{"slug": "ai-agents-are-coming", "title": "AI Agents Are Coming", "summary": "Developer Bartosz Cygankiewicz built a working MVP of an \"Orchestration Control Plane\" for managing more than twenty distributed Cezar agent instances in about five hours on September 21, 2026, after planning began September 20 at the Open Mercato HackOn in Wrocław, but has postponed the project because he sees no strong enough business case. Cygankiewicz named Mateusz Wiatrzyk, founder of the #aveCezar HackOn team, as the probable co-founder of Ventures Originals, and said he returned to running a single Open Mercato Cezar instance. He also noted that AI safety reached mainstream culture when Saturday Night Live's Weekend Update featured a Dario Amodei character on September 27, 2026.", "body_md": "ai-agents-are-coming\n\n# AI Agents Are Coming\n\nIs DHH crazy? A technical reality check from my little agent factory. Why writing code is becoming less important than deciding what should be built, and why Saturday Night Live is suddenly talking about AI agents.\n\n**TLDR:** DHH is still sane, but his stand-up skills went through the roof. If you have not seen his Rails World 2026 keynote yet, go watch it right now: [https://youtube.com/watch?v=vDjW_dRyKXY](https://youtube.com/watch?v=vDjW_dRyKXY). Seriously. It is a masterpiece and quite possibly the most important video you will watch in the next seven days. 🐐🔥🔥🔥\n\n## Report from my little slop factory floor\n\nWhat can you see above? In my [previous post](https://blog.cygankiewicz.com/en/is-open-mercato-an-ai-slop/) I said that I was looking for a co-founder and described an idea for a control plane sitting above [Cezar](https://github.com/open-mercato/cezar).\n\nThat was last Friday. It feels like ages ago.\n\nThe screenshot above is a small, working MVP of that idea. Planning started on September 20 after the [Open Mercato HackOn in Wrocław](https://blog.cygankiewicz.com/en/cezar-agent-orchestrator/). I genuinely thought getting to something useful would take me around a year. Instead, on Sunday I spent about five hours working on the MVP from an iPhone while visiting a cottage in the Beskid Śląski mountains.\n\nApparently a year is now a Sunday morning.\n\nThe interesting part is not even that I built a control plane quickly. The interesting part is how much the development loop has changed. The code can live somewhere else, the agents can live somewhere else, the compute can live somewhere else, and my interface can just be a phone. The workstation is slowly becoming optional.\n\n## There is some good news - Saturday Night Live is back\n\nApparently AI safety has become mainstream enough for Dario Amodei to appear as a character on Weekend Update.\n\nDario Amodei is at the desk to assure that the future of humanity is safe from AI [pic.twitter.com/HIem3WP5DX](https://t.co/HIem3WP5DX)\n\n[September 27, 2026](https://x.com/nbcsnl/status/2104080195485389259)\n\nAnd honestly, I love this. Not because AI risk is not serious - it is. But when something moves from research papers, Hacker News and technical conferences into Saturday Night Live, the cultural transition has happened too. AI agents are no longer some weird developer niche. They are becoming part of normal life.\n\nAnd the sketch is funny. That helps.\n\n## What is next for Ventures Originals?\n\nThe probable co-founder of [Ventures Originals](https://venturesoriginals.com/) is Mateusz Wiatrzyk, founder of our #aveCezar HackOn team:\n\n[https://pl.linkedin.com/in/mateusz-wiatrzyk-91637516b](https://pl.linkedin.com/in/mateusz-wiatrzyk-91637516b)\n\nMateusz is AI-native, open-minded and, most importantly, willing to actually **SHIP** things for the future instead of endlessly discussing the future. 🏭🤖💪🏻🚀\n\nThe “Orchestration Control Plane” was not a bad idea. Technically, I still like it a lot. Economically, however, I do not currently see a strong enough business case there. I have a working MVP, and it is cool that I can manage more than twenty Cezar instances distributed basically wherever I want, but “cool” is not a business model.\n\nFor my actual workload, I went back to running a single Open Mercato Cezar. After testing the opposite extreme, I think one Cezar is probably enough even for a serious power user.\n\nSo the project status is now: **postponed.