Making commerce better for everyone. Follow us for technical discussions and updates on how engineers build @Shopify. Explore open roles: https://xitter.twitterapi.xyz/t.co/NFSvvCJBXt
Working Remotely
Joined May 2016
- Tweets5.1K
- Following708
- Followers60.7K
- Likes4.8K
Two buyers search for “backpack.” One needs a laptop bag. The other needs a hiking pack. How do you retrieve the right products for each, across a catalog of billions, and make it fast enough for a live request?
Here’s how we trained search and recommendation together.
shopify.engineering/generati…
Shopify Engineering retweeted
How does Shopify outperform frontier AI models at a fraction of the cost? During #PyTorchCon North America keynote, @cmazzaanthony of @ShopifyEng explained @Shopify's "Flywheel" a state-of-the-art continual learning loop built on top of @PyTorch and @vllm_project.
As enterprises scale generative AI, the bottleneck quickly shifts from building an initial model to maintaining and improving its performance in production. Shopify solves this by turning real-world failures into a self-improving engine.
Watch the full keynote video on YouTube to learn how this continuous learning loop operates in production: youtube.com/watch?v=2jOgIJRU…
What becomes the bottleneck when agents write most of your code?
Thirty engineers rebuilt Shopify’s 300+ screen app in Swift and Kotlin in 12 weeks. This meant changing the way we review, compute, merge, and coordinate.
Here’s what it took to keep shipping:
shopify.engineering/shopify-…
We rebuilt our mobile apps in Swift and Kotlin with agents. To keep pace and hold our quality bar, we built Reflex: an agentic-first architecture that lets agents build and verify app behavior across iOS and Android without needing devices or simulators.
Here's how it works, piece by piece:
shopify.engineering/reflex
Shopify Engineering retweeted
Going to chat about productionizing agents, post training, and inference optimizations on @nebiusai live at #NVIDIAGTC Berlin in 35 minutes or so. Tune in!
Nebius Live at NVIDIA GTC Berlin | Day 2 xitter.twitterapi.xyz/i/broadcasts/1RKZzBdvl…
Shopify Engineering retweeted
Tobi Lütke on the AI agent revolution and future of Shopify
@tobi on where agent commerce is headed, sci-fi becoming reality, and his GPU wine cellar.
Why did Amazon block Meta's Muse but Shopify welcomed it? I sit down with Tobi in Toronto to discuss why the companies are taking different approaches to agents and how shopping changes when AI starts buying things on your behalf.
He explains the early AI shopping behavior he’s seeing. We also get into why he thinks AI makes starting a business easier, the backlash against the technology, and why everyone will eventually have to embrace it to get ahead in their careers.
We get into how AI agents will make money, who pays when they handle a purchase, and why advertising gets complicated when your assistant is supposed to work for you. We discuss his experience on Meta’s board and working with Mark Zuckerberg.
Lütke also shares why he turned his wine cellar into a GPU server rack and how he uses his personal AI agent that runs entirely from his house.
This is one of my favorite pods I've ever done.
Timestamps:
00:00 Amazon blocks Muse
02:40 Shopify's approach to AI agents
07:00 How AI agents will change shopping
11:05 Sci-fi and tech optimism
17:57 Zero-sum thinking vs. abundance
21:20 AI backlash and the founder advantage
45:28 Building an AI-first Shopify
52:18 Who profits from agentic commerce?
01:03:22 How Shopify stays ahead
01:10:39 Advertising and discovery in the agent era
01:16:02 Rack, Cellar, and Claw
Links:
Spotify: open.spotify.com/episode/71x…
Substack: sourcesnews.substack.com/p/t…
YouTube: youtu.be/r9SHzCW9zxo
Apple Podcasts: sources.news/p/tobi-lutke-sh…
This episode's presenting sponsor is @hyperagentapp
Thanks to the show’s premiere sponsors: @Atlassian, @meetgranola, and @mercury
Shopify Engineering retweeted
The new Edition drops today.
It’s a magical time to build. Hope this Edition shows how much fun we’re having.
shopify.com/editions/fall202…
Ok so our internal tools have ad campaigns now. 📷
We built Remote Dev so AI agents can build and test iOS and Android apps without maxing out engineers’ laptops. The engineering behind the ad:
shopify.engineering/remote-d…
Sidekick’s frontier model hands its most token-heavy work to open models that Shopify post-trains and serves itself.
Check out the loop we use to build them, and where @NVIDIA’s models, software, and GPUs help to make each turn faster and cheaper.
shopify.engineering/open-mod…
Shopify's Catalog API helps AI agents recognize when different stores sell the same product.
But merchants name, describe, and photograph that same product differently. To categorize which product groups belong together, we created a system that turns billions of listings and trillions of candidate pairs into clustered listings under a shared product identifier.
Here’s how we built it: shopify.engineering/catalog-…
Thank you @wcandillon
As part of our commitment to a smooth transition for Shopify's React Native open source libraries, we've transferred ownership of React Native Skia to @wcandillon. We'll continue sponsoring its development through the end of the year.
Excited to see where he takes it next!
2
8
3,584
Catch Shopify @ COLM2026 and learn how:
SimGym runs storefront A/B tests with VLM agents in a live browser, using personas built from production clickstreams. Experiment cycles go from weeks to under an hour.
ShopGym turns live storefronts into sandbox shops and generates benchmark tasks for e-commerce web agents. Built with North Carolina State University.
SimPersona learns discrete buyer types from raw clickstreams, so agents stop shopping like one "average buyer." 78% conversion-rate alignment across 8.37 million buyers.
🔗👇
SimPersona and ShopGym @ COLM 2026 Workshop on Learning from Situated and Embodied Interaction learning-situated-interactio…
#railsworld's first livestream is a can't miss-- join us as we MC the livestream at 9:30am!
Not making it to Austin? No worries, thanks to @Shopify you can still catch the Rails World Opening Keynote livestream tomorrow at 9:30 AM CT. Set a reminder and tune in here: youtube.com/live/V9SxpJpHuus
🧑💻 AI is dramatically increasing the amount of code teams can produce. But code generation is only one part of software delivery. What have teams had to change - in planning, architecture, review, testing, shipping, and collaboration - to keep pace?
At today's closed door Rails at Scale Summit, Shopify hosted the AI panel: When code is no longer the bottleneck, to hear perspectives from @rails orgs at various scales. Thanks to our participants: @Zendesk, @salesforce's fin, and Perry St.
Congratulations @MParakhin!
Thank you @Time for the recognition time.com/collection/executiv… and congratulations to the full list of honorees!
1
19
4,516
Did we mention we like building internal tools?
When we announced our move back to native, we got a lot of questions about how Helix works. Today we’re sharing more details.
• Instead of expecting a perfect first attempt, Helix breaks work into small checkpoints that must pass strict quality gates before moving forward.
• Different AI models are good at different things. Gemini has been especially effective at catching subtle visual differences during UI reviews.
• Engineer feedback goes into memory, so Helix gets more autonomous with each checkpoint. It can run overnight without approvals, and the gates stay just as strict.
Link to blog post👇
2
40
9,844
📊 Bug bounty surveillance log | August '26
• 599 vulnerability reports intercepted
• 257 new hackers onboarded
• 46 reports awarded bounties
• $186K+ distributed to hunters
5
12
3,158
🔍 Come join the hunt for bugs here: shopify.com/bugbounty
2
941