Professional "Vibe Coder." AI Engineer. Obsessed with MCPs. My favorite headless CMS is @strapijs. Embrace AI, code & create content around things I enjoy.
Las Vegas
Joined January 2019
- Tweets4.4K
- Following598
- Followers1.4K
- Likes4.4K
Pinned Tweet
Just updated my music knowledge base powered by @tan_stack and @strapijs to use the official Strapi MCP to expose my data to other services, when want to go beyond using local Ollama models.
repo for anyone interested: github.com/PaulBratslavsky/m…
Love how @strapijs and @tan_stack empower you to build things fast.
I consume a lot of music tutorials from YouTube and wanted to create a knowledge base to help me learn music. AI powered by Gemma 4. Working pretty well on my MacBook.
Paul Bratslavsky | formerly coding after thirty retweeted
The first Community Call is happening tomorrow at 9 am PT!
The legendary @thepixelgeek will take the lead on the show.
Register now to meet the Fimo agents: luma.com/8i0dsoht
Paul Bratslavsky | formerly coding after thirty retweeted
Been thinking a lot about AI disclosure for games, since it's been a hot topic.
Steam requires disclosure for player-facing content created with the help of AI tools, but says efficiency gains from AI development tools aren't the focus.
Let's say I'm making a tree mesh for my game.
Two obvious endpoints:
• I manually model it in Blender. No disclosure.
• I generate it using Tripo/Meshy. Disclosure.
Now let's interpolate from t=0 to t=1:
1) I model the tree, but use a Codex-written exporter.
2) I model the tree, but use Codex-written UV, LOD and geometry optimization tools.
3) I model the tree, but write some scripts, with Codex help, to automate branch placement, leaf distribution, etc.
4) I automate more of the modelling until I've written a procedural tree generator.
5) I design and write my own procedural tree generator, with Codex helping debug and optimize it.
6) I design the procedural tree generator, but Codex writes the implementation.
7) I give Codex reference images, ask it to suggest improvements to my design, then implement those suggestions myself.
8) Same as above, but Codex implements the suggested improvements.
9) I give Codex reference images and ask it to design and implement the generator itself.
10) I use that generator, manually selecting and tweaking parameters until I'm happy with the trees.
11) Codex operates the generator and chooses the parameters, but I review and approve the results.
12) Codex operates the generator, chooses the parameters, and selects which trees ship, without my involvement.
13) I ask Codex to operate Blender directly and create the trees.
14) I generate the trees using Tripo/Meshy.
Under a literal reading, at every point in that list, the player-facing content was "created with the help of AI tools".
At what point did this cross from AI-assisted development into AI-generated art?
Is this going to be the same for everyone?
Paul Bratslavsky | formerly coding after thirty retweeted
We completely revamped the Strapi Media Library ✨
- Folders are always in view 📁
- Finding and checking assets is faster 🔍
- It works on a tablet or a phone 📱
- Your AI agents can manage media now 🤖
- Images in rich text stop breaking on private buckets 🔒
- Replacing a file keeps it where it was 🔁
- Editors without settings access get a working Media Library ✅
- Deleting a folder respects asset permissions 🔐
Paul Bratslavsky | formerly coding after thirty retweeted
Redact started because I wanted our React sites to ship less JavaScript. Now we use it every day, and other people are shipping it in production too.
Same app, less JavaScript. Excited to bring it to more people.
Introducing TanStack Redact 🌴
A smaller runtime for your existing React app. Add it to your build config and ship less JavaScript without changing a single line of application code.
Works with TanStack Start, Vite, Vinext, and Next.js.
tanstack.com/redact
Paul Bratslavsky | formerly coding after thirty retweeted
1. Agents are going to eat the entire software development lifecycle
2. There is no upper bound to how much software we need
3. Tons of SaaS services are about to have their lunch eaten
In the future, software will be invisible.
A lot of people share cool game demos with a "look what I built" caption. Well, I didn't build this. I paid Claude to build it.
For educational purposes, I had it reverse engineer The Elder Scrolls IV: Oblivion, decompiling the game with REA and taking detailed notes.
Then, working from those notes, it built a brand-new game engine that runs the game in a web browser.
It didn't copy the original code. It reimplemented everything from scratch in TypeScript and Three.js, and adapted the original assets to work with the new engine.
To play it, you need to own the original game, since the assets are streamed from your copy.
It's kind of wild. I now have something that looks like a complete game running in Three.js.
And yes, I did learn something along the way. I asked Claude to create educational material to teach me about reverse engineering as we went.
