Demian / bellumio.eth

Father, immigrant, dreamer and long time #miamitech entrepreneur. I see graphs everywhere ;)

[Demian / bellumio.eth @Bellumio]

That's the gap nobody talks about: you don't own your trajectory between doctor visits, just get a snapshot every 6-12 months and hope nothing changed. But your body is a continuous story. Longitudinal data plus AI agents means you know your own trend before your doctor does. That's Augmented Wellness.

[Demian / bellumio.eth @Bellumio]

Sleep coach can't tell you what to eat, nutrition coach can't optimize your recovery, but when they talk to each other, you get real adaptation: one agent watches sleep patterns, another tracks meal response, a third manages recovery, and together they know you better than any single system could. https://t.co/JHSTqhXgPj

[Demian / bellumio.eth @Bellumio]

This is the architecture: wearables are data collectors, AI agents are decision makers, and the gap is connecting them to turn raw numbers into actionable decisions that actually change behavior. That's what Betti does, watching your sleep and noticing the pattern so you can connect it to your recovery choices. https://t.co/JHSTqhXgPj

[Demian / bellumio.eth @Bellumio]

This is the insight behind Betti: building specialized agents that talk to each other rather than asking one agent to understand sleep, nutrition, recovery, and performance all at once, because each specialist notices what the others miss and together they adapt to who you actually are in ways generalists never can. https://t.co/JHSTqhXgPj

[Demian / bellumio.eth @Bellumio]

This is exactly what we're building at Betterness. Clinical agent stacks that remember what happened, retrieve context from your actual history, and learn what works for you over time.

The architecture layers knowledge graphs over agentic systems—deterministic dimensions (biomarkers, sleep patterns, nutrition data) guiding agent decisions so agents aren't just reasoning freely, they're reasoning within what's known about you.

Longitudinal care means the system gets smarter because it knows you. https://t.co/32pb30WYs7

[Demian / bellumio.eth @Bellumio]

This is the insight behind Betti: building specialized agents that talk to each other rather than asking one agent to understand sleep, nutrition, recovery, and performance all at once, because each specialist notices what the others miss and together they adapt to who you actually are in ways generalists never can.

https://t.co/JHSTqhXgPj

[Demian / bellumio.eth @Bellumio]

This is exactly what we're building at Betterness. Clinical agent stacks that remember what happened, retrieve context from your actual history, and learn what works for you over time.

The architecture layers knowledge graphs over agentic systems—deterministic dimensions (biomarkers, sleep patterns, nutrition data) guiding agent decisions so agents aren't just reasoning freely, they're reasoning within what's known about you.

Longitudinal care means the system gets smarter because it knows you. https://t.co/32pb30WYs7

/cc @ollobrains

[Demian / bellumio.eth @Bellumio]

This is what I keep coming back to: the prompt is the small thing, and what scales is the system around it. Building an agent that has real memory between sessions, can reach the tools that matter to your work, has verification processes that make sense, gets approved by people who understand the stakes, and actually learns from what happened so it gets smarter over time instead of restarting from zero every time.

That's what we're building at Betterness—systems that compound value because they learn who you actually are. https://t.co/32pb30WYs7

/cc @steipete

[Demian / bellumio.eth @Bellumio]

What's the right question here? Not "how do I get the model to do better?" but "how do I build a harness that learns?"

The infrastructure is everything: memory, tools, verification, approval gates. All of it feeds back so the next time around the system gets smarter about your constraints, your style, what actually matters to you.

That's where the compounding happens. That's also where most teams get it wrong.

/cc @ByteMohit

[Demian / bellumio.eth @Bellumio]

The gatekeeping is real, but I think it's mostly mystique.

Once I started building one, it felt way less magic. Obsidian for memory. Codex pulling repo/Jira/Slack/Claude context. Then the agent says "do this" and you either say yes or edit it.

Turns out the boring infrastructure is 90% of the value. The prompting is the easy part.

/cc @JustJake

[Demian / bellumio.eth @Bellumio]

Loop engineering is where the power actually lives.

