Learning on the Shop floor
Summary
Simon Willison highlights Shopify's internal AI coding agent 'River' described by CEO Tobias Lütke, emphasizing its public Slack-based workflow that fosters transparency and osmosis learning among developers.
View Cached Full Text
Cached at: 05/11/26, 06:55 PM
Similar Articles
@fnthawar: https://x.com/fnthawar/status/2061498278303109316
Shopify is doubling down on hiring interns despite AI coding advances, leveraging their internal AI agent 'River' for transparent mentorship and acceleration. The public use of River across the company creates a collaborative learning environment that helps new engineers gain experience faster.
@tobi: https://x.com/tobi/status/2053121182044451016
Shopify CEO Tobi Lütke introduces River, an AI agent that operates exclusively in public Slack channels to facilitate code generation and knowledge sharing across the organization.
@zodchiii: Shopify's Head of Engineering: "If you don't figure out how to harness agents in 2026, you'll be behind." This intervie…
Shopify's Head of Engineering Farhan Thawar shares a practical breakdown of enterprise AI coding and how to harness agents in 2026, with a full playbook available in the interview.
How Shopify Uses ChatGPT Work to Build Faster with AI Agents
Shopify leverages ChatGPT and AI agents to enable non-developers to build tools independently, reducing reliance on engineering teams and accelerating internal process automation.
@chuhaiqu: The Claude Code Configuration Behind Shopify's 23,000 Engineers 1. First, Unify the AI Entry Point Shopify didn't lock the team into a single tool, but instead built an LLM proxy layer. Claude Code, Copilot, Cursor all go through the same gateway, connecting to OpenAI, Anthropic, Google...
Shopify shared 7 best practices on how to configure Claude Code to boost engineering productivity, including unifying the AI entry point, parallel agents, architecture review loop, MCP integration, permission control, etc., and noted that engineering time allocation has shifted from 70% execution to 70% strategy validation.