Still, I didn't make this game. I appreciate AI, and it's amazing. It lets us reach beyond what we could do on our own.
But if you're truly curious, learn the underlying skills.
That's why, a while back, I bought @iced_coffee_dev's Three.js course.
AI can probably build every game I can imagine, but I think the real joy is understanding how it's done and having the skill to do it yourself, even if you're not typing as much code by hand.
Think of it like music. Sure, I can use Suno to generate a song. But because I also learned music theory and how to play guitar (albeit poorly), I can hear almost any song and play it by ear.
So even when I create a song with Suno, I can still play it on a real instrument.
Code is the same way. I can use AI, but I want to know that if I'm ever broke and can't pay for Claude, or I don't have internet, I can still create things.
Anyway, rant over. Have a nice day.
Paul Bratslavsky | formerly coding after thirty retweeted
TanStack Start goes 1.0! This is huge! Congratulations team 👏
TanStack Start 1.0 is officially stable! 🎉
A full-stack web framework for React and Solid, already used to build millions of apps, from Fortune 500 companies to your favorite tools and weekend projects.
tanstack.com/start
Paul Bratslavsky | formerly coding after thirty retweeted
The wait is over! If you were looking for permission to use TanStack Start, this is it.
The only directive you need now is the one you give your agent:
"Use TanStack"
TanStack Start 1.0 is officially stable! 🎉
A full-stack web framework for React and Solid, already used to build millions of apps, from Fortune 500 companies to your favorite tools and weekend projects.
tanstack.com/start
What a time to be alive. AI slop at it's greatest, and I'm here for it.
I made a game that streams music and content from my YT channel, so as you play, I get views.
But I am sure there are better things I can be doing with my time.
Paul Bratslavsky | formerly coding after thirty retweeted
Actually @AlemTuzlak just TanStack AI-pilled me - it's *insanely* good. I can't wait to dive in there
Paul Bratslavsky | formerly coding after thirty retweeted
Code isn't some accidental bi-product of software, it's an exact set of instructions for the computer.
Saying "English is the new programming language" is cute, but obviously a bit of marketing fluff.
I say this as someone not "writing" code and only reading _some_ of the code.
Paul Bratslavsky | formerly coding after thirty retweeted
Here's a breakdown of 15 of the principles that drive my product development.
mega.dev/ship-without-readin…
Can't wait to be there and meet everyone in person.
Can't wait to hear you speak 💚@dantederuwe, @ErikCH, @_kaylasween, @vishnudhasan10, @thegounis, @nicodotdev, @isabelacmor, @codingthirty, @shaundai
Love @tan_stack and now TanStack Ai. So flexible and awesome. Pretty much using it in all my recent projects.
Turn your Strapi Content into AI Tools with MCP and TanStack AI
In this tutorial, Paul Bratslavsky shows how to connect AI clients to your Strapi content and build a local admin chat with TanStack AI and Ollama.
You’ll learn how to:
🔌 Connect Claude or Cursor to Strapi through MCP
🛠️ Write one healthcheck service and use it through REST, MCP, and the admin chat
💬 Ask questions about your content using a local model, with no API key required
🔐 Control which tools each client and admin user can access
👉 Follow the tutorial: strapi.link/4yYmvZW
Paul Bratslavsky | formerly coding after thirty retweeted
I'm telling you guys, you're sleeping on it.
If you don't feel FOMO you should be worried
Turn your Strapi Content into AI Tools with MCP and TanStack AI
In this tutorial, Paul Bratslavsky shows how to connect AI clients to your Strapi content and build a local admin chat with TanStack AI and Ollama.
You’ll learn how to:
🔌 Connect Claude or Cursor to Strapi through MCP
🛠️ Write one healthcheck service and use it through REST, MCP, and the admin chat
💬 Ask questions about your content using a local model, with no API key required
🔐 Control which tools each client and admin user can access
👉 Follow the tutorial: strapi.link/4yYmvZW
Yes. That is true. That is why I am excited about my presentation on TanStack AI and what I built at React Summit.
Also excited to have @AlemTuzlak to give us a presentation on TanStack AI at @strapijs
To be announced. 🙂
Paul Bratslavsky | formerly coding after thirty retweeted
GitHub actions are a super easy way to get started with software factories
1. Essentially free sandboxes for public repo's
2. You already have a login
3. Create tickets (pieces of work for the agent to do) as issues
4. Use labels to trigger actions, which create PR's
5. Actions can apply labels, which create loops
6. Cron jobs (albeit not very accurate) for running daily jobs
7. Simple observability for seeing what went wrong
Great for messing about with software factories before building them on your own infra