Roberto Solano

excelente video que envejece como el vino 🍷

Sandboxes are now fully standalone. No Docker Desktop required. Just install and go. Now with even faster cold starts, works out of the box with Claude Code, Codex, Copilot, Gemini, and Kiro. Even NanoClaw. Get full agent autonomy. Keep everything that matters safe. More → bit.ly/4lZ93jg

Meet our first hackathon co-host: @v0 by @vercel 🤝 To support all students, we will be providing v0 credits to every hacker to design, prototype, and ship faster. Apply now 👇 hack.dev3pack.xyz

if you think im just some dumb dumb thinking claude can find bugs and all my examples are wrong, just watch 15 min of this talk 😝 youtube.com/watch?v=1sd26p…

If ‘vibe coding’ disrupts the software market like SaaS did 20 years ago, what does this mean for cyber security? ncsc.gov.uk/blogs/vibe-che…

We just launched a new free course on Dagster University: AI-Driven Data Engineering 8 lessons. Blank directory to production ELT pipeline. Built entirely from prompts. If you've been curious about using AI agents for real data engineering work and dont know where to start, this is the one for you!

Want to win a Mac Mini to run your own OpenClaw agent? 🤖 Spend your April building an agent for a chance to win one. One month, fully online running in the background. Build whatever you want - tools, skills, plugins, payments, anything agent-related. Topped with a demo day at the Encode Hub to showcase the best agentic projects and crown the winner Register now ↓

State of Context Engineering in 2026 newsletter.swirlai.com/p/state-of-con… < this is good stuff. What are the patterns and considerations for giving your LLM or AI agent what it needs to know?

I went down the rabbit hole of the “filesystem + shell tool is all your agent needs” discussion and this is what I came back with: A shell tool is the most versatile tool an agent can have. But is it all an agent needs for context engineering? In this blog we look at: • Are filesystems making databases obsolete? • When to use shell tool + filesystem • When to use shell tool + database • When to use dedicated DB tool + database • How to find the right set of search tools for context engineering Blog: elastic.co/search-labs/bl…

Instead of one AI doing everything, what if you had a team of agents? One plans. One builds. One tests. This post from Docker Captains @mfranz_on & @esteban_x64 shows how Docker Agent + Sandboxes make it possible while keeping everything isolated from your machine. Read → bit.ly/4lRrHK2

Crea tu propio Vercel en cualquier servidor VPS. Se llama Dokploy y es de código abierto. ✓ Despliega Next.js, Node, Go, PHP, Java… ✓ Soporte nativo imágenes de Docker ✓ Integración con GitHub → github.com/Dokploy/dokploy

Building agent skills from scratch is a grind. We've been there. So we built the fix — and open-sourced all of it under MIT. PDF, Excel, PPTX, DOCX, and more. Use it, fork it, PR it. Intelligence with everyone. Github Repo → github.com/MiniMax-AI/ski… Try online → agent.minimax.io

Builders’ Challenge #4 is LIVE! This edition we’re building AI agents with @elizaOS and deploying them on Nosana 🤝 🏆$3,000 in prizes, top 10 get rewarded You’ll walk away with real experience on one of the fastest growing agent frameworks and a deployed project to show for it. 📅 Deadline April 14 Submit here → superteam.fun/earn/listing/n…

$100K in rewards are up for grabs for early-stage teams building onchain products across agentic DeFi, tokenization and more. Arbitrum’s 8-week Mentoring Program starts April 13th. Get support across: - go-to-market - liquidity design - distribution & VC fundraising Plus infra credits and tooling support from @awscloud, @Alchemy, @Dune, @moonpay, @Quicknode and more. Register today: tally.so/r/aQdj2W

Calling all community builders 📣 We are hosting the largest Web3 & AI student hackathon, and applications to host a local hub are now live. We will select 30+ hubs worldwide to get involved with us. You will never regret it! Apply by April 10 👇 tally.so/r/vGBr8g

Need to try this

We're excited to announce duckdb-skills, a DuckDB plugin for Claude Code! We think the embedded nature of DuckDB makes it a perfect companion for Claude in your local workflows. The skills supported include: + read-file and query – uses DuckDB's CLI to query data locally, unlocking easy access to any file that DuckDB can read. + read-memories – a clever idea to store your Claude memories in DuckDB and query them at blazing speed. These are powered by two additional skills: + attach-db – gives Claude a mechanism to manage DuckDB state through a .sql file linked to your project. + duckdb-docs – uses a remote DuckDB full-text search database to query the DuckDB docs and answer all of your (and Claude's own) questions. github.com/duckdb/duckdb-…

We’re launching a brand new, full-stack vibe coding experience in @GoogleAIStudio, made possible by integrations with the @Antigravity coding agent and @Firebase backends. This unlocks: — Full-stack multiplayer experiences: Create complex, multiplayer apps with fully-featured UIs and backends directly within AI Studio — Connection to real-world services: Build applications that connect to live data sources, databases, or payment processors and the Antigravity agent will securely store your API credentials for you — A smarter agent that works even when you don't: By maintaining a deeper understanding of your project structure and chat history, the agent can execute multi-step code edits from simpler prompts. It also remembers where you left off and completes your tasks while you’re away, so you can seamlessly resume your builds from anywhere — Configuration of database connections and authentication flows: Add Firebase integration to provision Cloud Firestore for databases and Firebase authentication for secure sign-in This demo displays what can be built in the new vibe coding experience in AI Studio. Geoseeker is a full-stack application that manages real-time multiplayer states, compass-based logic, and an external API integration with @GoogleMaps 🕹️

10 aws whitepapers every cloud engineer should read 1) the well-architected framework: the standard for cloud systems. learn to build scalable infrastructure. ↳ docs.aws.amazon.com/wellarchitecte… 2) serverless architectures: a real-world example for working with lambda. focus on event-driven logic. ↳ docs.aws.amazon.com/whitepapers/la… 3) aws security best practices: this is a must for shared responsibility. ↳ docs.aws.amazon.com/whitepapers/la… 4) microservices on aws: learn how to build, deploy, and scale decoupled services. ↳ docs.aws.amazon.com/whitepapers/la… 5) disaster recovery of workloads: ensure business continuity through proven DR strategies. ↳ docs.aws.amazon.com/whitepapers/la… 6) aws cost management: master the art of optimizing cloud spend and visibility. ↳ docs.aws.amazon.com/whitepapers/la… 7) building data lakes on aws: explore big data storage and analytics at scale. ↳ docs.aws.amazon.com/whitepapers/la… 8) machine learning best practices: a guide for developers to build and tune ML models. ↳ docs.aws.amazon.com/whitepapers/la… 9) containerized microservices: how to manage orchestration with ECS and EKS. ↳ docs.aws.amazon.com/whitepapers/la… 10) migration at scale: the blueprint for moving massive workloads to the cloud. ↳ docs.aws.amazon.com/whitepapers/la… truth is, watching tutorials will only get you so far. you can memorize all the service names you want. but to get hired and become a pro cloud engineer, you need to build production-grade projects. period. i remember when i first started, the biggest frustration was finding projects that were actually realistic. watching is not doing. stop watching cloud videos. start doing cloud architecture. 🫡 these projects force you to deal with cost optimization, data persistence, and identity management, the stuff you'll face in a job. what's the one whitepaper from this list you're going to read first this week? let me know! • • • 🔔 follow me (piyush sachdeva) for more cloud learning tips ♻️ share so others can learn as well