But coding was just the start. The latest multi-agent tools are aimed at people who don’t need or don’t want to develop software. Desktop apps such as Anthropic’s Claude Cowork (which the firm claims to have built using Claude Code in just 10 days, instead of the several months such a project might otherwise have taken), OpenAI’s Codex, and Perplexity’s Computer are all pitched as general-purpose productivity tools for white-collar professionals. They let you hand off bespoke workflows to teams of agents that coordinate across a wide range of computer-based office tasks, from managing inboxes and inventory to handling customer complaints.
And it’s not just office work. Multi-agent tools like Google DeepMind’s Co-Scientist let researchers use teams of AI agents to coordinate literature searches, generate and test hypotheses, design experiments, and more.
Think of multi-agent systems as the new assembly lines. Henry Ford’s innovation upended entire industries last century. In theory, networks of AI agents could do to white-collar knowledge work what assembly lines did to manufacturing.
That’s the vision, at least. Because this technology also comes with huge risks. It’s no secret that LLMs can be unpredictable. That’s an annoyance when chatbots are stuck inside their screen. When they start interacting more with the real world, it could be disastrous. Are we ready for agents to be let loose on our ubiquitous digital infrastructure, from health care to finance, social media to missile launchers?
