Yan: Practical multi-agent setups require isolated sandboxes without shared machines
Walden Yan · Devin’s 80% Moment: Background Agents, 7x PRs, & End of Hand-Held Coding — Walden Yan & Cole Murray · May 28, 2026 · at 39:45
Walden Yan, co-founder and CPO of Cognition (creator of Devin), discusses architectural challenges in multi-agent orchestration and why free-form swarms fail in practice.
0:00 / 0:34exact quote · 34.2s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“We've actually given Devon an MCP so they can just go arbitrarily message other Devons and create new Devons, et cetera. But I guess like it somehow creates like a really chaotic world in that sense. And so we, we've still found that most practical use on a day-to-day basis has been one single. Figure out how to segregate the work and get and have other Devons work on it in like a relatively Isolated sense, each with their own boxes, not sharing machines, so there's like very little room for conflict is kind of the regime that you have to create today.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Walden Yan
Yan: Getting agent integrations right often requires bespoke builds over MCP
“The thing we found is, so like MCPs obviously it has been like, it's like really big explosion of, oh, you can go like integrate it with all these different things. But to actually get the integration right and get the right experience, oftentimes we found tha…”
Yan: Cognition stripped obsolete Devin code after Sonnet 3.7 release
“So it's almost funny to be talking about how like big of a leaps on it. 3.7 was, and we honestly, a lot of it was stripping out parts of Devon that were no longer needed with that jumping of intelligence.”
Yan: Cognition merged PRs grew 7x as headcount grew only 10%
“It grew like seven X over like the last, I think it was like two months, three months, something like that. And then you see our engineering headcount growth, it's like gone up by like 10% or something.”
Yan: Autonomous agent sandboxes require full VMs instead of Docker containers
“Docker containers, not really a true security boundary for one. But the other is like, if you are running real applications, a lot of times those applications use Docker and then you have to think about Docker and Docker, which is like really weird. And so I t…”
Yan: Devin requires orchestrating multiple frontier models for end-to-end app testing
“Well, in some cases we found that actually no one frontier model can actually do this full end-to-end task itself. We've seen cases where we actually had had to orchestrate different frontier models together to kind of solve this problem together.”