Agent orchestration

When people say AI will speed up drug development or fear that it will bring about mass layoffs, what they have in mind—whether they know it or not—are AI agents. ChatGPT made large language models a mass consumer product. But to change the world, AI needs to do more than just talk back: It needs to do stuff. And that’s where agents come in.

Now, after much hype, the first bona fide multi-agent tools are starting to show their colors.

OpenClaw—a personal AI assistant that you could talk to from your phone—got everyone’s attention. Beneath the buzz, OpenClaw had a limited set of tricks—and a saboteur’s approach to security. But it felt like the future. And so companies from Nvidia to Tencent have been quick to build their own safer, more reliable bots on top of OpenClaw’s open-source code. 

But the real power of agents comes when they can work as a team. Instead of lone-wolf bots carrying out single tasks, such as using a browser to make a restaurant reservation or sending you a summary of your inbox, new tools can yoke together multiple agents, give each of them a different job, and orchestrate their behaviors so that they all pull together to complete more complex tasks than an individual agent could do by itself.  

For example, Claude Code, released by Anthropic last year, lets you launch and coordinate several coding agents at once (some users have reported having as many as a couple of dozen subagents on the go), with different agents working on different parts of the code base at the same time. Agents can also be given specific roles: One writes code, another tests it, a third fixes bugs, and so on. Such tools promise to turn coders into project managers, letting them delegate and oversee many more tasks than they could cope with by themselves.

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?