Blogsby GlyphNov 5
Reflex: an architecture for building mobile apps with agents
Our architecture lets agents test mobile app behavior without an emulator and use one test suite to keep iOS and Android in sync.
Shopify Engineering the engineering blog of Shopify: latest posts and feed
Shopify · Engineering blog · 3.4 a month · 437 posts since Oct 15, 2010
Oct 22
We gave AI agents a mobile dev environment
We built Remote Dev so AI agents can build and test apps in parallel, without maxing out developers’ laptops.
Oct 21
How Shopify turns open models into task experts
Sidekick’s frontier model hands its most token-heavy work to open models that Shopify post-trains and serves itself. Here’s the loop we use to build them, and where NVIDIA’s models, software, and GPUs make each turn faster and cheaper.
Oct 20
Cross-store product clustering across millions of stores
How we group product listings across millions of stores using tiered matching models, graph partitioning, and learned cluster merge decisions.
Oct 19
Building Overexposed: understanding application exposure
Our first scanner read config files and missed what was running. We rebuilt it with the cloud inventory, a careful probe, and honest results.
Oct 1
ShopGym: Realistic, reproducible sandboxes for shopping agents
ShopGym creates realistic online stores and generates shopping tasks based on each store’s products and features. Developers can then repeatedly test shopping agents under consistent conditions.
Sep 21
Helix: The internal tool powering our Shopify app's native migration
We built Helix to help LLMs rebuild the Shopify app in Swift and Kotlin, using small checkpoints and strict quality gates to keep the code shippable.
Sep 10
Native is now the future of mobile at Shopify
Coding agents changed what it costs to build mobile apps twice. Here’s why Shopify is moving from React Native back to Swift and Kotlin.
Sep 10
Migrating Shop app from React Native to native
We migrated the Shop app from React Native to Swift and Kotlin. Assisted by AI, the team was able to go from a proof of concept to a fully rebuilt native app published in the app stores in just 12 weeks.
Sep 2
How River takes security work from a fix to merge
River, Shopify’s AI agent in Slack, enables autonomous vulnerability remediation, not just detection.
Aug 19
Gisting: Compressing LLM Agent context to ↑ throughput and ↓ cost
Gisting compresses context into a set of learned tokens, preserving its quality while making the model faster and cheaper.
Aug 12
How we raised mobile end-to-end test stability to 98%
We rebuilt our mobile end-to-end testing framework with a strict API and computer vision, raising test stability drastically.
Aug 5
Sidekick's continual learning loop
How we compress production failures into model weights every day, beat frontier-model quality, and cut serving costs 96%.
Jul 29
Building an agentic harness that outlasts the model
We built an agentic code review and test oracle harness that discovers vulnerabilities, proves them with real tests, and provides Shopify-tuned fixes.
Jul 16
Upgrading Checkout Blocks app to Polaris web components
We moved five high-traffic checkout extensions to remote-dom and Polaris web components, cutting bundle sizes drastically and making checkout faster.
Jul 14
Inside Shopify Hack Days: Building a prototype for music-playing pages
How a Hack Days team built a music player, custom GLSL visualizers, and an artist toolkit for storefronts, all in three days.
Jun 17
Clustering billions of products for agentic commerce with Catalog API
Building an LLM-powered pipeline to match product listings across millions of merchants into a unified catalog that AI agents can search.
Jun 15
Teaching Sidekick to say no: automated data curation with LLM judge consensus
Production training data only captures successful queries; it can't teach a model when to say no. We built an automated curation pipeline using LLM judge consensus to close that gap.
Jun 10
Quick: An internal hosting platform for the AI era
Quick lets anyone at Shopify ship a site in seconds. It has changed the culture of how we build and share.
May 28
Under the River
What it took to ship our Slack-native agent River, lessons learned, and the substrate that runs beneath it. Co-authored by River.
May 12
We replaced Redis with MySQL for inventory reservations, and it scaled
How we used SKIP LOCKED, composite primary keys, and connection visibility to hit our scale targets.
Apr 22
Flow generation through natural language: An agentic modeling approach
We fine-tuned Qwen3-32B into a tool-calling agent that generates Flow automations from natural language, faster, cheaper, and more accurate than the frontier model it replaced, with a weekly retraining flywheel built on real merchant data.
Apr 15
Autoresearch isn’t just for training models
Tobi and I generalized Karpathy’s Autoresearch to improve 40+ metrics across Shopify, then we open-sourced our project.
Mar 19
Building a Magic Mirror: AI retail experiences with Remix
The technical blueprint for an AI-powered mirror that sees customers, analyzes their appearance, and delivers personalized product recommendations in real-time.
Mar 12
Shopify’s journey to faster breadth-first GraphQL execution
Conventional GraphQL execution uses depth-first traversal that incurs many hidden costs. We questioned why, rewrote it in a faster breadth-first manner, and saw dramatic results.
The latest 200 of 437 posts on file; older ones are under Months.
About this blog
Commerce at scale: Ruby, React Native, data and ML at Shopify.
Posts per week, last 26 weeks
3.4 a month over the last six months (or since the feed's oldest post)
Posts by month
Writes about
AI and agents (8), Developer tools (5), Product and company (2) in the last six months.