How many agents can one person run at once?

“One engineer might have three or four agents working in parallel: one implementing an API, one writing integration tests, one fixing a bug, one refactoring a legacy module. The engineer reviews each as it finishes, provides feedback, and merges.”

CoinbasePublished by the organization itself (post), no named author

“And I think … when I look at most companies, there's still somewhere between step one and two. … And when I look at Anthropic, we're probably somewhere around step three on average. So most engineers are running dozens or hundreds of agents. And the way you do this is you have the agent run another agent. And we have a lot of tools for this.”

Boris ChernyCreator and head of Claude Code, Anthropic · Leader, Anthropic

“We built agentic workflows to tackle mobile development tasks in parallel, but quickly hit the limits of our development machines. Just three or four workflows were enough to max out a laptop, with compilers, simulators, and emulators competing for resources.”

ShopifyPublished by the organization itself (post), no named author

“And I like to define what we've been calling frontier developers inside of Amazon by three behaviors that I've been seeing. One is hands off coding, frontier developers write maybe … of the code that they produce. The rest is agents. The second is that they interact with their agents infrequently. They'll aim to get their coding assistant to run for up to hours at a time without their intervention. And third is that they minimize idle time. These frontier developers tend to run multiple agents in parallel, … through a backlog of tasks.”

Clare LiguoriSenior Principal Engineer, AWS · Practitioner, Amazon

“I am running an organization of around 50-60 agents, five of whom are interfacing with around 10 humans in the outside world: myself, my 5-person core game design team, my accountant, my chief of staff, and a few others. Only Fable is allowed to talk to humans, via Slack and email.”

Steve YeggeIndependent; builds and runs Wheelhouse, a solo multi-agent software factory (2026) · Executive, Steve Yegge (independent)

“Mux is an internal multi-agent coding tool that started when one engineer built it to solve their own problem. The idea was minimal: each agent gets its own git worktree, its own branch, its own terminal. No conflicts. No stashing.”

CoinbasePublished by the organization itself (post), no named author

“Locking also caused too much contention. 20 agents would slow to the throughput of 1-3 with most time spent waiting on locks.”

Wilson LinResearcher, Cursor (author of the Towards self-driving codebases post) · Practitioner, Cursor (Anysphere)

“Workers pick up tasks and are solely responsible for driving them to completion. They're unaware of the larger system. They don't communicate with any other planners or workers. They work on their own copy of the repo, and when done, they write up a single handoff that the system submits to the planner that requested the task.”

Wilson LinResearcher, Cursor (author of the Towards self-driving codebases post) · Practitioner, Cursor (Anysphere)

“He's orchestrating 16 agents and he's going a whole lot faster.”

Will GaybrickPresident, Technology and Business (also styled President of Product and Business) · Executive, Stripe

“And you can see here that the prompt I provided was very trivial. It's like, hey, we've done a bunch of code review, solve all of the requests from the code review. And you can see that it's generated, I don't know, about 20-something tasks, yeah, about 23 tasks. And we get this beautiful DAG that defines what needs to be done in what order.”

Shardul VaidyaSolutions Architect, Data and AI, AWS · Practitioner, Amazon

“It definitely feels a bit different. It's maybe a bit less intense, but you're managing more things cognitively. I'm thinking of ideas that normally would've taken me a week to experiment with. And I think of multiple of these experiments and then fire them off all simultaneously. [It feels as] if I was a college professor with a whole swarm of research assistants, and they're all off doing things and it's coming back really rapidly.”

Peter MattisCo-founder and CTO, Cockroach Labs · Executive, Cockroach Labs

“In a new world, an engineer can spin up 10 agents and those agents can work 24 seven. I mean, I'm kind of exaggerating a little bit.”

Brian CheskyCo-founder and Chief Executive Officer · Executive, Airbnb

“Our first approach used a high-level orchestrator agent for this role. It worked, but it was expensive, slow, and sometimes unreliable. … We learned that although an LLM can orchestrate a workflow, predictable coordination is better implemented in code.”

StripePublished by the organization itself (post), no named author

“Context engineering, ability to multitask, and ability to review and verify the outputs: these skills have become much more important now because you’re able to parallelize a lot more than before.”

Uday Kiran MedisettyDistinguished Engineer · Practitioner, Uber