SHOPIFY MAKES ITS AI CODING AGENT PUBLIC-BY-DEFAULT IN SLACK
Shopify runs its internal coding agent River only in public Slack channels to turn everyday work into shared learning. Tobias Lütke’s team designed River to de...
Shopify runs its internal coding agent River only in public Slack channels to turn everyday work into shared learning.
Tobias Lütke’s team designed River to decline DMs and prompt a public channel instead, creating a searchable "teaching workshop" where others can jump in, review, and learn through osmosis. See Simon Willison’s recap: Learning on the Shop floor.
Willison also draws a parallel to Midjourney’s early public Discord workflow, arguing public-by-default interaction accelerates collective learning and reduces siloed, one-off exchanges—especially with agents in the loop. More detail: Learning on the Shop floor.
Public-by-default agent threads reduce repeat questions and speed up onboarding.
Searchable discussions put code reviews and context where more engineers can see and improve them.
-
terminal
Pilot a Slack agent that declines DMs and moves work to public channels; track onboarding time and duplicate Q&A drops.
-
terminal
Run code reviews or incident threads in open channels; measure cross-team participation and time-to-merge.
Legacy codebase integration strategies...
- 01.
Start in non-sensitive domains; define redlines and auto-scrub secrets before making channels broadly visible.
- 02.
Add retention, export, and access policies; publish a channel taxonomy so engineers know what goes public.
Fresh architecture paradigms...
- 01.
Design "work-in-public" by default: open channels, thread-first reviews, and searchable archives from day one.
- 02.
Instrument thread analytics and tie agent outputs into internal search to build a living knowledge base.
Get daily SHOPIFY + SDLC updates.
- Practical tactics you can ship tomorrow
- Tooling, workflows, and architecture notes
- One short email each weekday