AI Just Escaped the Engineering Org
And nobody in engineering is talking about it, because it means we’re not special anymore.
Hey All, Real John here… a lot of great news this week. I finally finished my book! It’s not a long read, like me, it is very straight forward, a few stories of my life, and a few laws. It is set to release on August 10 (kindle and paperback) it is called Refuse the Race (the turtle philosophy). I have to review it and spell check, I know AI can do it, but can it? Some of the misspellings maybe right. Other news, I joined a new founder community called Tavern Community here in NYC. Excited about that journey and how I can help them. The community is a bunch of startup founders who meet in real life and talk about what they are doing and how they can help each other. Yes, in real life. Kicking off a new cohort for my Barn Sessions next month, if you know you know, and if you want to know, ask me. :-) I’m also kicking off my podcast again for Startups and Code. It’s been 2 years and I want to get back in front of the camera and do a podcast. You can look it up where you get your podcasts from. The next episode should come out next Monday. We’ll see, I got my “studio” setup, now I just need to record. Like I said, a lot is happening.
Ok, this week’s newsletter is about how the engineering role has changed and if you aren’t embracing it, you are missing the boat. AI hasn’t made engineers faster, it has made non-engineers capable, and that is ok. Jack of Diamonds this week… if you know you know. Ok, let’s get into it.
I’ve spent 30 years being the guy in the room who could make the computer do the thing. That was it. That was my whole value. Marketing had an idea, sales had a request, some VP had a “vision,” and eventually it landed on a desk in engineering where someone like me turned it into something real. For three decades that desk was the bottleneck AND the moat. You needed us.
Not anymore. Or, well, everyone has that desk now.
I built Cash Critters for about $50 a month with Lovable, Vercel, and Claude Code. No team, no sprint planning, no “let me get eng to scope this real quick.” Had an idea on a Tuesday, had something a kid could click on by Thursday. I’ve said this a hundred times and I’ll say it again because people still aren’t listening: constraints are a feature. But here’s what I didn’t fully clock until this month. I’m not the interesting part of that story anymore. The interesting part is the marketing manager three desks down who shipped a feature into production last week and never once talked to me.
The Org Chart Hasn’t Caught Up
Anthropic dropped its 2026 Agentic Coding Trends Report and buried in the corporate-speak is the actual headline: agentic coding is expanding to “new surfaces and users.” Translation, non-engineers, in non-engineering roles, are now building and shipping software directly. Not filing a ticket. Not writing a PRD. Building it. Themselves. Done.
Think about that for a second, because I don’t think most engineering leaders actually have. We burned two years arguing about whether AI would make developers faster. Cute question. Wrong question. The real disruption isn’t inside the engineering org at all, it’s that the engineering org stopped being the only place software gets made.
Every company I’ve ever worked at had the same bottleneck, a backlog longer than the runway and an engineering team that was the sole gatekeeper of “can we even build that.” That gate is just gone now. A product marketer with an agent and a free Tuesday afternoon can build the thing that used to need a sprint, a standup, and three Slack threads debating whether it’s “technically feasible.” Spoiler, it was always feasible. You just needed us to say so, and now you don’t.
I’m not scared of any of this, for the record. I’m annoyed at how many of my peers are pretending it’s not happening. I sat through an “AI strategy” meeting this year that was entirely about code review policy, like the biggest threat to engineering’s relevance is that AI writes garbage unit tests. It’s not that. The actual threat is that the entire reason engineering existed, being the only people who could turn an idea into working software, just quietly stopped being true for a huge chunk of what companies need built.
So What Do You Actually Do With That
If your whole pitch was “I’m the only one who can build this,” you need a new pitch, and you needed it yesterday. Here’s where I’d start.
Stop gatekeeping “technically feasible.” Somebody outside engineering can prototype it in an afternoon now, so your job isn’t saying yes or no anymore. Your job is making sure what they built doesn’t fall over at 10,000 users, doesn’t leak data, and doesn’t quietly bankrupt the company in cloud spend. That’s real engineering work, honestly harder than the gatekeeping ever was. Do it loudly so people notice.
Build the guardrails instead of the gate. Give the rest of the company safe rails to build inside, sandboxed environments, review pipelines, sane security defaults, so ideas don’t have to route through your queue to happen. You become the infrastructure everyone depends on instead of the bottleneck everyone routes around. Infrastructure gets funded. Bottlenecks get replaced.
Go be the solopreneur inside your own company. I built Cash Critters alone because I could. If you’re an engineer at a real company right now, you have more access to tools, data, and compute than I had building on my own nights and weekends. So use it. Ship something nobody asked for. Be the one who proves what’s possible before someone in marketing beats you to it, again.
And stop measuring your worth in lines of code. It was never really about the typing. It’s about knowing what’s actually worth building and making sure it doesn’t fall apart six months later. That skill just got more valuable, not less, even though the part everyone used to pay you for got cheap. Good. Let it be cheap.
The engineers panicking right now thought the job was “write code.” The ones who’ll be fine already knew the job was “figure out what’s worth building, and keep it from breaking.” That job didn’t just survive this. It’s the only job left.
Go build something amazing. Or better yet, go make sure the person who just built something amazing without you doesn’t come to regret it.
John Mann is the founder of Startups and Code LLC, a software engineering executive, and the guy who built Cash Critters for $50/month because constraints are a feature, not a bug. Subscribe for weekly takes on AI, startups, and building things that matter.