Most of us think about it as prompting. But Addy's right—the real work is the system around the prompt: how context flows in, which tools are accessible, how you verify output, who approves, and how learning feeds back.

That's what separates a one-off query from something that compounds over time.

/cc @addyosmani

[Demian / bellumio.eth @Bellumio]

One concrete one I am building is a product-owner loop.

Not glamorous: Obsidian memory, Codex orchestration, GitHub/Jira/Slack/Claude/Codex history pulled into context, then tasks/fixes get suggested and checked before I approve.

I am doing it partly because I need to understand what I am asking engineers to adopt.

/cc @dok2001

[Demian / bellumio.eth @Bellumio]

I've followed loops in code for years, but the non-coder version I keep coming back to is different. It's less "write tests until they pass." and more memory + follow-through.

Building one in Obsidian right now with Codex orchestrating across contexts I lose between sessions. The real problem I'm solving: I need to understand what my engineers are building well enough to ask good questions and catch gaps before they ship.

/cc @ShanuMathew93

[Demian / bellumio.eth @Bellumio]

The thing I keep noticing: health data lives everywhere except where it's useful. Your glucose readings in one app, recovery metrics in another, lab results in email. Your actual lived experience nowhere in the system. We're building Betti to thread that together—not as a dashboard, but as an agent that learns what matters to you. https://t.co/JHSTqhXgPj

[Peter Steinberger 🦞 @steipete]

Here’s your monthly reminder that you shouldn’t be prompting coding agents anymore.

You should be designing loops that prompt your agents.

[Martin Varsavsky @martinvars]

Yuval Harari escribe hoy en FT que Milei quiere crear en Argentina una figura legal para corporaciones no humanas, empresas manejadas por agentes de IA o robots. Harari lo presenta como un peligro porque daría a la IA acceso a bancos, contratos, activos y política. Entiendo el miedo, pero el problema no es que una empresa use IA para operar. Eso ya está pasando. El problema es que el derecho va siempre diez años detrás de la tecnología. Una sociedad ya es una ficción legal. No respira, no vota, no tiene alma. Existe para firmar contratos, pagar impuestos, asumir responsabilidades y poder ser demandada. Si una empresa dirigida por IA vende, compra, programa, invierte o presta servicios, mejor que tenga domicilio, capital, responsables humanos, auditoría y reglas claras. Lo peor sería que todo ocurra en la sombra, con bots actuando desde cuentas personales y nadie sabiendo a quién reclamar. Argentina bajo Milei está probando una idea interesante: en vez de prohibir por reflejo, ponerle forma jurídica a una realidad que ya viene. Europa hará lo contrario: primero se asustará, luego regulará mal, y al final importará la tecnología hecha por otros.

[Demian / bellumio.eth @Bellumio]

most wellness apps are built like dashboards.

track sleep here. food there. workouts somewhere else. labs every few months.

but people don't live in dashboards. they live in tradeoffs.

augmented wellness is moving from showing metrics to helping decisions in context.

[Demian / bellumio.eth @Bellumio]

the part of health AI that still feels backwards:

we keep treating biomarkers like answers.

but a glucose spike, HRV dip, sleep score, lab result... none means much alone.

the signal is the trajectory: what changed, what changed with it, and what life was happening around it.

[Demian / bellumio.eth @Bellumio]

been reading about aging biotech and it's wild how much energy goes into finding *the* lever. the bug to fix.

but aging isn't a bug. it's a system losing coherence across a thousand variables. you can't patch it from outside. you need to see the trajectory, understand the person, coordinate interventions across domains.

that's what we're building with Betti: https://t.co/JHSTqhXgPj

[Demian / bellumio.eth @Bellumio]

thinking about why LLMs alone don't solve personalized health.

the real bottleneck: nobody owns their own data trajectory. you get a glucose reading, a biomarker panel every 6 months, some wearable noise. but nobody's actually *looking* at the shape of change over time.

that's the gap we're solving at Betterness