“You could give your agent a Slack MCP and okay, it can post messages back to you on Slack. But we actually use Devin like a coworker in Slack, and that’s how it’s been built from the ground up. But to do that, you actually need to, support webhooks that come back, right? And then Devin has to respond in a natural way and then hopefully don’t spam your threads too much and annoy the people in your company.”
Walden Yan, Co-founder and Chief Product Officer. Co-founder and product chief of the company that makes Devin, so he sees its internal usage data; Cognition sells AI coding agents and has reason to present them favorably.
Cognition sells AI or agent tools or services, so it has a reason to publish flattering numbers about AI. The passage stays in the archive; read it with that in mind.
How this was checked
Checked against the source by a first reader, then confirmed independently by a second reader who fetched the source without seeing the first reader's notes (Independent review agent (Claude Sonnet), blind second pass from passage text and citation only, no repository access, 2026-11-03).
The page transcript attributes this to Walden at [00:26:46]. The wording matches exactly apart from curly vs straight apostrophes. The tag-stripped text continues after the quoted ending ('So you got to tune that expe...').
How to cite this passage
Walden Yan (Cognition), “The Age of Async Agents: Cognition's Walden Yan and OpenInspect's Cole Murray”, Latent Space, 2026-05-28, at 00:26:46. https://latent.space/p/cognition Archived at https://the-ai-record.com/passages/cognition-use-devin-like-coworker-slack-webhooks-2026
Context. Walden Yan was describing an internal graph of Cognition's merged pull requests, which he said had grown 7X; the passage is the continuation of that answer.
Context. Yan was describing an internal experiment building real products by auto-merging AI-written code with no code review, to see how many weeks it could run before the codebase became unmanageable.
Cognition