Jeremy W retweeted
i just automated our release and QA process!
using Grok Bot i made two Team Bots: sandcastle, my release manager, and poteto, my engineer bot. i added them to Slack and made a new channel for managing releases.
first i tell sandcastle that i want to do a cut. it'll DM all the contributors with links to their PRs so they know what goes in the next release and can DM the bot back if they have any blockers or objections.
sandcastle then kicks off the build, watches it automatically, and starts up an automated fuzz swarm. usually this is 10+ agents running on Grok 4.7 xhigh to run the build, click around and use it like a real user (using our verification skills and feature map), some are directed while a few are "chaos monkey" clicking things randomly to see what breaks.
whenever it finds an issue, i tell it to @ mention my engineer bot poteto, to spin up a Cursor Project to own triaging and fixing all the high pri issues. depending on the severity i may ask it to cherry pick the fix into our release branch and cut a patch release, or if it's a pre-existing issue i still fix it but include in the next release instead
that's one more tedious task that Grok Bot now handles for our team
Jeremy W retweeted
NEW: Grok 4.5 costs just $0.31 per Intelligence Index task — nearly 89% less than Claude Fable 5.
Shopify launched (quietly) a free tool/scanner shopify.com/agentic-readines… that tells you how visible your store is to AI shopping agents like ChatGPT and Microsoft Copilot.
Paste a URL. Then it runs 31 checks across five categories: AI discoverability, product schema, transaction readiness, trust signals, and operational maturity.
I've been talking about AI discoverability and catalog metadata for a while now. This tool makes the gap visible in a way that's hard to ignore.
I ran it across several stores. The same three issues showed up almost every time:
→ Missing llms.txt - the file that tells AI agents what your store sells and who it's for. Most stores don't have it.
→ Incomplete product schema - the JSON-LD fields that AI uses to understand and recommend products Missing fields mean missing recommendations.
→ Thin policy pages/contents - short or missing privacy, returns, and shipping pages that AI checks before recommending a store
The tool is very useful for diagnosing what's broken and ranking it by priority.
But it does NOT fix anything.
If your score is lower than you expected, there’s many of you out there. Most stores just don’t realize how further behind they are on AI readiness than they realize.
Jeremy W retweeted
Shopify just reported on Q1. The numbers speak for themselves.
→ $101B in merchant sales, second consecutive quarter over $100B, up 35% YoY
→ $3.2B revenue, up 34% YoY
→ $476M free cash flow, 15% margin
That’s what a clear strategy, well executed, looks like.
For Q2 and beyond, here’s what really matters. AI will accelerate entrepreneurship more than any other job.
Jeremy W retweeted
OpenDesign is fantasic. Within 10 minutes it's already replaced Claude Design for me
github.com/nexu-io/open-desi…
Jeremy W retweeted

tobi lutke@tobiApr 15
Canada!
CanadaConnected via Canada App StoreLocation may be affected by a proxy or VPN.Account-level information, not a live location or per-post device.
Autoresearch isn’t just for training models shopify.engineering/autorese…
Jeremy W retweeted
We just launched Shopify Editions Winter 2026 🎨
Here's the technical breakdown of how we built it 🧵
Jeremy W retweeted
DockYard is looking for a React dev with React Router & Apollo experience mid - senior role. DMs open.
(no recruiters, no agencies, only devs)
Jeremy W retweeted
We've fully switched the license for Campfire over to MIT now. Do whatever you want, run it however you want, but just don't come asking for a warranty! once.com/license
Jeremy W retweeted
Introducing Tidewave: beyond code intelligence.
While working on our web apps, we run code, query the database, read logs, search docs… but AI tools are limited to compiling code.
Watch Tidewave transform Claude Desktop into an agent by running a MCP server in your web app!
Jeremy W retweeted
Replying to @ThePrimeagen
Jeremy W retweeted
37signals is hiring a Junior programmer. We're accepting applications until Wednesday, April 23rd at 12:00 PM CST. The salary is $145,849. apply.workable.com/37signals…
Jeremy W retweeted
Code speaks louder than words.
@ShopifyEng are builders. We craft software that empowers millions of entrepreneurs, tinkerers, and creators to shape the future of commerce. If you love to build, show us what you’ve made—GitHub repos, passion projects, anything you're proud of. Your code is your resume.
Send your work to 📩 [email protected].
Let’s build together. 🚀
Jeremy W retweeted
Meet Medley 🚀: The AI-powered health assistant that helps you understand your symptoms, manage non-emergency conditions, and make smarter health decisions—all from your phone. No panic, no guesswork, just clarity. Ready to take control of your health👉🏾 medleypro.com
Jeremy W retweeted
Elon Musk is right.
The Pentagon, with a budget of $886 billion, just failed its 7th audit in a row. It’s lost track of billions.
Last year, only 13 senators voted against the Military Industrial Complex and a defense budget full of waste and fraud.
That must change.
Jeremy W retweeted
Become a ghost for 6 months.
Make everything your fault.
Find the beast within you.
Throw yourself into pain.
Cut out all the excuses.
Go all in on yourself.
Train like a warrior.
Work like a robot.
Eat like a king.
Reject vices.
Transform.
Upgrade.
Create.
Thrive.
Win.

























