Karpathy's 2026 Playbook: Build Agent-First or Perish
Our read
Most of the AI apps you're building right now? Dead on arrival. Andrej Karpathy's 2026 playbook is a brutal obituary for 'vibe coding,' demanding builders ditch their flimsy 'Software 1.0 plumbing' and embrace 'agentic engineering' in verifiable niche domains, or get eaten by the next LLM release.
Key findings
Andrej Karpathy's 'December inflection' describes a recent, dramatic improvement in AI model outputs that enabled 'vibe coding,' accelerating rapid prototyping.
'Software 3.0' posits that the Large Language Model (LLM) itself becomes the programmable computer, with prompts acting as code, rendering many traditional 'orchestration' apps obsolete.
The 'pivot or perish' test suggests that if an application's core functionality can be replicated with a single multimodal prompt and tool calls, it's building 'plumbing that's about to get eaten' by the next model release.
'Agentic engineering' is introduced as the successor to 'vibe coding,' focusing on verifiable workflows, explicit specs, and robust testing to achieve 10x development speed without quality loss in production environments.
'Verifiability' is presented as 'the actual 2026 moat' for software applications, suggesting that the ability to ensure correctness and trust in AI-driven systems will be the defining competitive advantage.
What happened
The AI world just got a gut punch: Andrej Karpathy's 2026 forecast declares most current AI apps obsolete, exposing the 'December inflection' as the moment 'vibe coding' became a death sentence for 'Software 1.0 plumbing.' Forget mere iteration; accept that LLMs *are* the programmable computer in 'Software 3.0.' Builders clinging to their old ways will fail the 'Menu Gen Test,' becoming 'plumbing that's about to get eaten.' The only path to survival demands a pivot to 'agentic engineering', rigorous, verifiable workflows in niche domains, and building 'agent-first infrastructure.' Forget the hype; 'verifiability' is the actual 2026 moat, and everything else is just waiting to die.
The fight
- The 'December Inflection' and 'Vibe Coding' 01:03
Around December, AI models became so good at generating code that they 'just worked,' leading to a new style of rapid development called 'vibe coding.'
Evidence: Andrej Karpathy's personal experience building numerous side projects quickly, where he stopped correcting the model and started trusting its output.
- Software 3.0: A New Computing Paradigm 01:50
Software development has evolved from hand-written rules (1.0) and neural network training (2.0) to a new paradigm (3.0) where the LLM itself is the programmable computer, with prompts as code and the context window as the lever.
Evidence: A conceptual breakdown of software evolution by Karpathy, illustrating the shifting role of the developer from writing explicit code to prompting and managing LLM context.
- Obsoleting Apps via Native LLM Capabilities 02:40
Many current applications that merely orchestrate tasks an LLM can perform natively are becoming obsolete.
Evidence: Karpathy's 'MenuGen' app, built last year to visualize menu items, can now be fully replicated by a simple multimodal prompt in ChatGPT, demonstrating that previously complex workflows are now native LLM features. Rob also mentions his own 'Levercast' app as an example of AI integration vs. full LLM native solution.
- The 'Pivot or Perish' Test 04:57
Builders must assess if their current projects could be achieved with a single multimodal prompt plus tool calls/MCP; if so, their current plumbing is at risk of being eaten by future model releases.
Evidence: No direct evidence provided, but it's a logical extension of Argument 3, framed as a strategic imperative.
- Building Verifiable Domain Capabilities for Business Wins 06:49
Small builders should focus on niche, verifiable domains (like financial trading, supply chain, data cleaning) where the deterministic nature of code allows for clear feedback to AI models, providing a competitive advantage not pursued by large frontier labs.
Evidence: Karpathy's observation that models are excellent at code because it's verifiable, unlike much of the real world. He suggests identifying niches that combine verifiability with specific domain expertise.
- 'Agentic Engineering' Replaces 'Vibe Coding' 07:30
'Vibe coding' raised the floor of building, but professional builders must now move to 'agentic engineering,' which involves rigorous practices like specs, plans, proper review, and continuous integration to maintain quality while achieving 10x speed.
