“So we have like some Slack channels internally, maybe a Slack channel dedicated to, a specific product like DeepWiki maybe. And you can imagine that, or you want a Devin that never stops, it’s just always awake, but it has this like memory dock that it can just maintain for itself about, okay, what are like the number one priorities of what we have to fix and prioritize? Who is responsible for some upcoming work?”
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 tooling, 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, 2026-11-01).
Exact match, including 'memory dock'. The turn is labeled 'Walden [00:33:01]' in the page transcript.
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 00:33:01. https://latent.space/p/cognition Archived at https://the-ai-record.com/passages/cognition-devin-permanent-pm-memory-file-slack-channel-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