Learning on the Shop Floor
- Source
- x.com
- Author
- tobi lutke
- Date
Context
Shopify designed its internal , River, to make working methods visible to colleagues. Tobi Lütke says River declines direct messages and instead works in company-visible Slack channels. Employees can search past conversations, watch experienced colleagues investigate problems, and reuse their approaches. Lütke's account describes this as an apprenticeship environment.
The shared conversation also gives teams a place to identify missing and improve River's instructions. Lütke attributes its progress partly to this collective feedback. The supported idea is organizational: an agent's working history can become teaching material for coworkers as well as input for improving the agent.
- The design choice that does the work is a refusal: River will not answer direct messages. She declines and suggests opening a public channel, which is what makes every request searchable, joinable, and reviewable by anyone in the company.
- The usual worry about AI is that the agent does the thinking. Lütke reframes it: the danger is not the agent doing the work, it is the work happening in a private window, where the person at the keyboard is the only one who learns anything.
- The merge rate climbed without a retrain or a model swap. It moved because people watched the agent work and fixed the patterns — a system improvement, not a model improvement.
- Context is pushed down to the edges. Each channel pre-loads the zones, skills and instructions its own team needs, written by the people closest to that work, and the agent keeps a memory it updates and un-learns over time.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
- context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
“About one in eight pull requests merged into our codebase last week was authored by River, reviewed by us.”
“There are a lot of coding agents in the world right now. What makes River special is a constraint: She only works in the open.”
“The risk is not that AI does the work. The risk is that AI does the work and we never learn from it.”
“The agent does not replace the apprentice, nor does it replace the mentor. The agent makes the whole company an apprentice because everyone is constantly watching the most experienced people work alongside it.”
Checking sign-in…
Loading comments…