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 'Ralph Wiggum loop' concept involves an AI agent grabbing a single task, completing it, shutting down, and then repeating the process. This mirrors how developers pull user stories from a board, making it an effective model for orchestrating agent teams.

Graph engineering isn't a single concept. Knowledge graphs map relationships within data (customer to company), while agent graphs design multi-step AI workflows (planner to researcher to skeptic). Understanding this distinction is key to applying the right AI approach for a given problem.

A new 'loop engineering' paradigm structures work into two parts: an 'inner loop' for autonomous AI execution and a human-managed 'outer loop' for strategic direction and oversight. This model clarifies the division of labor, ensuring humans retain control over key decisions while leveraging AI for execution.

The most sophisticated loops don't execute all work in a single thread. Instead, a primary agent identifies sub-tasks and instantiates new, specialized "sub-agents" to handle them autonomously. This creates a powerful, scalable hierarchy of automation.

Instead of focusing on complex technical workflows, design loops by outlining a specific job to be done for an agent, just as you would when onboarding a new human employee. This managerial mental model simplifies the design process and makes it more accessible.

Moving beyond "loop engineering" which programs a single agent's iterative process, "graph engineering" designs the entire system of interaction between multiple agents, tools, and humans. It defines the "agentic organization"—specializations, data flows, and failure protocols—making the entire AI-powered workforce programmable, not just individual tasks.

The goal of graph engineering isn't creating the largest diagram of AI agents. More agents often lead to more noise and coordination overhead. The most effective graph is the smallest one that significantly improves work quality by separating workers from checkers and adding human approval at critical junctures.

Iterative AI agent loops, like Andre Karpathy's Auto Research, are not just another tool but a new foundational building block of work. Similar to how spreadsheets or email became ubiquitous across all roles and industries, these loops will be a core component of how knowledge work is performed, fundamentally changing process and productivity.