Founder @Grin_Mexico YC S18 @investovc (Rappi, Nowports, Solugen, BankMercury, Jeeves, StarkBank, Kovi +100)
🇧🇪🇺🇸🇲🇽🇧🇷🇮🇱
Joined July 2012
- Tweets2.8K
- Following911
- Followers4K
- Likes7K
💥
No one will use your app.
They’ll use an agent that uses your app.
Today, we’re launching Gigi MCP, giving Claude and ChatGPT the one thing they were missing: a network.
Your agent can now search everyone you know, tap into the networks of people you trust, and find warm paths to people you couldn’t reach before.
That investor you’ve been trying to meet. Your dream hire. The customer you can’t get in front of.
Just ask Claude or ChatGPT who can get you to them.
Jonathan Lewy retweeted
No one will use your app.
They’ll use an agent that uses your app.
Today, we’re launching Gigi MCP, giving Claude and ChatGPT the one thing they were missing: a network.
Your agent can now search everyone you know, tap into the networks of people you trust, and find warm paths to people you couldn’t reach before.
That investor you’ve been trying to meet. Your dream hire. The customer you can’t get in front of.
Just ask Claude or ChatGPT who can get you to them.
Jonathan Lewy retweeted
Who knows who is THE most valuable data in the world. But until now, it's been locked inside people's heads, and invisible to agents.
Meet Gigi: the trusted network that gives agents access to people.
We've turned that invisible network into a graph that agents can actually use. Your agent can now search everyone you know, ask the agents of people you trust who they know, and find real warm paths to almost anyone.
PS: you can plug Gigi directly into Claude or ChatGPT, giving your favorite agent something it's never had before: a network.
Go get access to anyone you want 👇
Hace 5 meses, un taxista en Madrid me dijo que los coches autónomos estaban a décadas.
Yo le dije que ya existían, pero que por regulación tardarían unos años en llegar a Europa, y sobre todo a España.
Me equivoqué. No eran años, eran meses.
¡Hola, Region of Madrid! 🇪🇸 We’re thrilled to announce that we’re coming to Spain, beginning with Madrid. This will be our first region in Spain and second in the European Union. We plan to launch fully autonomous ride-hailing in Madrid in 2027.
Sign up for future updates: waymo.com/waymo-in-spain
¡Hola, Comunidad de Madrid! 🇪🇸 Nos emociona anunciar que llegamos a España, empezando por Madrid. Esta será nuestra primera región en España y la segunda en la Unión Europea. Planeamos lanzar nuestro servicio de ride-hailing totalmente autónomo en la Comunidad en 2027.
Me considero un hombre de centro izquierda. Pero de la izquierda de los años 90.
Una izquierda a favor de la inmigración, siempre que fuera legal y respetara los valores sobre los que se construyó un país.
Una izquierda que quería mejor educación y mejor sanidad para todos. Las mismas oportunidades al principio, pero no la promesa del mismo resultado al final.
Una izquierda que defendía la libertad de expresión y la de elegir su religión. Libremente, pero respetando los valores y las reglas de la sociedad. No una izquierda que impone sus ideas por la fuerza o con disturbios. Ni una izquierda que acepta que se imponga una religión a los demás.
Soy de izquierda por sus valores y su moral, no por cálculo electoral.
Si hoy mis ideas se consideran de extrema derecha, no es porque yo haya cambiado. Es porque el panorama político se ha desplazado.
La etiqueta importa menos que la idea. Pero no son las ideas las que definen una moral. Son sus resultados.
La izquierda de hoy se proclama moralmente superior. Sin resultados que mostrar. Sin demostrarlo nunca.
Este modelo ya se ha probado. En Venezuela, en Cuba y en otros lugares. Ya sabemos cómo terminó.
Y aun así seguimos prometiendo lo mismo esperando un resultado distinto. Es la definición misma de la locura.
Je me considère comme un homme de centre gauche. Mais de la gauche des années 90.
Une gauche favorable à l'immigration, à condition qu'elle soit légale et qu'elle respecte les valeurs sur lesquelles un pays s'est construit.
Une gauche qui voulait une meilleure école et une meilleure santé pour tous. Les mêmes chances au départ, mais pas la promesse du même résultat à l'arrivée.
