A year ago, Andrej Karpathy told everyone to give in to the vibes. Millions did. They prompted their way to MVPs, weekend projects, and startup prototypes where 95% of the code came from an LLM.
Collins Dictionary named vibe coding its 2025 Word of the Year. Y Combinator reported a quarter of its Winter 2025 batch ran codebases that were almost entirely AI-generated.
Then came the hangover.
The Hangover Nobody Planned For
By September 2025, Fast Company was writing about senior engineers trapped in development hell with AI-generated code. A CodeRabbit analysis of 470 open-source GitHub pull requests found AI-co-authored code contained roughly 1.7 times more major issues than human-written code. Lovable, a Swedish vibe coding platform, shipped 170 apps with security holes that exposed personal data to anyone who looked.
METR ran a randomised controlled trial with experienced open-source developers. The result was brutal: developers using AI coding tools were 19% slower, despite predicting they would be 24% faster and still believing afterward they had been 20% faster.
The Problem Was Never the AI
The problem was not that AI generated bad code. The problem was that people skipped the engineering. No architecture. No specifications. No tests. No review. Just prompts and prayers. As Addy Osmani from Google Cloud put it: AI did not cause the problem. Skipping the design thinking did.
Enter Agentic Engineering
On 5 February 2026, exactly one year after coining vibe coding, Karpathy posted an update. The new term: agentic engineering. Agentic because developers no longer write most code directly — they orchestrate agents and act as supervisors. Engineering because the process still requires expertise, art, and science.
In vibe coding, you prompt and hope. In agentic engineering, you plan, direct, and review. The AI does the repetitive lifting. You own the architecture, the guardrails, and the outcomes.
Anthropic’s 2026 Agentic Coding Trends Report: TELUS created over 13,000 custom AI solutions while shipping engineering code 30% faster. Zapier hit 89% AI adoption with 800+ agents deployed internally. The engineers who thrive are not the fastest prompters. They are the clearest thinkers.
What Actually Changed
The shift mirrors every tech wave: democratisation euphoria, then the hangover, then professionalisation. The tool stays. The discipline returns. We are entering phase three right now.
Dario Amodei wrote in January 2026 that the strongest engineers he knows hand over almost all coding work to AI — but those are strong engineers who know what to delegate and when the agent is confidently wrong.
Where This Leaves Product Managers and Founders
Specifications before prompts. Write design documents before touching a coding agent. Clear specs lead to better AI output.
AI output is untrusted by default. Treat every AI-generated line of code like a pull request from a new hire. Review it, test it, question it.
The moat is the workflow, not the model. Intelligence is a commodity. Your product value lives in context, state management, and trust layers.
The role is shifting from writing to orchestrating. Less typing, more thinking.
What Comes Next
The organisations pulling ahead in 2026 are not removing engineers from the loop. They are making engineering expertise count where it matters most: architecture, security, system design. The agents handle implementation.
The question is not whether to use AI for development. That debate is over. The question is whether you are vibing or engineering. One of those scales. The other generates consulting invoices for the cleanup.