Evidence: A conceptual distinction between 'floor vs. ceiling' (vibe coding vs. agentic engineering) and a list of practices that improve quality and speed in agent-driven development.
Visual-only receipts
- 00:00: Animated neon line art representing a brain and connections, then a human figure.
- 00:01: Andrej Karpathy speaking at an 'AI Ascent' event.
- 00:07: Tesla Autopilot UI showing 'Unprotected Turns.'
- 00:10: Tweet from @karpathy: 'There's a new kind of coding I call "vibe coding".'
- 00:22: Slide: '= Karpathy's 2026 Playbook*{' // what to actually build with AI now. switchdimension.com.
- 00:30: Slide: '// next 10 minutes' with bullet points: '01 What he actually said about 2026.', '02 What you should be building.', '03 Four frameworks every AI builder needs.'
Quotes
“If you're still building apps the way you were last year, he's got bad news for us.”
Rob Shocks · 00:13
“So essentially, if you haven't sat down in the last 60 days and seriously tried to build something end-to-end with a Clog, Code, Codex, Cursor in agent mode, you are really flying blind according to Karpathy.”
Rob Shocks · 01:23
“A huge percentage of the apps people are building right now shouldn't exist either. They're basically orchestrating things the model can already do natively, that's only just appeared in the last couple of months.”
Rob Shocks · 04:35
“Take what you're building and ask, 'Could I do this with a single multimodal prompt and the right tool calls or an MCP or two?' If the answer is yes, you're building plumbing that's about to get eaten by the next model release. Stop or pivot.”
Rob Shocks · 04:57
The brief
Andrej Karpathy's 2026 AI outlook is a goddamn obituary for most AI-wrapped apps currently limping along. Forget slapping AI onto existing software; the demand is to fundamentally rethink what to build and how to build it, abandoning the naive high of 'vibe coding' for the cold, hard reality of 'agentic engineering.' This is the brutal playbook for builders who want to survive the AI landscape, forcing them to target verifiable niche domains and construct genuinely 'agent-first infrastructure.'
The rot started with the 'December inflection,' a sudden, dizzying leap in AI model capability that made 'vibe coding' feel like genius, rapid prototyping with minimal human correction. But that fleeting honeymoon is over for anyone serious. 'Software 3.0' is the new operating system where the LLM itself is the programmable computer. Prompts are code, and the context window is the primary lever. This paradigm shift doesn't just render traditional 'orchestration' apps obsolete; it annihilates them. The 'pivot or perish' test is simple: if your app's core functionality can be replicated by a single multimodal prompt, it's 'plumbing that's about to get eaten' by the next model release. Your shit is dead.
Survival means embracing 'agentic engineering.' This isn't some soft 'disciplined approach'; it's the brutal replacement for informal 'vibe coding,' demanding explicit specs, ruthless human review, and continuous integration with robust testing. That's the only way to hit 10x speed without sacrificing quality in production. The real fight is in 'verifiable workflows' within niche domains. That deterministic nature of code, providing clear feedback to AI models, is the 'moat' against the frontier labs. And the future isn't begging for 'agent-first infrastructure'; it demands it. Strip away human-centric UIs, expose the raw sensors and actuators for direct AI agent interaction. This isn't a wake-up call; it's a goddamn emergency. It slices through the hype with a pragmatic, painful diagnostic, the 'Menu Gen Test', for assessing your projects' imminent obsolescence. It's a brutal redirect of creative energy towards the only novel opportunities left in 'Software 3.0,' screaming that 'verifiability' is the next, and perhaps only, big moat.
Related dispatches
- Vibe Coding is DeadWhile 'vibe coding' democratized AI building, it's a dead end for anyone serious about production-grade systems. The real game is 'agentic engineering,' where you leverage AI for 10x speed but still demand verifiable output and rigorous testing, because trust in AI isn't built on vibes.
- The Menu Gen Test: Is Your App Obsolete?The 'Menu Gen Test' is the brutal reality check every AI builder needs: if a single multimodal prompt can do what your app does, you're building a dead product. It's painful to kill projects, but it's better than watching them die slowly while you waste time on 'Software 1.0 plumbing' that the next model release will eat for breakfast.