{"slug": "ai-doesn-t-ship-software-you-still-do", "title": "AI Doesn't Ship Software. You Still Do.", "summary": "A developer argues that while AI can rapidly generate the first 90% of a software project, the remaining 90%—handling real-world edge cases, scalability, and security—still requires human expertise. The post highlights that AI models lack the experiential knowledge needed to anticipate production failures, making experienced engineers more valuable than ever.", "body_md": "*AI made the easy 90% of software instant. The hard 90% is still yours.*\n\nYou type one sentence into a prompt box. Ninety seconds later, there's a running app.\n\nA form. A database. A chart that updates when you submit it. It looks done.\n\nIt isn't.\n\nOpen two browser tabs. Log in as the same user in both.\n\nSubmit the same form twice, fast — the way a nervous user does when the button doesn't visibly respond.\n\nLeave the thing running for a week instead of a five-minute demo.\n\nSomewhere in there, the wheels come off. A race condition nobody wrote a test for. A query that's instant at 40 rows and takes 40 seconds at 4 million. A webhook handler that isn't [idempotent](https://stripe.com/docs/idempotency), so a single retried request charges someone twice. A rate limiter that doesn't exist, so one flaky client retrying in a loop quietly takes the whole service down.\n\nPull up the git history. There's a decent chance an API key is sitting in a commit from three days ago, in plain text, one `git push`\n\nfrom being public forever.\n\nNone of this means the model failed. It built exactly what you asked for: something that runs.\n\nWhether it survives real users, real load, and real time was never the question it was answering.\n\nIn 1985, a Bell Labs programmer named Tom Cargill coined a line that Jon Bentley made famous in a *Communications of the ACM* column.\n\nThe first 90 percent of a project's code takes 90 percent of the time. The remaining 10 percent takes the other 90 percent.\n\nBentley called it, only half-jokingly, the [\"Rule of Credibility\"](https://en.wikipedia.org/wiki/Ninety%E2%80%93ninety_rule) — a warning to anyone tempted to trust a schedule from someone who'd never shipped anything to production.\n\nForty years later, the joke lands harder than it used to.\n\nAI collapsed exactly the part of the timeline the rule isn't about. Scaffolding an app — the login form, the CRUD boilerplate — used to eat real days. Now it's minutes.\n\nWhat Cargill was pointing at was always the second 90 percent: migrations that can't safely run twice, and the edge case where a deleted user's session token quietly keeps working for six more hours because nobody thought to invalidate it.\n\nThat part hasn't gotten any faster. It was never a typing problem to begin with.\n\nAsk an engineer with ten years of on-call scars what they think about while reviewing a pull request. It's rarely the syntax.\n\nIt's this: What happens under load? What's the blast radius if this throws at 3 a.m. and pages someone? Where does this leak a secret, a connection, or a customer's data?\n\nThose aren't questions you answer by reading more code. They're questions you answer by having watched systems break before, and having built a mental model of why.\n\nA language model doesn't have that model. It has, at enormous scale, a very good sense of what competent code *looks like*.\n\nThat's genuinely useful. It's also not the same thing as knowing what competent code *does under pressure*.\n\nAsk it for an authentication flow and you'll get something clean, conventional, and quietly wrong — in a way that won't surface until one specific, unlucky sequence of events happens in production.\n\nAt which point it's not a code review comment anymore. It's an incident.\n\nIt's the opposite, actually. Worth saying plainly, because a lot of people are drawing the wrong conclusion from how good the tools have gotten.\n\nThe part AI is genuinely eating is the mechanical translation of a spec into syntax — which was always the least interesting part of the job anyway.\n\nJunior work that amounted to \"implement this ticket exactly as written\" is getting cheaper by the month. It's not coming back.\n\nBut the value of understanding how a database index actually works, or why two requests hitting the same row in the same millisecond corrupt data, hasn't dropped.\n\nIf anything, it's gone up. That understanding is now the only thing standing between a working demo and an outage.\n\nThe engineers pulling ahead right now aren't the ones who avoided AI. They're the ones using it the way you'd use a very fast, very confident junior developer: delegate the boilerplate, then read every line that comes back like it's a pull request from someone you've never worked with before.\n\nWhat is it assuming about the input? What happens if this function gets called twice at once? Is the error actually handled, or just caught and silently swallowed?\n\nNone of that is a new skill. It's the same one code review has always demanded, aimed now at a collaborator that writes fast and never once says \"I'm not sure about this part.\"\n\nThe engineers falling behind aren't the ones without AI access — everyone has AI access. It's the ones who ship what it hands them without being able to explain why it works, and who have no idea where to even start once it stops.\n\nThat's the actual gap AI hasn't closed. It never set out to.\n\n*This piece was sparked by* *Anuradha Weeraman's essay on the same gap**— worth the five minutes.*\n\n*Originally published on ZyVOP*\n\n💡 For more articles like this, [subscribe to the ZyVOP newsletter](https://zyvop.com/newsletter)!", "url": "https://wpnews.pro/news/ai-doesn-t-ship-software-you-still-do", "canonical_source": "https://dev.to/pradeep_kumar_bc4e7e9f7ec/ai-doesnt-ship-software-you-still-do-5a5a", "published_at": "2026-08-01 16:09:38+00:00", "updated_at": "2026-08-01 16:44:37.604635+00:00", "lang": "en", "topics": ["artificial-intelligence", "developer-tools", "ai-products"], "entities": ["Tom Cargill", "Jon Bentley", "Bell Labs", "Communications of the ACM", "Stripe"], "alternates": {"html": "https://wpnews.pro/news/ai-doesn-t-ship-software-you-still-do", "markdown": "https://wpnews.pro/news/ai-doesn-t-ship-software-you-still-do.md", "text": "https://wpnews.pro/news/ai-doesn-t-ship-software-you-still-do.txt", "jsonld": "https://wpnews.pro/news/ai-doesn-t-ship-software-you-still-do.jsonld"}}