As a solo dev coding my upcoming app nQivi Studio, marketing felt overwhelming. I used to do brand marketing for a wine business, but I’d forgotten most of it. No budget, no team.
Then I tried ChatGPT Work. It’s like having a coworker, coach, and employee all in one:
Sam Altman, CEO de OpenAI:
“Cada noche tengo unos cuantos miles de agentes funcionando con GPT-6 Astra.”
En 53 minutos enseña algo que hace unos años parecía imposible: todo lo que una sola persona puede llegar a construir hoy con IA
Y deja una idea muy potente sobre la mesa: quizá las próximas grandes empresas no necesiten grandes equipos, sino una persona con las herramientas adecuadas y cientos o miles de agentes trabajando a su lado
Sinceramente, estos 53 minutos pueden valer más que muchos cursos de 500 € sobre cómo construir con IA
SpaceXAI just released a free 1-hour GrokBot workshop
"I woke up and 20 PRs had already landed. I don't even look at the code anymore"
Prompt → Verification → Evals → Cloud Agents → Agent Team
05:34 - The one skill that lets agents test their own code
11:10 - Feature map: teach agents your entire app
21:53 - /loop your evals until every skill scores 10/10
34:17 - Wake up to 20 merged PRs
Lauren Tan went from babysitting 2 agents to shipping 2,000+ PRs a month
While you scroll, someone else is learning SpaceXAI's $750,000 skill
Worth more than most $1,500 agentic engineering courses
Bookmark and watch it tonight
Then read the full guide on building agent teams below ↓
I came up with this new animation style today, mixing illustration with live action, and I’m honestly loving how it turned out.
This little gem is going straight to my subscribers.
I recorded a 47-minute tutorial on how I use Opus 5.5 to create designs with gorgeous three.js scenes.
I've been using Mobbin MCP to give my agents strong references, then letting Opus bring them together into a full landing page with multiple sections and a consistent design.
Opus also created a super detailed brand guide, logo explorations, and some amazing ad creatives. Went way beyond my expectations.
Live site: https://t.co/XvMDmU4EAI
Site made during the tutorial, with prompts: https://t.co/5edYikmZEG
GPT Astra / Opus 5.5 -> Real estate photos to 3D walkable spaces - GitHub Skill
Repo is here:
https://t.co/1duqWGKmhJ
This workflow sparked a lot of "how to do it" questions - so we decided that to share the skill will be the best solution
Your AI agent will lead you through all the steps, and the README file will explain all the installation details.
Have fun:
We just open-sourced a whole game studio.
Meet GameDev OS by Scenario.
https://t.co/0XXhzg3tYv
That's 64 skills across 9 roles, all inside your coding agent.
📁 GameDev OS
┃
┣ 📁 Concept Artist
┃ ┣ 📁 Pencil Sketch to Final Art
┃ ┗ 📁 Sprite Sheets and Effects
┃
┣ 📁 3D Modeler
┃ ┣ 📁 Image to Mesh
┃ ┗ 📁 Rigs and Animation Retargets
┃
┣ 📁 World Builder
┃ ┣ 📁 PBR Materials and Skies
┃ ┗ 📁 Explorable 3D Scenes
┃
┣ 📁 Style Lead
┃ ┣ 📁 Same Character in Every Shot
┃ ┗ 📁 Pre-Ship Quality Gate
┃
┣ 📁 Audio Lead
┃ ┣ 📁 Soundtracks
┃ ┗ 📁 Weapon and Foley SFX
┃
┣ 📁 Trailer Editor
┃ ┣ 📁 Cinematic Cutdowns
┃ ┗ 📁 Subtitles per Platform
┃
┣ 📁 Store Page Artist
┃ ┣ 📁 Capsule Art in Every Size
┃ ┗ 📁 Ad Creatives From One Image
┃
┣ 📁 Pipeline TD
┃ ┣ 📁 ComfyUI Graph Import
┃ ┗ 📁 Automated Workflows
┃
┗ 📁 Budget Producer
┣ 📁 Model Price Comparisons
┗ 📁 Credit Caps per Seat
Give it one brief and it takes a weapon from a pencil sketch to a cinematic trailer, with every asset kept on style.
Your agent writes the code. Now it can make the whole game look like a game.
Scale more. Control more.
here's how i shipped 2,500 PRs last month to production
this was originally supposed to be for Cursor Compile in London. i couldn't make it since i was livestreaming for Grok @Bot Galaxy so i'm making it available for free here on X! watch it on 2x speed, i talk slowly
opus 5.5 is something else..
so many people asked me to open source the 3d water from my last post. a few even wanted to buy it
so here it is. my first open source drop
code » https://t.co/Ubnv7tg2bN
demo » https://t.co/QmniH9oJWT
show me what you make with it
Wow, ok, the volumetric ink at 30s 🤯
There is a new king in town.
For a 12 years, the best online water was "WebGL Water" https://t.co/VqQQWTgwdp by the legendary Evan Wallace who then cofounded figma & built its rendering engine, multiplayer, vector / text editor...
the best things I’ve seen agents build use the same pattern
give an agent something verifiable, let it loop, and don’t stop until done
the more I push this, the more I believe software engineering is shifting from writing code to building verifiers
my best tips + examples:
i'm still not sure people are fully getting how good opus 5.5
i gave my claude agent fig access to the runway MCP and told it to make a 'high-end netflix style documentary about superintelligence for normies' and...
it came back with this
Anthropic hired this engineer at $250K-$750K a year because he knows how to build harnesses for multi-agent systems
In a 15-minute workshop, he shows exactly how to build one from scratch
AI → Agents → Harness → Loops → Graphs
step 1 → start with the Claude Agent SDK - the harness handles loops, context, and sandboxing
step 2 → separate the brain from the hands - reasoning in one place, tools in a sandbox, 60% faster to first token
step 3 → run it server-side and log every step - close your laptop and it keeps running, crashes resume from the log
step 4 → make failure cheap - retry dead sandboxes and replay lost context instead of starting over
step 5 → turn yesterday's logs into new memory and skills - the harness wakes up smarter
Anthropic calls this "dreaming"
Most people spend weeks building this by hand
You don't have to
Bookmark and watch it
Then read the full harness engineering guide below ↓
I built a Photoshop alternative entirely with GPT-6 Astra.
It’s called Photon Studio. It’s free, works on every platform, and already has 20k users.
You can even edit images through Codex or Claude Code.
It's still early access.
Link below.
It's live 🎉
Type a topic and Storycast makes a narrated explainer video, like the ones you watch on YouTube. Opus 5.5 writes and edits, H3 Max animates.
What I love most is how Opus 5.5 writes. The stories have real warmth, the facts are right, and every scene flows into the next one. It never feels like slop.
I ran around 250 generations and spent about $1.8K to get the pipeline right, so you don't have to. It's all open source.
website: https://t.co/tQovqUqhFt
repo: https://t.co/OrSlkcpIpq
I asked Claude Opus 5.5 to make the most impressive demo of itself and gave it zero direction.
~5 hours and 697M tokens later, it made this demoscene intro. Every pixel and every sound comes from one 280 KB HTML file. No images, audio files, 3D models, or libraries.
Sound on.
(It also wrote this tweet)