{"slug": "i-handed-ai-agents-almost-the-whole-product-except-one-part-and-that-part-is-the", "title": "I handed AI agents almost the whole product. Except one part - and that part is the job", "summary": "A developer built a working prototype of MERIDIAN, a travel app that maps a user's photo library, in days using AI agents. The developer argues that as coding becomes cheap, the critical job shifts to deciding what to build, and describes a system where agents handle volume while humans keep judgment and verification. The prototype emerged from a feature in a previously killed product, highlighting the importance of product decisions over code.", "body_md": "Recently an agent built a working prototype of MERIDIAN in a couple of days. A live page - where I've been, where I am, where next - plus a world map the app draws itself from the EXIF in your photo library, on-device, with zero manual input. Expo, React Native, a black SVG map. What would have taken a week of dense frontend a year ago was ready to screenshot-test the same day.\n\nHere's what that speed did. It didn't remove the risk - it moved it. While code was expensive, the main question was \"can we build it.\" Now building costs almost nothing, and one expensive question is left: am I even building the right thing. The risk moved off \"make it\" and onto \"decide what to make.\"\n\nSo I rebuilt how I run product. Not around who writes the code - there's unlimited code now. Around who decides which code is worth writing at all. I barely write myself - I hand tasks to agents, check, and cut. Below is how it's wired. Not \"look at my system,\" but something you can copy.\n\nThe work is split into pieces. Each piece has an agent that carries the volume, and a piece I keep. The line between them is the whole job.\n\nNotice what I did NOT hand to agents: deciding what to believe, the final roadmap cut, and checking someone else's work for lies. Everything else is volume, and volume is cheap now.\n\nAn agent left alone lies with confidence. It generates a hypothesis, justifies it, and serves it as fact - in the same tone it would use for the truth. So the one that generates and the one that checks are different in my setup. And between them sits a simple sort. Every claim - mine, a user's, an agent's - lands in one of three buckets:\n\nAnything in \"want it true\" gets a test attached: confirm or kill. Nothing rides into the build unmarked - and my own gut gets the hardest check, because it's the loudest.\n\nWhere this actually saves me. An agent proposes a feature and writes \"users want X.\" The second one goes to the source and finds that \"want\" is one thread in one chat. That's \"looks like,\" served as \"know.\" Without the second agent that \"want\" would have rolled onto the roadmap dressed as data. With it - it gets a test and waits. Costs pennies, and catches the most expensive class of error: confident lying that looks like fact.\n\nBack to the prototype, because the whole point is in it.\n\nBefore MERIDIAN I killed the previous hypothesis - Nomad Bridge, a two-sided marketplace for nomads. It didn't survive my own teardown: two sides, both needed from day one, the classic cold start that kills marketplaces, and the only paying demand I could find was by analogy, not by evidence. Inside that dead product sat a small feature I never took seriously - a profile page with a map of the countries you'd been to. I threw it out with everything else.\n\nThen I spent a month looking for the next thing. Around 350 ideas, nine runs with agents, and in almost every run one motif kept surfacing - that same movement map. The feature already in my hands, that I hadn't seen.\n\nHere's the trick. The agent built the prototype in days - and that speed is exactly what showed the hard part was never the code. The hard part was that I spent a month scoring 350 ideas on a spreadsheet and nearly missed what was in my pocket. When code was expensive, slow building masked the error in my head - you build so long you never notice you're building the wrong thing. When building got fast, the one real job was left naked: decide what's even worth building.\n\nHonest now, or everything above is just a nice shop window.\n\nThe client of this system is me. One user, who's also the developer, who's also the one who needs it. Which means the gains aren't proven by numbers - only that it suits me better, which is the weakest proof there is. Yan OS isn't finished and, honestly, by its nature never will be.\n\nNext - an agent loves its own ideas. A second agent grown from the same model tends to love the first one's ideas a little more than it should. So I keep the final knife, not the second agent: it lowers the lying, it doesn't zero it.\n\nContext costs money and attention. For an agent to judge well you have to feed it the right context, and gathering and keeping that context fresh is work nobody counts until it quietly eats the speed gain. A system that saves hours on the build easily returns them through the back door, on wrangling context.\n\nAnd the main thing - I can't be replaced exactly where there's nothing to check against. An agent is brilliant when there's a reference to compare the answer to. When there's nothing to compare - when the question is \"am I building the right thing\" and the market hasn't answered yet - taste decides, appetite for risk, and willingness to carry a product for years. That doesn't hand off yet. The whole thing stands on it - more on that here: [when building gets cheap, judgment becomes the job](https://nerovny.com/writing/when-building-gets-cheap-judgment-becomes-the-job).\n\nPut it together. When design and code are almost free, a team hiring a product person stops buying a pair of hands to execute a spec. There are unlimited hands now, and they're cheaper than any hire.\n\nWhat gets bought is exactly what I didn't hand to agents: deciding what to believe, the discipline to kill your own hypotheses, and a nose for lying that sounds like fact. Not the person who writes a PRD faster. The one who runs the agents that write the PRD - and knows which one is worth building.\n\nI built this alone, with agents - the same way I ran [Unicorn Embassy](https://unicornembassy.com) for three years with zero ad spend. Building dropped to nothing. The price of judgment is the only thing that went up\n\nI'm Yan Nerovny - product lead and founder of [Unicorn Embassy](https://unicornembassy.com). I write about product, AI and building from anywhere at [nerovny.com/writing](https://nerovny.com/writing/).\n\nRunning product with agents yourself? The part worth stealing is the three-bucket sort - known / looks-like / wanted-to-be-true. Tell me where it breaks for you: [Telegram](https://t.me/nerovny_blog) or [LinkedIn](https://linkedin.com/in/nerovny).", "url": "https://wpnews.pro/news/i-handed-ai-agents-almost-the-whole-product-except-one-part-and-that-part-is-the", "canonical_source": "https://dev.to/nerovny/i-handed-ai-agents-almost-the-whole-product-except-one-part-and-that-part-is-the-job-39b", "published_at": "2026-08-01 20:18:17+00:00", "updated_at": "2026-08-01 20:40:24.543709+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "developer-tools", "ai-products"], "entities": ["MERIDIAN", "Expo", "React Native", "Nomad Bridge", "Yan OS"], "alternates": {"html": "https://wpnews.pro/news/i-handed-ai-agents-almost-the-whole-product-except-one-part-and-that-part-is-the", "markdown": "https://wpnews.pro/news/i-handed-ai-agents-almost-the-whole-product-except-one-part-and-that-part-is-the.md", "text": "https://wpnews.pro/news/i-handed-ai-agents-almost-the-whole-product-except-one-part-and-that-part-is-the.txt", "jsonld": "https://wpnews.pro/news/i-handed-ai-agents-almost-the-whole-product-except-one-part-and-that-part-is-the.jsonld"}}