The progression from prompt engineering to graph engineering is not about finding better words. Each step—context, harness, loops, graphs—is fundamentally about giving AI systems more independence and the ability to operate at a larger, more complex scale.

The focus in AI engineering has shifted from the agent itself to the surrounding system or 'harness.' This includes managing workflows, context, permissions, and tools. Engineering these reliable systems is now seen as more critical for delivering value than simply prompting a more powerful model.

Contrary to intuition, as AI models become more capable, the tooling (or "harness") around them must become more sophisticated to manage complex, long-running tasks. Features like "auto mode" are complex software built to leverage the model's advanced abilities.

Early agent development used simple frameworks ("scaffolds") to structure model interactions. As LLMs grew more capable, the industry moved to "harnesses"—more opinionated, "batteries-included" systems that provide default tools (like planning and file systems) and handle complex tasks like context compaction automatically.

The standard practice of building a generic harness to hot-swap AI models is becoming obsolete. As models develop unique capabilities, tightly integrating an agent's logic and tools with a specific model is now crucial for extracting maximum performance.

Building on AI involves a "tick-tock" cycle. First, engineers create a complex "harness" of prompts and skills. Then, a new, more powerful base model is released that performs those skills natively, "eating the harness" and forcing engineers to simplify and build a new layer of more advanced heuristics.

The focus in AI has shifted from crafting the perfect prompt (prompt engineering) to providing the right information (context engineering), and now to building the entire operational environment—tooling, systems, and access—that enables a model to perform complex tasks. This new paradigm is called harness engineering.

To fully leverage rapidly improving AI models, companies cannot just plug in new APIs. Notion's co-founder reveals they completely rebuild their AI system architecture every six months, designing it around the specific capabilities of the latest models to avoid being stuck with suboptimal implementations.

What we call an AI 'model' is no longer just a set of weights but an entire system with scaffolding for tool calling, search, and code execution. This external 'harness' indicates future native capabilities, as the model eventually 'eats' the scaffolding and incorporates these functions directly, pushing the innovation frontier outward.