DeepStation

It was amazing hosting the @googlecloud Hackathon with Sergey Brin by @DeepStationAI, @MDCollege, and @thelabmiami 🤩 Selfie of a lifetime! Thank you for coming out and helping give a big welcome to the Co-Founder of Google! 🙏 @saif305 @ayalstern @melmedina305 @FrancisSuarez

@saif305 @Google @thelabmiami @MDCollege @GianniDalerta @mdcpresident @FrancisSuarez Thank you @saif305! It was truly an incredible experience to meet Sergey at the event we hosted with @googlecloud, @thelabmiami, and @MDCollege!

People still acting like Miami is hype. Meanwhile, Sergei Brin of @Google just casually showed up at a hackathon with @thelabmiami x @MDCollege x @DeepStationAI. Standing room only. Thx @GianniDalerta for sharing. The future is not being discussed in Miami. It’s being built here.

Sergey Brin spotted in miami

@ayalstern @wynwoodceo @thelabmiami @googlecloud DeepStation was proud to partner with The LAB Miami and Miami Dade College to host the Google Hackathon!

On a random Friday night in Wynwood… Sergey Brin walks into @thelabmiami . Room full of builders deep in a @googlecloud hackathon shipping all weekend. Miami isn’t coming, it’s here 🔥

We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord. Use this to message Claude Code directly from your phone.

🎙️ Meet the mentors showing up for the first-ever Google Hackathon by @DeepStation — March 20th & 21st in Miami. We built a mentor bench that covers every angle: AI engineering, cloud architecture, product design, executive coaching, data platforms & more. Here's who's in your corner 👇 🧠 Your Mentor Lineup: 👤 Ajith Punnakula — Engineering Manager, Pinterest 👤 Ather Husain — Technical Lead, Capgemini 👤 Damian Montero — AI Advocate 👤 Carlos Arevalo — Sr. Product Designer, Flow 👤 Nihal Kaul — Lead SWE, Revscale AI 👤 Vladyslav Budichenko — Founder, Vocaly AI 👤 Richmond Taylor — CEO, Bishop AI This kind of mentor lineup? Only community can build this. 🙌 Hackers, you are in great hands. 🔧 Build with Google ADK, Gemini API & Antigravity ☄️ Cash prize from OutRival 🤖 Gemini is literally one of the judges 🎟️ Grab your spot (limited tickets): luma.com/rmwe5d5a #GoogleHackathon #DeepStation #MiamiTech #AI #Hackathon #Mentorship #Gemini #GoogleADK #BuildWithAI #TechMiami #AIHackathon #MiamiStartups

🎙️ DeepStation is excited to announce our first @Google Hackathon with Miami Dade College and The Lab Miami on March 20th and 21st! ☄️ The Google Hackathon will give CASH PRIZES to the winners, as well as FREE credits during the event for over 50 teams using Google’s ADK, Gemini, and Antigravity! 🎟️ Signup here (limited tickets available): luma.com/rmwe5d5a Presented by: 🔸 Google 🔸 DeepStation 🔸 Miami Dade College 🔸 The LAB Miami Cash Prize Sponsors (so far!) 🔸 OutRival Community Partners: 🔸 hello_miami 🔸 The AI Collective 🔸 AI Builders 🔸 Kaufman Rossin 🔸 Software Internals 🔸 Miami Tech Works Acceptance Criteria (one of the following): 🔹Google ADK 🔹Gemini API 🔹Google Antigravity ⚖️ Judges from Google, Mastercard, DeepStation, Miami Dade College, and additional leading organizations will be present to assess the lucky winners! The Google Hackathon will even have an LLM as a judge by the name of Gemini… literally! 🧑‍🏫 We’re looking for more sponsors and mentors, so if you’d like to contribute please send me a direct message here on Linkedin! 🤝 Thank you to our cash prize sponsors Google and OutRival, community partners including the AI Salon, AI Collective, and Hello Miami, as well as our official sponsors Miami Tech Works & Kaufman Rossin! 🌞 A huge thank you to folks leading the charge at Google to make this big moment happen: ☁️ Pipe Martina and Miguel Suárez, and the overall Google team! Without all of your community support, none of this would be possible! Together, we will build Miami into a leading global AI & tech center! Date and Time: ⏰ March 20th: 4 - 9:30 pm: 🔹 4 PM: Walk-in 🔹 5 PM: Official Start ⏰ March 21st: 12 PM - 9:30 PM 🎟️ Signup here (limited tickets available): luma.com/rmwe5d5a @FrancisSuarez @ayalstern @thecmrfrd @hellomiami @AICollectiveCo @timurmeyster @rubenharris @outrivalAI @jonoringer @GrantKurz

