💍 One Prompt to Rule Them All – Standing at the Edge of the Next Big Leap



I love where I am right now.

Not just geographically — though Barcelona is certainly not a bad place to be — but in the sense of having reached a point where my work, my passions, and my vision for the future finally converge.

For years, my commitment has been the same: to improve human existence.
Cognitively, through neurotechnology (Binaurapp).
Emotionally, through YANA – You Are Not Alone.
And, if possible, in every other way I can.

We, as humans, have a recurring opportunity: to let technology truly help us live better. That was always the point of technology. The person who invented the wheel didn’t do it to work more — they did it to make less effort, to free time for other things.

I’ve always stood by the idea that a tool is just a tool. Its power lies in how we use it.

Sting sings in If I Ever Lose My Faith in You:

“I’ve never seen no miracle of science that didn’t turn from a blessing into a curse.”

Much as I love Sting, I couldn’t disagree more. He may be thinking of atomic science turned into bombs — but that overlooks the fact that science has vastly improved quality and expectancy of life, far beyond any harm it has caused. We could debate this for hours (and perhaps we should, in another post), but wars and human misery existed long before modern science. The real conversation is about how humans choose to use their tools, not the tools themselves.

I believe in the miracle of science and technology — in how they have and will continue to improve human life. Blaming technology for our lack of progress in social and political skills is another matter, one that also deserves attention.

But let’s not get sidetracked into philosophy just yet.
The future of AI is here. It’s now.
And right now, we are standing at the door of a great leap — and I couldn’t be happier to be part of it.



The Crux of the Matter: Context

In AI, there’s a term: context window.
Technically, it’s the limit of how much information a model can “remember” or process at once.

You’ve probably noticed it in long conversations with AI: after a while, it starts going rogue — hallucinating, contradicting itself, or suggesting things that clash with what it told you just a few lines earlier.
When that happens, you’ve hit its context window.

Even with today’s larger context windows — and tools like Knowledge Graph Memory, mem0, Neo4j, or Letta — the way we structure context will determine whether we can ever truly say:




Imagine building an app in a single prompt. No further programming. No more “vibe coding” sessions to stitch the pieces together.

It’s possible — but only if the AI has the right context.
If it can trace elements of the implementation back and forth, maintain dynamic relationships, and reshape them as the situation evolves.

This is more than just having context.
It’s having the right parts of the right context, at the right time — grounded in solid knowledge but flexible enough to adapt while doing.

That’s the ultimate goal, and as part of our Financial Services Innovation team at Thoughtworks we´re making significant progress toward it.

Here’s why:
A prompt, no matter how well written, will fail when the task exceeds the model’s capacity to hold and apply relevant knowledge. Ask it for a fully functional stock market analysis app, and you’ll hit that wall fast.

The challenge isn’t more context.
It’s better context selection — exactly what your brain does automatically, without you even realizing it.



I love metaphors.

When my son was six, I taught him to skip stones across the water — “hacer patitos,” as we call it in Argentina.

As an adult, I can explain the physics behind it: the equation for lift, the role of angular momentum (spin), and the release angle. The more spin, the more skips. Simple, right?

But does a six-year-old need a full scientific breakdown to throw a stone?

If I gave this note to my kid would it have him skipping stones? 

L = I_z ω, with I_z ≈ (1/2) m R^2

Not at all.

I’m an over-informed kid raising a not-so-over-informed kid (by design), and I know for a fact that if I had started reciting formulas, I would have lost him before the first throw. The explanation had to be practical. Immediate. Something his body could feel before his brain could analyze.

I didn’t have to consciously debate this approach — it’s what many would call common sense.
And common sense, in this context, is our brain’s innate capacity to select the right context and adapt to it. It’s the same capacity that stops you from saying something you’ll regret five seconds later.

That, too, is context choosing.

So teaching a six-year-old to skip stones didn’t require the why.
It required the how:

  • Keep the stone flat.

  • Push with your index finger on release.

  • Let your wrist flick as you throw forward.

And just like that — he got it.

The funny thing? Even a brilliant physicist might miss the first throw while following the above equation if they’ve never done it before. Theory is one thing; applied context is another. Wormholes may be theoretically possible, but has anyone traveled through one?

That’s exactly where AI is right now:
It’s not about the amount of context it has — it’s about knowing which context is relevant, and how to apply it in the real world.





Why This Is Our Biggest Challenge (and Opportunity)

This is what excites me most in my work at ThoughtWorks right now:
We’re not just coding apps — we’re designing brains. We’re shaping minds. Artificial ones, yes, but minds nonetheless.

Our brains don’t work in tokens and probabilities. They are infinitely more complex, in ways even neuroscience can’t fully explain. And yet, year after year, AI gets closer to imitating some of the functionalities of human cognition.

With that in mind, we’re refining how context can be maintained, reshaped, and adapted — all while relying on a large, purpose-built knowledge base. In our case, it’s specifically designed for BFSI (Banking, Financial Services, and Insurance), which means precision, compliance, and reliability aren’t optional; they’re the core of the architecture.

The challenge isn’t just generating new tools or integrating existing ones. It’s cracking the routing and architecture that connect the right nodes at the right time — continuously, reliably, and without losing context.

Think of the human brain: it takes roughly 18 years, in a healthy individual, to develop the neural connections needed for its full potential. So how “old” is our AI child?

If AI is in its teenage years, we know what that means in human terms: mental rewiring. The brain reshapes itself in ways we’re only beginning to understand. Much of what desperate parents interpret as erratic, rude, or impulsive behavior is simply neurons reconfiguring their pathways.

And memory? Neuroscience is finding it’s not linear, nor purely graphical, but constructive. We rebuild our memories as narratives, mixing “facts” with interpretation. In other words: we hallucinate far more than we think — and we accept those hallucinations as truth.

The human brain after teenage-hood finally rewires to a context selection ace, that will allow it to choose, behave, act in the most beneficial way for it´s own preservation and eventual success. If you think about it, most of adulthood is just proper context selection.

The big leap ahead is about rewiring and re-routing AI architectures so they can handle context in a way that’s closer to how the human brain does it — flexible, adaptive, and self-correcting.

Whoever masters that will shape the future of AI.



My Path Here

I didn’t get here through a perfect plan.
I got here through detours.
Twenty-five years in professional music industry. Five years in neuroscience research. A pandemic that shut everything down. A full career reset at a fullstack bootcamp.

Out of that came Binaurapp, my neurotech project born from my theory of Moving Binaural Waves, and YANA, a non-profit emotional support app. Both built without a budget, with AI as my first “co-founder.”

Through trial, error, and relentless curiosity, I learned that constraints can be a gift. They force you to innovate. To think like water finding its way through rock.

And now?
I’m standing here, part of a global team at ThoughtWorks, working on problems that didn’t even exist when I started my career — and loving every second of it.


The Leap Ahead

We’re not far from the moment where “one prompt to rule them all” is real.
Where anyone, anywhere, can turn an idea into an application, a business, or a movement — without touching a line of code.

It’s not magic. It’s context.
And when we crack it, the distance between thought and creation will collapse.

Until then, I’ll be here, throwing stones across the water, teaching AI how to skip.






Comments