Co-Founder @aurapathai | @claude Community Ambassador New York
NYC
Joined August 2012
- Tweets8.1K
- Following1.6K
- Followers425
- Likes41.5K
One product URL, two readers. Vercel Shop serves the same page as a visual storefront for people and as machine-readable content, price, availability, and options, for agents.
That takes the guessing out of it. An agent stops inferring stock from layout.
Model Context Protocol sits at the merchant's own domain, so catalog search and cart building happen without navigating the site at all. Template is open source Next.js, built on Shopify's rebuilt Hydrogen software development kit, which also became generally available today.
Storefront and shopping assistant share one codebase and one cart, so a shopper keeps what they added moving between the two.
xitter.cf/vercel/status/21122040…
Vercel and @Shopify are making agents first-class shoppers. Vercel Shop, our Next.js storefront template for Shopify, is GA.
• Built on Shopify's rebuilt Hydrogen SDK
• Agents can read product pages directly
• MCP for product search and carts vercel.com/blog/vercel-and-s…
A repeated prompt mapped to a physical key keeps your hands in the work.
GitHub has been working with Logitech on their MX Keypad for 18 months, and the Copilot app is now integrated directly.
Three questions to get more out of it:
1. Which interruption repeats every day?
2. Which steps does that key actually remove?
3. What context lives in that prompt so it runs clean every time?
You still decide which actions earn a key, and when the keyboard or command palette is better.
Write the prompt down first. Then map it.
xitter.cf/github/status/21115151…
Your workflows have changed with AI. How about your setup?
Physical controls are back. Take the new Logitech MX Keypad, now directly integrated with the GitHub Copilot app.
This experience allows you to run agentic workflows with control, map a repeated prompt, start or resume a session, and help you stay in flow.
github.blog/news-insights/co…
Builders still just hit Publish. What changes is where the app lands.
Replit shipped Bring Your Own Cloud across Azure, Google Cloud, and Amazon Web Services in three levels. Full BYOC puts the platform and the agent harness in your own tenant, in private preview. BYOC for Published Apps hosts published projects in your cloud while Replit runs the platform. Image Exports hand you a Docker image, a Terraform file, and a software bill of materials. Both are in early access.
Three questions:
1. Which data cannot leave your premises?
2. How much deployment work do you want to own?
3. Who reviews an app before it goes live?
Admins set the destination per workspace. Map that first.
xitter.cf/Replit/status/21112190…
We’re introducing Bring Your Own Cloud (BYOC) for Replit, with options for development and production in your cloud, whether you use @Azure, @GoogleCloud, or @AWScloud.
Our approach gives security and platform teams greater isolation and control while preserving the familiar Replit experience.
Explore BYOC: replit.com/blog/bring-your-o…
Per-request logic gets rewritten every time you move runtimes. Supabase Middleware closes that.
Free and MIT-licensed.
What this means for you:
1. Bridges for Hono, H3, Elysia, NestJS, and TanStack Start are a file you copy, so the only install is the package.
2. withOAuthProtectedResource makes Model Context Protocol authorization one entry, and your row level security policies apply to an agent like they do a browser session.
Take the logic in one handler and make it an entry this week.
xitter.cf/supabase/status/211119…
Introducing Supabase Middleware.
Write per-request logic once, like checking who's calling, and run it on any runtime that has fetch. The same middleware also works inside Hono, H3, Elysia, NestJS, and TanStack Start with a bridge you copy.
Learn More ↓
supabase.com/blog/supabase-m…
The shareable link is the part that changes who gets to see the work.
Cursor cloud agents can now build interactive canvases. You ask for a dashboard or a report while the agent is still working, then you share the finished canvas with your team as a link.
Three questions before you use it:
1. Who on your team currently waits on a screenshot of agent output?
2. What belongs on that canvas every single run, so the next one starts from a baseline?
3. Where does the report end and the decision begin?
Asking for the view while the work happens is the habit worth building.
Pick one task you already run in the cloud and ask for the canvas with it.
xitter.cf/cursor_ai/status/21111…
Voice is a product decision, and you now have two paths to it.
GPT-Live-1 apps can shape a voice from a prompt, or use nine new presets created with native-speaking actors in French, German, Hindi, Japanese, and Korean.
Three questions before you pick:
1. Who is listening, and in which language do they want to be met?
2. Where in the product does this voice show up?
3. Who signs off on how it sounds?
Write those answers down first. That is your spec.
Read the custom voices guide, then run your real script through both paths and listen.
xitter.cf/OpenAIDevs/status/2111…
Brandon Slicklein retweeted
literally no one can shift the entire world's mood like elon
self-driving cars, flying cars, skyscrapers thrown into the sky and then caught by giant chopsticks, people controlling computers with their minds
every few months this madman comes out with something straight out of sci-fi and gets everyone excited about the future
a generational vibe shifter making the future look like the future
Brandon Slicklein retweeted
So in fact we actually can get robots, flying cars, superintelligence, fast internet on planes, space travel, space colonies, orbital data centers, unlimited energy, likely cures for nearly every disease, and more all in our life times. Pretty great.
Every team has the internal tool nobody built, because the database and the authentication layer were the whole project.
Sites is now generally available for Enterprise, with US and EU data residency for new Sites in eligible workspaces. Databases and authentication come with it. Plugins let each teammate pull their own connected data, and updates can run on a schedule.
1. Workspace custom domains publish on your organization's verified domain, in a format like support.sites.[yourdomain].com.
