-engineers-at-artemis-merged-an-activity-7496235403826581504-9fW9), co-founder & CTO, Artemis Security : "Every line of code in our platform is written by AI agents. Our engineers design systems, set constraints, and review outputs." [^4]: [The Complete Guide to pstack, Pt. 1](https://x.com/poteto/status/2094457600259842065), Lauren Tan, 1 September 2026 : "It's allowed me to ship 2,000 PRs a month to production with high confidence." Her verification-skill example is [MIT licensed](https://github.com/poteto/verification-skill-example). The New Stack profiled the workflow in [One engineer shipped 2,000 PRs a month to production](https://thenewstack.io/agentic-verification-distributed-systems/), 19 September 2026. [^5]: [Thinking in Systems : A Primer](https://www.amazon.com/Thinking-Systems-Donella-H-Meadows/dp/1603580557), Donella H. Meadows, 2008, chapter 6. [^6]: [Three Years In](https://tomtunguz.com/three-years-in/), 10 July 2026 : building Theory as a technical organization, agents to map markets & research infrastructure to cover the ground of a firm several times our size.