Albert Vila

Building software and BJJ addict🤓

[Albert Vila @Albertvilaa_15]

Such a great video for learning and understanding agentic engineering!!

[Kun Chen @kunchenguid]

many people asked me to make a video about my complete agentic engineering workflow

excited to share it's finally here!!!

it took me about 20 hours in total to record this 45 minutes of walkthrough - it covers everything i do to ship production quality code at an average 40+ PRs/day velocity

hope this can be a useful reference to everyone exploring good ways to use AI. and would appreciate a reshare with anyone you think might benefit from this!

enjoy! https://t.co/oA0UCrBvqo

[Patrick Collison @patrickc]

New from Stripe Economics: The Age of the Solopreneur

https://t.co/GTS8jEcK5z

[jesus monleon @jemonleon]

Una de las cosas q estoy muy de acuerdo con el podcast de ayer de Jon Uriarte, hay gente joven crack dispuesta a comerse el mundo (no hace falta q sean mckinsey o jpmorgan), y esos los quieres contigo, solo se trata de encontrarlos.

[Albert Vila @Albertvilaa_15]

I'm building the AI solution for non professional bjj competitors who want a personalized training plan and a good competition prep

Any Bjj fighters here?

[Albert Vila @Albertvilaa_15]

Set up de Agentes de IA. Empieza por uno simple como un daily brief.

Creación de visuales con IA, short-form videos.

Distribución. Cuando construir es más fácil que nunca la atención es el bottleneck.

Hardware + IA. Pulseras de whoop, google fitbit, gafas meta...

[Albert Vila @Albertvilaa_15]

¿Qué respondéis a alguien que os pregunta cómo aprender IA?

Mi respuesta es, investiga sobre

[Albert Vila @Albertvilaa_15]

@itsalexvacca @MichLieben Linkedin

[David Roberts @recap_david]

I don't think people understand what this actually means.

Every application on earth can now build an agent that teaches ITSELF how to use the application through the UI.

Not through API integrations. Not through documentation. Through the actual interface, the same way a human learns.

Here's the loop:

You define what success looks like (an eval). You point Claude at your application via Computer usage. Claude tries to complete the task through the UI. It fails. It writes what it learned to a skill file. It tries again. Recursively. Hundreds of times.

This is Karpathy's auto-research method applied to software usage.

Let me make this concrete.

I built a company called CoinLedger — crypto tax software, ~1 million users. The product is powerful but complicated. Users have to import wallets, classify transactions, handle edge cases, and generate accurate tax reports. The learning curve is our single biggest challenge.

With Claude computer use, I can hand it public wallet addresses and CSV files and say: use CoinLedger to produce an accurate capital gains report with no errors.

Claude opens the app. Navigates the import flow. Hits an error. Documents the failure. Adjusts. Tries again.

Each cycle produces better skill files. Each skill file captures how to properly use a specific part of the app. After enough iterations, Claude has built a complete agent harness — a set of instructions that lets it use CoinLedger as well as our best power user.

Then I ship that agent to every user who struggles with the platform.

The biggest friction in a million-user product, solved by an AI that grinded through the learning curve so humans don't have to.

Now multiply this across every complex application. Every SaaS product with a steep onboarding curve. Every enterprise tool where 90% of users touch 10% of features.

The first applications that build these recursive agent harnesses will compound in ways their competitors can't catch.

[Albert Vila @Albertvilaa_15]

@maverickecom Me

[Albert Vila @Albertvilaa_15]

Actualització de Claude quasi diària, això en condicions normals és impossible.

La IA s'està creant a ella mateixa.

El futur ja és aquí senyors😉

[Claude @claudeai]

Your work tools in Claude are now available on mobile.

Explore Figma designs, create Canva slides, check Amplitude dashboards, all from your phone.

Give it a try: https://t.co/hwPB3zlk0w

[Albert Vila @Albertvilaa_15]

@damienghader @Lovable General

[Gerard Giménez Adsuar @gmnzgerard]

https://t.co/q5iYrujGPt

[Albert Vila @Albertvilaa_15]

Dels millors comptes actuals per descobrir tips de Claude Code👀

[Lydia Hallie ✨ @lydiahallie]

You can now set effort level in skills/slash commands!

This controls how long the model thinks before answering, and overrides your session default

[Albert Vila @Albertvilaa_15]

És interessant veure com Lovable està pivotant.

Quan construeixes no només has de fer l'MVP, has d'analitzar dades, crear presentacions, marketing...

Aquesta no és només una nova actualització, és l'inici del camí cap a un co-founder que et permet fer tasques més generals.

[Anton Osika @antonosika]

Introducing Lovable for more general tasks.

Lovable has always been for building apps. Today it also becomes your data scientist, your business analyst, your deck builder, and your marketing assistant.

This is a big step toward what Lovable is becoming: a general-purpose co-founder that can do anything.

See examples below.

[Albert Vila @Albertvilaa_15]

@maverickecom System

[Albert Vila @Albertvilaa_15]

@spwfeijen Make

[Albert Vila @Albertvilaa_15]

@Zephyr_hg NEWS

[Albert Vila @Albertvilaa_15]

@michelleefang Merry Xmas!!!

[Albert Vila @Albertvilaa_15]

@Jacobsklug @Lovable Agency

[Albert Vila @Albertvilaa_15]

@itsedaxe 85