🎙️ DeepStation is excited to share the summary and photos from OpenClaw: Demos, Agent Swarm, and Workflows at Miami Dade College! 🌐 "OpenClaw & The Intent Era" Alan Garcia, Head of Engineering at Soma Capital and former Full Stack Engineer at The New York Times, made the case that the winners of 2026 won't have better models — they'll have better judgment. Alan mapped the evolution from Prompt Engineering to Context Engineering to the next leap: Intent Engineering — teaching agents not just how to act, but when and why. Drawing from his work building Soma Capital's "Growth OS," which orchestrates agents across sourcing, technical evaluation, and outbound at scale, he shared practical frameworks for building agent judgment into workflows and what actually breaks when you hand real work to autonomous systems. 🤖 "OpenClaw: AI Agent Swarm — A Real Life Example" Michael Friedberg, Senior Software Engineer at Oracle, tackled a problem every professional knows — you collect dozens of business cards at events and never follow up. Michael demonstrated NextHello, a coordinated swarm of specialist AI agents that research your new contacts, qualify connections, personalize outreach, and deliver it all through WhatsApp. He walked through how to design specialist agents that coordinate as a swarm, practical patterns for conversational automation, and hard-won lessons from building and shipping an autonomous multi-agent system solo. 💡 "Sandbox the Claw: Live-Deploying OpenClaw in Under 15 Minutes" Gianni Crivello, CTO & Co-Founder of Sylow Technologies and Co-Creator of Nightshift, went live in a terminal with zero safety net. Autonomous coding agents can write code, edit files, and make network calls — and without proper isolation, one compromised agent can take down your entire host. Gianni performed a from-scratch deployment of OpenClaw into Firecracker microVMs using the Nightshift SDK, giving an autonomous agent full shell access while each session gets its own dedicated vCPUs, memory, filesystem, and KVM-backed isolation. No slides. No safety net. Just pip install to fully sandboxed coding agent in minutes.

Wow! What an OpenClaw Tuesday at DeepStation 🦞 Thank you to everyone who made it in Miami and to the many folks who watched our livestream! Stay tuned, we’re only getting started with our mission to accelerate AI education and innovation through the power of community Connect with us here: deepstation.ai/connect

Looking for Miami based AI-native agentic ninja 100x engineer to help me scale testing several concepts. DMs open.🌴🤖🚀

@jonoringer Hi Jon, we’re the largest AI community in Miami! May I share your message with our community?

dozens of DMs and counting .. will get to them all tonight!

openclaw meetup in Miami had 450 people attend this is a cultural moment that has escaped the normal tech bubble. the crowd included more non technical builders than technical ones I got to chat with small business owners and bulge bracket bankers. most people were just getting started and had varying degrees of experience with exiting agent harnesses and chat interfaces but everyone agreed that we’re all students again and the future will be driven by agents the excitement reminded me of the early crypto meetups. the awareness that our world has fundamentally changed, and an eagerness to figure it out together

TLDR: it is a cron job dispatching tickets from Linear to workers, each of which is a Ralph loop using a Linear comment as draft pad for persisted state. Yes it is all you need. Beautifully designed and minimal. github.com/openai/symphony

🚀 "Click to buy" is about to disappear. The future? AI agents shopping and paying on your behalf — no cart, no checkout. Stores aren't going anywhere. Only HOW we buy is changing. 🎬 Clip from our deep dive on Agentic Payments w/ Google's AP2 & Mastercard's Agentic Pay: youtu.be/23MjXTfEy8w

It is hard to communicate how much programming has changed due to AI in the last 2 months: not gradually and over time in the "progress as usual" way, but specifically this last December. There are a number of asterisks but imo coding agents basically didn’t work before December and basically work since - the models have significantly higher quality, long-term coherence and tenacity and they can power through large and long tasks, well past enough that it is extremely disruptive to the default programming workflow. Just to give an example, over the weekend I was building a local video analysis dashboard for the cameras of my home so I wrote: “Here is the local IP and username/password of my DGX Spark. Log in, set up ssh keys, set up vLLM, download and bench Qwen3-VL, set up a server endpoint to inference videos, a basic web ui dashboard, test everything, set it up with systemd, record memory notes for yourself and write up a markdown report for me”. The agent went off for ~30 minutes, ran into multiple issues, researched solutions online, resolved them one by one, wrote the code, tested it, debugged it, set up the services, and came back with the report and it was just done. I didn’t touch anything. All of this could easily have been a weekend project just 3 months ago but today it’s something you kick off and forget about for 30 minutes. As a result, programming is becoming unrecognizable. You’re not typing computer code into an editor like the way things were since computers were invented, that era is over. You're spinning up AI agents, giving them tasks *in English* and managing and reviewing their work in parallel. The biggest prize is in figuring out how you can keep ascending the layers of abstraction to set up long-running orchestrator Claws with all of the right tools, memory and instructions that productively manage multiple parallel Code instances for you. The leverage achievable via top tier "agentic engineering" feels very high right now. It’s not perfect, it needs high-level direction, judgement, taste, oversight, iteration and hints and ideas. It works a lot better in some scenarios than others (e.g. especially for tasks that are well-specified and where you can verify/test functionality). The key is to build intuition to decompose the task just right to hand off the parts that work and help out around the edges. But imo, this is nowhere near "business as usual" time in software.

AI agents won’t just recommend products soon… They’ll complete payments for you. 🤖💳 We just dropped a DeepStation episode diving into agentic payments with a Principal Engineer at Mastercard. Inside the convo: • PayPal x Microsoft Copilot momentum • AI-native payment architecture • Security implications of autonomous transactions • What enterprises are doing internally We’re shifting from: AI that assists ➝ AI that acts. That’s a massive leap. Curious what that means for fintech & AI builders? Watch here 👇 youtu.be/WeVqAphcQDI