The Truth About Multi-Agent Workflows - by Swapnil Talekar

Swapnil's Substack

SubscribeSign in

The Truth About Multi-Agent Workflows<br>Are People Actually Using “Agent Teams”?

Swapnil Talekar<br>Aug 10, 2026

Share

Multi-agent systems, to me, have felt like a very powerful and fascinating construct ever since I got introduced to them. Sometime at the beginning of the year, agent orchestration became a real thing. Frontier Labs did some cool demos. Companies announced that orchestration is the next frontier for agents. Steve Yegge created gastown as an early open-source framework for orchestrating multiple agents. I began to feel that I needed to upgrade my game.<br>Last week, I sat down to write a follow-up post on Loops and deep-diving into multi-agent systems. But then I realised something – I personally have had half a dozen multi-agent experiments and use cases sitting in my to-do list which I’m yet to try out. I do use multi-agents for a few things but not to the extent I’ve wanted. That realisation took me down a different rabbit-hole altogether: What are the real use cases which benefit from a multi-agent system? What are the friction points and shortcomings of it? And most importantly, if they’re so powerful, why aren’t more people using them, excluding all the AI-influencer demos?<br>Thanks for reading Swapnil's Substack! Subscribe for free to receive new posts and support my work.

Subscribe

If you’ve been doom-scrolling AI Twitter, you’ve definitely seen the hype: “I built a 12-agent swarm that codes, writes, and launches SaaS products while I sleep.” Meanwhile, in your actual workflow, you’re still copy-pasting between three different chats and praying nothing explodes. So I set out to find: do people actually use multiple agents simultaneously in a meaningful way today? And more importantly: outside of coding and tech demos, is this “agent team” thing real, or just a fancy word for “I opened three tabs”?<br>So this article is a bit opinionated and based on my interaction with developers, engineering leaders and non-tech [AI-pilled] folks in my circle. It also includes some online research, for which I actually did use “multi-agents”. I encourage you to share in comments any inaccuracies or contradictions you may have seen compared to my own experience.<br>This is what I’ve found. The short answer is: yes, people are using multi-agent workflows. But not to the extent that AI-influencers would have you think. Almost no one is running a “swarm of tiny robots”. They’re running it more for role-delegation and evaluating multiple solutions. Let’s break down what’s actually happening in the wild and how Claude, Cursor, and Codex each approach this. I look at specifically those three because I believe they cover the majority of users and use cases.<br>I reviewed this post after I finished writing it. While I really wanted to explore how this powerful construct of multi-agents can be leveraged by non-tech folks too, unfortunately, the way today’s tools are built, these features are largely targeted towards engineers. So heads-up, this gets a bit technical. But I encourage non-tech folks also to go through it and think about how they can apply these to their own workflows.

The three flavors of multi-agent

1. Claude: The closest thing to a real “team”

Claude Code’s Agent Teams feature is the most explicit “team of agents” product you’ll find right now. Released with Opus 4.6, it’s designed so that one session acts as a team lead , spawns teammates , and coordinates them through a shared task list and a mailbox system. Note that the feature is still experimental and you have to explicitly enable it in settings.json before you can use it. There are a few tutorials on YouTube that go in more depth about how to set it up and use it, but below are some key features of this:<br>Team lead + teammates: One main Claude session becomes the manager. It spawns other sessions, each with its own context window and role-specific instructions.

Shared task list: All agents see the same Kanban-style task board. Tasks have states, dependencies, and can be claimed by teammates as they become available.

Peer-to-peer messaging: Teammates can send structured messages to each other directly, not just back to the lead. This is interesting because it means, say for example, a security reviewer agent can flag an issue to the performance reviewer agent mid-run without stalling the whole team.

File locking: When one agent writes to a file, it acquires a lock, so that two agents don’t try to edit it at the same time.

Automatic orchestration: You describe a complex task, and Claude figures out what specialist agents to spawn, in what order, and how they should check each other’s work. But if you’re really particular about those things, you can also specify all of those things explicitly.

In practice, apparently people are using Agent Teams for:<br>Research tasks with competing hypotheses.

Full-stack features where one agent handles frontend,...