Une gauche qui défendait la liberté de s'exprimer et celle de choisir sa religion. Librement, mais dans le respect des valeurs et des règles de la société. Pas une gauche qui impose ses idées par la force ou par l'émeute. Ni une gauche qui accepte qu'on impose une religion aux autres.
Je suis de gauche pour ses valeurs et sa morale, pas par calcul électoral.
Si mes idées sont aujourd'hui classées à l'extrême droite, ce n'est pas moi qui ai changé. C'est la scène politique qui s'est déplacée.
L'étiquette compte moins que l'idée. Mais ce ne sont pas les idées qui définissent une morale. Ce sont ses résultats.
La gauche d'aujourd'hui se proclame moralement supérieure. Sans résultats à montrer. Sans jamais le prouver.
Ce modèle a déjà été testé. Au Venezuela, à Cuba et ailleurs. Avec les résultats que l'on connaît.
Et pourtant, on continue à promettre les mêmes choses en espérant un résultat différent. C'est la définition même de la folie.
I consider myself a man of the centre left. But the left of the 90s.
A left that supported immigration, as long as it was legal and respected the values a country was built on.
A left that wanted better schools and better healthcare for everyone. Equal chances at the start, but no promise of equal outcomes at the finish.
A left that defended freedom of speech and the freedom to choose one's religion. Freely, but with respect for the values and rules of society. Not a left that imposes its ideas through force or riots. Nor a left that accepts religion being imposed on others.
I'm on the left for its values and its morals, not for electoral reasons.
If my ideas are now labeled far right, it's not because I changed. It's because the political landscape shifted.
Labels matter less than ideas. But ideas don't define morality. Results do.
Today's left claims moral superiority. With no results to show. Without ever proving it.
This model has already been tested. In Venezuela, in Cuba, and elsewhere. We know how that turned out.
And yet we keep making the same promises and expecting a different result. That's the very definition of insanity.
💥
The hardest part of building finance agents is knowing when it's right and when it's wrong. And my guess from seeing thousands of vibe coded agents (if we can call them that?) is that it's somewhere in the 30% range today.
Ensuring accuracy within AI workflows is key for finance. And most of it comes down to separating deterministic from probabilistic work. Combining LLMs with code.
Once a workflow has been validated, the repeatable steps get parameterized and frozen so they run identically every time.
The non-deterministic reasoning stays confined to the narrow set of tasks it actually handles well. Some work falls outside both categories, because the answer isn't in the data at all.
That's what @Concourse_ai's agent context layer is for.
It sits across the systems where the reasoning actually lives, email, SharePoint, Slack, Drive, the ERP, and reads the memos and threads alongside the numbers, so an agent works from what your team has already decided.
When two sources conflict, the agent stops and routes the question to whoever owns the call, waits for the answer, then documents the exception and applies it the same way until the policy changes.
Every correction lands in the context layer as a new version, auditable of who decided & when.
Where does your team's judgment live right now? My guess is somebody's inbox.
What about your agents's judgement? My guess is you've outsourced it entirely to an LLM.
Making AI work in production is complex especially for finance teams!
Una sociedad está perdida cuando lo extremo empieza a sonar totalmente razonable y completamente absurdo al mismo tiempo.
A society is doomed the moment extreme ideas start sounding both completely right and completely insane.
Why is it acceptable for immigrants in the West to criticize Jewish self-determination in Israel (Zionism), while fiercely defending their own presence in Europe & America?
Borders, history & belonging apply to everyone—or no one. Applying this double standard is simple antisemitism.
¿Por qué es aceptable que inmigrantes en Occidente critiquen la autodeterminación judía en Israel (sionismo), mientras defienden ferozmente su propia presencia en Europa y América?
Las fronteras, la historia y la pertenencia aplican a todos o a nadie. Aplicar este doble estándar es simple antisemitismo.
“Software is the new employee.”
Forget headcount. The most productive “hire” you made this year probably runs 24/7, never calls in sick, and costs less than a mid-level salary.
The question isn’t if AI replaces roles — it’s whether your team is the one directing it, or being replaced by it.
