Features built to guide AI agents, like an explicit "plan mode," will become obsolete as models become more capable. The Claude Code team embraces this, building what's needed for the best current experience and fully expecting to delete that code when a new model renders it unnecessary.
Related Insights
Box CEO Aaron Levie advises against building complex workarounds for the limitations of cheaper, older AI models. This "scaffolding" becomes obsolete with each new model release. To stay competitive, companies must absorb the cost of using the best available model, as competitors will certainly do so.
As underlying AI models become more capable, the need for complex user interfaces diminishes. The team abandoned feature-rich IDEs like Cursor for Claude Code's simple terminal text box because the model's power now handles the complexity, making a minimal UI more efficient.
Overly structured, workflow-based systems that work with today's models will become bottlenecks tomorrow. Engineers must be prepared to shed abstractions and rebuild simpler, more general systems to capture the gains from exponentially improving models.
Early on, Google's Jules team built complex scaffolding with numerous sub-agents to compensate for model weaknesses. As models like Gemini improved, they found that simpler architectures performed better and were easier to maintain. The complex scaffolding was a temporary crutch, not a sustainable long-term solution.
In the fast-paced world of AI, focusing only on the limitations of current models is a failing strategy. GitHub's CPO advises product teams to design for the future capabilities they anticipate. This ensures that when a more powerful model drops, the product experience can be rapidly upgraded to its full potential.
The early focus on crafting the perfect prompt is obsolete. Sophisticated AI interaction is now about 'context engineering': architecting the entire environment by providing models with the right tools, data, and retrieval mechanisms to guide their reasoning process effectively.
The best UI for an AI tool is a direct function of the underlying model's power. A more capable model unlocks more autonomous 'form factors.' For example, the sudden rise of CLI agents was only possible once models like Claude 3 became capable enough to reliably handle multi-step tasks.
The Browser Company's Dia browser was built with the conviction that AI models would rapidly improve. Core features like "memory" were impossible, killed, and then revived just before launch when a new model suddenly unlocked the capability, validating their forward-looking bet on the technology's trajectory.
An AI tool's quality is now almost entirely dependent on its underlying model. The guest notes that 'Windsor', a top-tier agent just three weeks prior, dropped to 'C-tier' simply because it hadn't integrated Claude 4, highlighting the brutal pace of innovation.
The recent leap in AI coding isn't solely from a more powerful base model. The true innovation is a product layer that enables agent-like behavior: the system constantly evaluates and refines its own output, leading to far more complex and complete results than the LLM could achieve alone.