2. Private tunnels connect hosted Sites to approved internal infrastructure and APIs.
Pick the spreadsheet your team keeps emailing around. That is your first Site.
xitter.cf/OpenAIDevs/status/2110…
Sites is now generally available for Enterprise, with US and EU data residency for new Sites in eligible workspaces.
Build team apps with databases and authentication.
@kagigz shows how to schedule updates and let teammates use their own connected data with Plugins in Sites:
Pacing is what makes a voice interface feel like a conversation, and this release is tuned for exactly that.
GPT-Live-1.1 brings new voices, better accents, and less "checking..." to Voice in ChatGPT, Codex, and dots. New voices land in French, German, Hindi, Mexican Spanish, Korean, and Japanese. Rolling out today to all users, with API access coming soon.
Three questions:
1. Which work are you typing through that you could talk through instead?
2. Which languages do your users actually work in day to day?
3. What should a voice agent say while it is working?
Open Voice and run one task you normally type.
xitter.cf/OpenAI/status/21107978…
Scoped tokens minted per agent task is the detail to read twice.
Vercel expanded Enterprise Apps and Agents. Bring Your Own Cloud on AWS is generally available, so application functions run in your own AWS account. Enterprise-Managed Authorization through Vercel Connect is in public beta: employees sign in through your identity provider, and agents use connected services under those same permissions.
Three questions:
1. Which agents still run on long-lived credentials?
2. How many models are you routing across today?
3. Who owns the budget on each key?
Klaviyo reports 512 employees deployed 356 apps in two weeks.
Start by listing every credential an agent holds.
xitter.cf/vercel/status/21107909…
Vercel for Enterprise gives you a single control plane for governing every builder, app, agent, token, and dollar.
vercel.com/blog/vercel-for-e…
Your agent's files outlive the sandbox that ran them.
Vercel Drives is generally available for Vercel Sandbox on all plans. Create a drive once, mount it when you create a sandbox, and whatever is written there is waiting on the next run. Other sandboxes can mount the same drive. If one agent builds a dataset, other agents can mount read-only copies. Forking is generally available: each fork starts with the drive's contents and gets its own writable workspace.
Two questions:
1. What does your agent rebuild every run that it could mount instead?
2. Which files belong to the work, and which belong to the machine?
Pick one agent that clones a repo every run and give it a drive.
xitter.cf/vercel/status/21107884…
Vercel Drives is generally available. You can now run stateful agents on Vercel.
vercel.com/blog/introducing-…
Workers that stay running between jobs change what fits in one deploy.
Python is generally available on Vercel: FastAPI, Flask, and Django on standard CPython with your PyPI dependencies.
Containers ship any language with the OS libraries it needs, running as Functions on Fluid compute.
Daemons is in Public Beta: your worker pulls jobs from a queue or database, and Vercel restarts the process when it exits.
Three questions:
1. Which jobs would run better as a worker that stays up?
2. Which system library has been living outside your deploy?
3. Where could your frontend and the work behind it ship together?
Take one background job this week and give it a worker.
xitter.cf/vercel/status/21107863…
Run your backend on Vercel.
• Python is generally available
• Containers for other runtimes & system libraries
• Daemons for async jobs & background workers
vercel.com/blog/backends-on-…
An agent that checks in before an important action is the detail to read twice.
Meta shipped Muse Wonder and Muse Wonder Full. Active Memory carries context about you across conversations and retrieves what matters now. Active Focus sustains effort on a hard goal, tries other approaches, and asks for clarification before important actions, measured through FocusBench and SWE-Marathon.
Three questions:
1. What context should an agent carry between sessions?
2. Which actions deserve a check-in first?
3. Where do your long jobs stall?
Muse Wonder is available today in the Meta Model API and Muse Code, Muse Wonder Full for Muse Code subscribers.
Run one long task and watch where it pauses.
xitter.cf/AIatMeta/status/211051…
Muse Wonder and Muse Wonder Full deliver SOTA performance on personal and professional agentic tasks.
Learn more about the models on our researcher blog: go.meta.me/musewonder
Brandon Slicklein retweeted
BREAKING: A radioactive peptide that targets cancer cells and delivers radiation to destroy them has just succeeded in a Phase 3 trial.
Brandon Slicklein retweeted
we've been working on simplifying the ui and making it easier to manage multiple sessions. there are a lot of things in this update, hope you enjoy it!
The marketplace opening to public submissions is the line to read twice. Any team building developer tools can publish an app.
Origin, Cursor's code hosting platform, now connects repos to over 20 integrations: CI, deployments, code review, security, monitoring, and project management.
Three questions for your repo:
1. Which of those six categories is still a manual handoff for your team?
2. What breaks today when someone forgets to run a step?
3. If you make developer tools, what would you publish?
Wiring that up once beats rebuilding it on the next project.
Read the publishing guide, then connect the tools you already use.
xitter.cf/cursor_ai/status/21100…
Placeholder images stop blocking the build when asset generation lives where you code.
Runway now connects to Replit: generate images, video, and assets directly inside your project. Generations bill to your Runway credits and save to your Runway library with the rest of your work. The same connection works in Claude and Cursor through Model Context Protocol.
Two things to decide before you wire it in:
1. Which assets are one-off, and which need to stay consistent across the whole site.
2. What your prompt specifies about light and framing so the shots hold together.
Build one landing page this week where the hero video comes from the same session as the code.
xitter.cf/Replit/status/21100633…
You came for the cute puppy. Stay for what you can create. 🐶
Introducing Runway for web design. Connect @runwayml 🤝 @Replit to generate images, video, and assets directly inside your project, from first idea to finished site.
Connect in seconds: runway.com/mcp#replit