**\n\nNot dead. Not deleted. I just do not see a reason to keep building something because the architecture makes me happy. That may be the most useful business lesson I learned this week.\n\n## So naturally I already have another idea\n\nThe next Ventures Originals idea is **little-cezar**, but only if [Open Mercato](https://www.openmercato.com/) is interested in collaborating.\n\nLittle-cezar would be a tool for children and, more broadly, EdTech. Kids are becoming builders much earlier than we did. Their imagination should not be wasted just because computers historically required years of syntax before they allowed you to make something interesting.\n\nIf software creation increasingly becomes a conversation between intent, agents, tools and verification, education should probably focus more on decomposition, curiosity, systems thinking, verification and understanding what is worth building.\n\nThis is just an idea right now, but I like this one.\n\n## DHH is not crazy\n\nNow we need to talk about David Heinemeier Hansson.\n\nHis Rails World 2026 Opening Keynote:\n\n[https://www.youtube.com/watch?v=vDjW_dRyKXY](https://www.youtube.com/watch?v=vDjW_dRyKXY)\n\nis a masterpiece.\n\nI do not mean that I literally agree with every sentence. I mean that I strongly agree with the direction of the argument. And the funniest part for me is the beginning of the talk - portrait painters.\n\nI had never thought about programmers through that analogy before, and it is disturbingly good.\n\nFor centuries, if you wanted an accurate image of yourself or your family, somebody had to paint it. It could take an enormous amount of skilled human labor. Photography did not make painting disappear and did not make art disappear. It destroyed the assumption that accurately reproducing somebody’s appearance had to be done by a painter.\n\nThat distinction matters.\n\nToday almost nobody orders a family portrait that takes one to three years to paint, apart from perhaps billionaires and sufficiently determined nouveau riche. Painting survived. The economic role of the portrait painter changed.\n\nAnd maybe software engineering is going through something similar.\n\nIn 1995, being able to build software by hand was an extraordinarily scarce skill. It was still scarce in 2015. It was still economically important in 2025.\n\n2026 feels different.\n\nNot because software suddenly stopped mattering.\n\nBecause the bottleneck moved.\n\n## Keep the happy memories\n\nIf you do not have time for the full DHH keynote, this is a good recap:\n\nMy god this is such a good speech that every SWE needs to hear. You know what? Every person should hear it\n\nKeep the happy memories, eyes on the reality, be excited about the future. That’s the best that anyone can do [pic.twitter.com/KKFUXfesFb](https://t.co/KKFUXfesFb)\n\n[September 25, 2026](https://x.com/scottstts/status/2103401938058723765)\n\nI really like that summary: **Keep the happy memories. Eyes on reality. Be excited about the future.**\n\nSounds reasonable to me.\n\n## I was never really a programmer\n\nI know how to code. I learned C at university. Later in life I wanted to become a full-stack web developer, which is one of the reasons I still love JavaScript.\n\nC and pointers were difficult for me, and my sophisticated technical opinion around 2012 was basically: **why the fuck do I need this pointer?**\n\nJavaScript felt completely different. Flexible, expressive, beautiful in its weirdness. I loved its functional side. TypeScript made the whole thing even better.\n\nBut I never really built my identity around being a programmer, and maybe that helps now.\n\nProgramming languages matter less to my daily work than they did even a year ago. AI agents are already surprisingly good across different languages and stacks, including old systems and languages like COBOL.\n\nSo instead of saying “programming stopped being a job”, which is obviously too broad, I would put my actual experience this way:\n\n**Around February 2026, writing code by hand stopped being the defining activity of software development for me.**\n\nProgramming did not disappear. The abstraction boundary moved again.\n\nWe used to manipulate machine code, then assembly, then higher-level languages, then frameworks. Now I increasingly manipulate intent, context, specs, tests, tools and agents.