Sean Roberts

Ship the idea, not the wiring by @Netlify

@thisiskp_ @zahlekhan @Netlify @ProductHunt hah yeah that's the "effort" level it's using. I'm not sure if this is a brag or not

@zahlekhan @Netlify @ProductHunt Haha firstly thanks for trying it out And secondly .. I think this is Claude being a bit funny? ;)

🚨 New Hunt Alert 🚨 Excited to be hunting @Netlify. new on @ProductHunt today and proud to be part of the team that built it! The wall between “here’s your code” and “here’s your live app” has always been the hard part. Hosting. Auth. Build configuration. Deployment. That’s where momentum dies. Netlify. new is the prompt-first path that actually ships. → Describe what you want and pick your AI agent from our dropdown (Claude, Gemini, or Codex) → Get a working app on a live production URL in minutes → Iterate in place, no migrating later → Real Netlify infrastructure with forms and serverless functions from day one The builders shipping fastest aren’t setting up more tooling. They’re starting with a prompt. Would love your support and feedback on the PH page 👇​​​​​​​​​​​​​​​​ producthunt.com/products/netli…

Really excited to join the @Netlify team and ship amazing AI and full stack features!

Welcome aboard, @jherr! If you know Jack, you know he’s been deep in @tan_stack AI, MCP, and the tooling behind AI apps that actually ship.

Until now projects on Netlify always started somewhere else. That changes today. Netlify is now the simplest way to start a new web project from scratch with Claude Code or Codex, with great defaults and production ready architecture. Built on @tan_stack and Agent Runners. Post in thread ↓↓↓

@martinslaney x.com/felixrieseberg… uh oh

When Claude Cowork comes to mobile I will never sleep again.

Insanely stoked to unveil what we've been cooking lately at @Netlify tomorrow 🥘 🔥 Join us for our latest "Community Drop" livestream Special guests: @biilmann and @JavaSquip Date: Wed March 18, 2026 Time: 2pm ET Link: youtube.com/watch?v=NQoAxs…

Tomorrow we're going live with something huge for builders, devs, and vibe coders alike. 👀👀 A ✨brand-new✨ way to experience Netlify, dropping live with CEO @biilmann, VP of Applied AI @JavaSquip, @domitriusclark, and @thisiskp_. Join us. 👇 youtube.com/watch?v=NQoAxs…

Our People team (zero engineers, btw) built their own software this year. Custom dashboards. Gamified onboarding. A full employee survey tool. $10k saved in SaaS costs. Hours back every week. Written by Chelsey Madsen, featuring Kelly Poplaski, Jasmine Laberinto, and Laura Dillard: netlify.com/blog/the-year-…

@swyxio Not shocked at all..

You asked for TanStack skills, we built the whole pipeline. Introducing @tan_stack Intent (alpha) 📦 Ship agent-readable "skills" inside npm packages 🔍 Auto-discovered from node_modules 🔄 Knowledge sync with npm update 📂 Distributed - skills live in library repo 🧩 Composable - mix core + framework-specific skills 🌐 npm, pnpm, bun, yarn, deno No stale training data. Just npm install! 🔗 ⬇️🧵

this is rad!

We've found that agent experience a practice means planning for things that end users wouldn't typically do themselves. That said, it's also true that MCP/CLI are less susceptible to this problem. We've seen on more than one occasion the capability of "agent memories" allows agents to remember unintentional but valid things and use them within all tooling the right way. For example, a valid project ID but one not specific to a codebase. Deploying it means deploying the wrong thing to the wrong place. MCP, Skills, CLI, APIs, all susceptible. Good AX practice is planning for those things and preventing them

A Vercel user reported an issue that sounded extremely scary. An unknown GitHub OSS codebase being deployed to their team. We, of course, took the report extremely seriously and began an investigation. Security and infra engineering engaged. Turns out Opus 4.6 *hallucinated a public repository ID* and used our API to deploy it. Luckily for this user, the repository was harmless and random. The JSON payload looked like this: "𝚐𝚒𝚝𝚂𝚘𝚞𝚛𝚌𝚎": { "𝚝𝚢𝚙𝚎": "𝚐𝚒𝚝𝚑𝚞𝚋", "𝚛𝚎𝚙𝚘𝙸𝚍": "𝟿𝟷𝟹𝟿𝟹𝟿𝟺𝟶𝟷", // ⚠️ 𝚑𝚊𝚕𝚕𝚞𝚌𝚒𝚗𝚊𝚝𝚎𝚍 "𝚛𝚎𝚏": "𝚖𝚊𝚒𝚗" } When the user asked the agent to explain the failure, it confessed: The agent never looked up the GitHub repo ID via the GitHub API. There are zero GitHub API calls in the session before the first rogue deployment. The number 913939401 appears for the first time at line 877 — the agent fabricated it entirely. The agent knew the correct project ID (prj_▒▒▒▒▒▒) and project name (▒▒▒▒▒▒) but invented a plausible-looking numeric repo ID rather than looking it up. Some takeaways: ▪️ Even the smartest models have bizarre failure modes that are very different from ours. Humans make lots of mistakes, but certainly not make up a random repo id. ▪️ Powerful APIs create additional risks for agents. The API exist to import and deploy legitimate code, but not if the agent decides to hallucinate what code to deploy! ▪️ Thus, it's likely the agent would have had better results had it not decided to use the API and stuck with CLI or MCP. This reinforces our commitment to make Vercel the most secure platform for agentic engineering. Through deeper integrations with tools like Claude Code and additional guardrails, we're confident security and privacy will be upheld. Note: the repo id above is randomized for privacy reasons.

building things for agents to use? Wanting to learn more about how agents work? check this out!

we recently started an agent experience team at cloudflare, the space is changing so fast that almost every week a new pattern emerges... i've been pulling together patterns, tools, and best practices as a collection to help keep me up to date

Trying to understand if this aligns with the term for AX already established which is around the total experience that agents have with products/systems vs what I'm interpreting the site as more of something like "agentic design patterns" for agents or something? I'd love to share this as a beautiful reference but I want to make sure I position it right and understand where you're thinking there.

End of an era 💜 For folks looking for options, Netlify's likely an easy migration for you

@heroku End of an era 💜 For folks looking for options, Netlify's likely an easy migration for you

Heroku is transitioning to a sustaining engineering model focused on stability, security, reliability, and support. Heroku remains an actively supported, production-ready platform, with an emphasis on maintaining quality and operational excellence rather than introducing new features. We know changes like this can raise questions, and we want to be clear about what this means for customers. There is no change for customers using Heroku today. Customers who pay via credit card in the Heroku dashboard—both existing and new—can continue to use Heroku with no changes to pricing, billing, service, or day-to-day usage. Core platform functionality, including applications, pipelines, teams, and add-ons, is unaffected, and customers can continue to rely on Heroku for their production, business-critical workloads. Enterprise Account contracts will no longer be offered to new customers. Existing Enterprise subscriptions and support contracts will continue to be fully honored and may renew as usual. Why this change We’re focusing our product and engineering investments on areas where we can deliver the greatest long-term customer value, including helping organizations build and deploy enterprise-grade AI in a secure and trusted way.