'Co-Intelligence' Author Ethan Mollick Proposes the 'Conjurer' Workflow: Summon AI Agents, Evaluate Results
On the release of his new book Co-Existence, Ethan Mollick draws on his own experience producing data charts with Opus 5.5 to propose a third mode of human-AI collaboration: the 'conjurer'—summoning AI agents, assigning tasks, and evaluating results without step-by-step guidance. He considers this the most powerful way to use AI today, but it means losing control over what the AI is actually doing.
Ethan Mollick recently produced a set of data charts for his new book Co-Existence. The tool he used was Opus 5.5 inside Claude Projects—an 'orchestrator' agent that, upon receiving instructions, splits tasks on its own, spins off sub-agents, assigns work, and relays results back to him. He gave a couple of sentences of suggestions, and the AI completed what would have taken him hours: all the research, all the graphing, all the layouts, all the images, all the citations. He even told the AI to 'make it better'—a vague reaction that would drive a human team mad—and the AI complied. More surprisingly, it caught a math error he had made.
This experience itself became the starting point for his argument. In Co-Intelligence, published in early 2024, Mollick described two modes of human-AI collaboration: 'centaur' work (divided between AI and humans, each doing their own parts) and 'cyborg' work (blended between AI and humans). Both keep you in the loop. But now that we have real agents, he added a third: the 'conjurer.' Conjurers summon agents when needed, assign them work, and evaluate what comes back. The way he made these charts was conjurer-style: summon agents, give some general guidance, and say 'make it better' repeatedly.
Why has this shift happened? Mollick uses the METR Long Horizon Benchmark to illustrate. The benchmark measures the amount of human work an AI can do with at least a 50% chance of success from a single prompt. From the release of GPT-4 to the end of the METR measure, that number doubled eight times. In 2024, an AI could do a four-minute task; by April 2026, when he turned in his draft, an AI could do 17 hours of human work. Then the benchmark itself ran out—METR said they could no longer accurately measure the amount of work an AI could do using their current methods. Other studies suggest that number might be 17 weeks of work, or more.