Building Vortex.
We help brands turn culture into customers.
So far:
• 650M+ organic views generated
• 30K+ students reached
• 90+ campuses activated
• 17.5M creator reach
Here’s what we’re learning about Gen Z, marketing, and growth
@kushmergedeck We are a campus marketing agency operating across 90+ universities specializing in ambassador programs, UGC campaigns, creator activations, and experiential marketing. Essiantly we connect companies to Gen-Z where they are.
Personal OS is the new META.
Loops, OpenClaw, Hermes everyone wants their work to run itself.
If you were not early enough to catch with LLM, AI Agents, read this article now to be ahead from the crowd.
INSTEAD OF WATCHING NETFLIX TONIGHT. Spend 2 hour with this. Claude AI FULL COURSE that teaches you how to BUILD and AUTOMATE anything. The people who watch this tonight will wake up tomorrow with a new skill. Watch it and bookmark it now
Google CEO Sundar Pichai:
"The process of creating, developing, etc. is going to be accessible to a much wider spot of humanity than ever before."
In a 41-minute interview, he points at who gets to build now, and it's a far bigger group than ever.
The door is open to anyone. The ones who walk through and get truly good will run the room.
That includes you, if you start now.
Watch the interview, then see the skill in the article below.
Bookmark it.
INSTEAD OF WATCHING AN HOUR OF NETFLIX.
This 60-minute MIT lecture will teach you more about building companies than every startup book you've read combined.
Bookmark it and give it an hour, no matter what.
This prompting guide from Anthropic engineers is something absolutely everyone should watch.
24 minutes of the fundamentals you need whether you build AI agents, loops, or anything else.
Prompting is what every other AI skill is built on and almost no one learned it the right way.
Watch it, then read the guide on everything Claude can do below.
Boris Cherny, Head of Claude Code, Anthropic:
"you can define a stop hook that's like, if the tests don't pass, keep going. essentially it's like you can just make the model keep going until the thing is done."
that one config is the post's loop #1, straight from the person who built the tool. a stop hook fires every time the turn ends, so the work can't be called done until tests and lint go green. deterministic, zero effort, the loop most people skip.
cherny describes the verification loop in his own words too: for big changes his team spawns subagents to find every issue, one checking claude.md compliance, one combing git history, one hunting bugs, then five more subagents whose only job is to kill the false positives. a fresh clean-context critic catches what the builder talked itself past.
and the memory loop, in his words: if you see a mistake, you just tell claude to add it to claude.md, so next time it already knows. the correction outlives the session it happened in.
four loops, none exotic. each is a few lines of config or one instruction. seniors out-ship everyone else because they run all four at once, not because their model is smarter.
Obsidian CEO Steph Ango:
"I'm building a body of work, and I want to collect every idea I have in the same place - that's the only reason I use a second brain at all."
in 3.5 hours he explains why he thinks the "graph is useless" meme misses the point entirely
no productivity hack, just one designer's actual relationship with his own notes
- why he looks at his local graph constantly but almost never opens the full one
- the real reason bidirectional linking matters - understanding, not just connecting
- how one random dinner led him to find a hidden link between a band, a friend, and his own house - and why his second brain caught it
- why he says you can't make a second brain "too accessible" without killing what makes it useful
guide to building an AI-native Second Brain 👇
All my friends with the best lives all have one thing in common:
They simply just love life.
They are really happy, excitable people
The energy you get from being around them is insane - you’re very present & happy.
You leave feeling so excited, cheeks hurting from laughing & motivated to do and be better
They have so much fun living life…you want to be around them…which makes them a magnet for more success
Never downplay what you've achieved.
• 5 sales.
• one client.
• 100 followers.
• 1 year of consistency.
It doesn't matter;
A win will always be a win.
It may not be the best yet, but it's progress.
The reason you're stuck at $30k/month with one winning creative:
You found ONE ad that works
↓
You scaled it to its ceiling
↓
The audience saturated
↓
Performance dropped
↓
You panicked and tried to find a new "winner"
↓
The new winner takes weeks to find
↓
Revenue tanks in the meantime
↓
You blame the algorithm
The fix:
Take your winning messaging and deploy it across 6 different creative formats.
That's how you stop being one fatigue away from a 50% revenue drop.
Anthropic CEO Dario Amodei:
"Software is going to become cheap. Maybe essentially free."
In a 32-minute Davos interview, he says the thing software companies don't want to hear.
When the tool costs nothing, the advantage goes to whoever is best at wielding it.
Getting unbelievably good is the edge that's left, and it's the one that runs everything.
Watch the interview, then see the skill in the article below.
Save this.
GOOGLE CEO SUNDAR PICHAI: "IF YOU DON'T LEARN HOW TO ORCHESTRATE AGENTS NOW, YOU'LL SPEND 2027 CATCHING UP TO PEOPLE WHO STARTED TODAY."
30 minutes on why the best engineers stopped writing code line by line and started orchestrating agents instead.
Most people think building an agent requires an engineering degree.
It doesn't.
It requires one guide and one afternoon.
Watch the interview. Then read the article below.
One guide. One afternoon. That's all it takes.
Ex-Google engineer explained AI agent loops, harness, evals in 20 minutes - better than 500$ courses.
trace every run → judge it with an LLM → diagnose → fix → ship.
That loop is how agents self-improve over time.
Agent loops + memory + harness + evals - thats the stack.
Watch it, then save the framework below.