\n\nThe code is still there. I just touch less of it directly.\n\n## “Do nothing” is becoming a technical skill\n\nThis may be the part of DHH’s argument that interests me most.\n\nWhen execution becomes extremely cheap, the important question is no longer “Can I build this?” More and more often, the answer is simply yes.\n\nThe better question becomes:\n\nShould I build this?\n\nMy orchestration control plane is a perfect example. A week ago I thought it could become a company. Then I built the MVP, used it, looked at the economics and stopped.\n\nThat is not failure. That is progress.\n\nWhen execution becomes cheap, the ability to say **no** becomes more valuable. Wait. Observe. Use the boring existing thing. Kill the project before you spend six months polishing it.\n\nIn a world where agents can implement ideas faster than humans can properly evaluate them, restraint might become one of the highest-leverage technical skills.\n\n## More context from Warsaw\n\nThere is another video worth watching if you are interested in how software development actually looks in the second half of 2026.\n\nCallstack’s panel:\n\n**Future of Software Development | Closing Panel at Agent Conf 2026**\n\n[https://www.youtube.com/watch?v=0Swn0O6HxtU](https://www.youtube.com/watch?v=0Swn0O6HxtU)\n\nWhat I like about watching DHH and then watching engineers discuss the same transition is that the question is no longer whether coding agents work.\n\nThey work.\n\nThe interesting questions are now architectural and organizational: how much autonomy should agents get, how do we review their work, how do we preserve context, how do we control fleets, what stays deterministic and what remains human?\n\nAnd increasingly: **what should never have been built in the first place?**\n\n## Changes on this blog\n\nOne final thing.\n\n欢迎 🇨🇳\n\nChinese readers are first-class citizens here.\n\nThis blog now has dedicated routes for:\n\n- `/zh-cn/` - 简体中文\n- `/zh-tw/` - 繁體中文\n\nThis post will live in four languages:\n\n[https://blog.cygankiewicz.com/pl/ai-agents-are-coming/](https://blog.cygankiewicz.com/pl/ai-agents-are-coming/)\n\n[https://blog.cygankiewicz.com/en/ai-agents-are-coming/](https://blog.cygankiewicz.com/en/ai-agents-are-coming/)\n\n[https://blog.cygankiewicz.com/zh-cn/ai-agents-are-coming/](https://blog.cygankiewicz.com/zh-cn/ai-agents-are-coming/)\n\n[https://blog.cygankiewicz.com/zh-tw/ai-agents-are-coming/](https://blog.cygankiewicz.com/zh-tw/ai-agents-are-coming/)\n\nI also worked on Simplified and Traditional Chinese documentation for [Cezar](https://github.com/open-mercato/cezar).\n\nOpen source should not quietly assume that everybody worth talking to reads English comfortably. Making software available globally also means making its documentation understandable globally.\n\n## See you in the cloud ☁️\n\nSo that is today’s report from my little factory.\n\nIn roughly a week I went from wanting a co-founder for an orchestration control plane, to building the control plane, to discovering that I probably should not build a company around it.\n\nOnce, that would have felt like failure. Now I think it might be the opposite.\n\nImplementation costs fell enough for me to **test the idea instead of falling in love with a PowerPoint about the idea**.\n\nDHH argues for optimism. I would add one thing:\n\n**optimism with a kill switch.**\n\nBuild quickly. Use it. Look at reality. Keep what works. Kill what does not.\n\nThen go outside.\n\nThe agents will still be there when you come back.\n\n☁️🏭🤖💪🏻", "url": "https://wpnews.pro/news/ai-agents-are-coming", "canonical_source": "https://blog.cygankiewicz.com/en/ai-agents-are-coming/", "published_at": "2026-09-28 00:00:00+00:00", "updated_at": "2026-09-28 05:46:32.654702+00:00", "lang": "en", "topics": ["ai-agents", "ai-startups", "ai-tools"], "entities": ["Bartosz Cygankiewicz", "Cezar", "Open Mercato", "Ventures Originals", "Mateusz Wiatrzyk", "Dario Amodei", "Saturday Night Live", "little-cezar"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/ai-agents-are-coming", "markdown": "https://wpnews.pro/news/ai-agents-are-coming.md", "text": "https://wpnews.pro/news/ai-agents-are-coming.txt", "jsonld": "https://wpnews.pro/news/ai-agents-are-coming.jsonld"}}