MilkStraw AI

Me vibe-coding weird stuff into the UI while @abderizik is trying hard to clean-up the FE code at @MilkStrawAI 😂

We just raised our seed round 🥛 I met @jawad_shreim & @anas_y_abdallah working on a small project and we clicked instantly. Months later we went our separate ways, but we all knew we had to build something together. Late 2023, we came back together and started @MilkStrawAI: optimize your AWS cloud in 10 minutes, save up to 50%. My AI background helped us build the recommender engine that powers our optimization. But I also taught myself Ruby on Rails and shipped our first version with the team in early 2024. As CPO, I became the glue. Translating between our business vision and technical execution, making sure we build what actually matters. We raised $600k pre-seed in 2024 to scale. And as we worked with more clients, we learned something: cloud isn't just expensive, it's hard to see. So we built observability into MilkStraw. Clients now manage all regions and resources from one tab. See more, save more. Optimization is polished. Now we're expanding. We also brought on incredible talent to help us get there: → @alihfadel, Founding Engineer → @zboon101, AI Engineer → @abderizik, Design Engineer → @Gyamm994, Founder Associate With this round, we're making MilkStraw the place you go to manage your cloud. Grateful to our investors, our customers, and to this team for believing in what we're building. Let's milk the cloud ☁️🥛

The quality of PR titles at @MilkStrawAI 😂 "Remove previous bugs and add new ones" Big changes coming up 🔥 Shoutout to @abderizik & @alihfadel for keeping things fun 🚀

⚙️ Automating changelog drafts v2 I’ve continued working on automating our monthly changelog drafts at @MilkStrawAI Last month I started with a simple idea: grab commit messages with git log and feed them into an LLM It worked, but I quickly realized that commit messages alone are too short and very technical. They don't usually capture the real context behind a change, which makes it harder for the LLM to write a meaningful changelog So I added a second source: PR descriptions PRs usually tell a clearer story of what changed and why. And since BugBot in @cursor_ai adds its own PR summary for every pull request, we suddenly had a lot more context to work with without any extra effort! To grab these PR descriptions, I’m just using a simple gh client command. Combined with the commit messages, the LLM now produces changelog drafts that are much clearer, more complete, and closer to how I would write them myself Small upgrade, big difference every month Small upgrade, saving hours of manually reviewing changes to write the changelog every month

I often tweak local config files like 𝚌𝚘𝚗𝚏𝚒𝚐/𝚎𝚗𝚟𝚒𝚛𝚘𝚗𝚖𝚎𝚗𝚝𝚜/𝚍𝚎𝚟𝚎𝚕𝚘𝚙𝚖𝚎𝚗𝚝.𝚛𝚋 or other files, but I never want to commit those changes Still, every time I run git status, they keep showing up and it drives me crazy! I just found a simple trick to stop that: 𝚐𝚒𝚝 𝚞𝚙𝚍𝚊𝚝𝚎–𝚒𝚗𝚍𝚎𝚡 ––𝚜𝚔𝚒𝚙–𝚠𝚘𝚛𝚔𝚝𝚛𝚎𝚎 <𝚏𝚒𝚕𝚎_𝚙𝚊𝚝𝚑> Now Git completely ignores my local edits And if I ever need Git to track the file again: 𝚐𝚒𝚝 𝚞𝚙𝚍𝚊𝚝𝚎–𝚒𝚗𝚍𝚎𝚡 ––𝚗𝚘–𝚜𝚔𝚒𝚙–𝚠𝚘𝚛𝚔𝚝𝚛𝚎𝚎 <𝚏𝚒𝚕𝚎_𝚙𝚊𝚝𝚑> Such a small thing, but it made my workflow so much cleaner

We first built @MilkStrawAI's savings tool as a copilot, giving smart recommendations to add/remove Savings Plans Clients hated it 😂 Too much maintenance So we went autopilot instead Now they just onboard, enable savings (EC2, RDS, etc.), and that’s it The system handles everything in the background. Zero maintenance. Zero hassle. 50% savings. Now the same people who disliked the copilot loved the autopilot 😂 Sometimes users want a copilot. Other times, they need an autopilot. Design by @jawad_shreim

Such an amazing event we had at @MilkStrawAI with @kajogo777 from @stakpak_dev Thanks for everyone who attended, and special thanks to George for the amazing simple and great session The best part for me was that he broke the hype around the "agents" by showing us how easy it is to build one @kajogo777 @alihfadel @anas_y_abdallah @ibraheemcodes @abderizik @zboon101