@JavaSquip
Account based inUnited States
About this account
- Account based in
- United States
- Connected via
- Web
Account-level information from X, not a live location or the device used for a specific post.
Trying to make the web better! VP of Applied AI @Netlify by day Indie Hacker by night
ATL, USA
Joined August 2011
- Tweets4.3K
- Following2K
- Followers1.2K
- Likes6.9K
Sean Roberts retweeted
we're on netlify!
TypeSafe's Jev answers typed questions about your program state instead of writing prose. You hand it the state and declare the answers you are willing to accept. A routing question can come back as sales, support, or spam and nothing else, which means you can branch on it directly without parsing anything.
netlify.com/changelog/typesa…
I definitely think Jev is a mind shift for what we’ve thought about with models, this is my breakdown for how to use it
Here is the full walkthrough if you want to watch it work.
A real support ticket goes in, and Jev comes back with the team that owns it, a frustration score, and a probability that it reads as urgent. The confidence value on each answer decides what gets handled automatically and what a person sees.
TypeSafe's Jev answers typed questions about your program state instead of writing prose. You hand it the state and declare the answers you are willing to accept. A routing question can come back as sales, support, or spam and nothing else, which means you can branch on it directly without parsing anything.
netlify.com/changelog/typesa…
Cursor Origin 🤝 Netlify. That team is doing some of the coolest explorations in what new git flows could look like
Cursor Origin repos can now deploy on Netlify.
Push, preview, and ready to rollback in a click. Live in beta.
netlify.com/blog/cursor-orig…
Agent experience includes addressing the security side of agent interactions. This is a good direction
Hi Team,
We have been working on the OWASP MCP Security Taxonomy an open, vendor-neutral framework designed to create a common language for MCP security risk
📷 github.com/OWASP/MCP-Taxonom…
Please feel free to raise a GitHub issue, submit a pull request, or share your comments @owasp
Astra on Netlify. LFG
GPT-6 Astra is now available in Netlify AI Gateway and Agent Runners.
Use gpt-6-astra with the OpenAI SDK in Netlify Functions, without managing API keys or authentication. Or use it directly with Agent Runners, with zero configuration required.
netlify.com/changelog/gpt-6-…
GPT-6 Astra is now available in Netlify AI Gateway and Agent Runners.
Use gpt-6-astra with the OpenAI SDK in Netlify Functions, without managing API keys or authentication. Or use it directly with Agent Runners, with zero configuration required.
netlify.com/changelog/gpt-6-…
AX
1 million MCP calls to @resend this month.
April: 106,719
May: 153,597
Jun: 242,271
Jul: 580,121
Aug: 1,062,650
it's our fastest growing usage category.
Sean Roberts retweeted
The Web is amazing and MCP is exciting - so what does that make WebMCP?!
Looking forward to see what our community can come up with, to make web experiences that thrives inside ChatGPT's in-app browser.
AX to the max.
Netlify is partnering with @OpenAI to support the WebMCP Challenge, which opens today. Build an agent-native web app, or add WebMCP to one you already run.
There are 3 million Netlify credits up for grabs and a $5,000 prize pool for builders:
webmcpchallenge.netlify.app
Sean Roberts retweeted
@ChatGPT built-in browser speaks WebMCP and millions of @Shopify storefronts are live and ready! 🎉
That's a huge milestone and upgrade for your agent, which can now use site provided tools and efficiently explore merchant's catalog, build carts, and more.
Pumped to support @OpenAI WebMCP challenge too: openai.com/webmcp-challenge — join in on the fun!
🤫 p.s. psst, need a winning idea? Head to UCP.new to explore how you can build new shopping experiences with Shopify Global Catalog, then install UCP-cli (github.com/Shopify/ucp-cli) agent skill and let it cook.
We’re adding support for WebMCP in the ChatGPT desktop app’s built-in browser and ChatGPT Sites.
When you visit a compatible website, ChatGPT or Codex can automatically use it to complete your task.
Update to the latest version of the ChatGPT desktop app, then just ask Codex to create a WebMCP-enabled app and deploy it to Sites.
Join the Hackathon and see how far we can push the use of WebMCPs! Very excited to see what everyone builds
The WebMCP Challenge is here.
We’ve teamed up with @ChromiumDev, @CloudflareDev, @ShopifyDevs, @vercel, @render, and @Netlify for a 10-day hackathon.
Up for grabs: $35,000 in cash prizes, Codex Micros, ChatGPT Pro subscriptions, and more prizes from our supporters.
Netlify Agent Runners turn a prompt into a deployed application. You describe what you want, an agent builds it inside a real production environment, and you get a working preview back.
As of today, it can also ask you a few questions before it starts.
There it is! wondered when this was going to come full circle. “We need this as an industry solve” seems like a good idea. With them, it’s Vercel top of funnel in a tench coat. “Sign up for Vercel” happens quick!!
couldn’t keep the logo off the “oss” agent plugins social img either. 🤦♂️
Sean Roberts retweeted
We’re making open models easier to access wherever builders already work.
Starting today, that includes @Netlify.
Developers can now access DeepSeek, Qwen, GLM, Kimi, and hundreds of other frontier and open models through OpenRouter directly inside Agent Runners and Netlify AI Gateway.
Build with the models that fit your use case, all in one place.
Sean Roberts retweeted
Open models have gone from being far from the frontier, toright at it.
Today we launch GLM 5.2, Kimi K3, Deepseek V4 and more are in Agent Runners.
Thanks to @opencode for harness and @OpenRouter for partnership.
Prompt netlify.new/ and pick your harness and model.
All of y'all coming to my neck of the woods for @RenderATL need to stop by my workshop on axis.run to eval the quality of your AX. If nothing else you can look at this guy's goofy faces for 25 mins
Most teams shipped something for agents this year with no way to know whether it worked. At @RenderATL, @javasquip closes that gap live: he'll score a real project with AXIS, the open-source framework for measuring agent experience, and separate model problems from the slow endpoints and vague tool descriptions you can actually fix.
