Lautaro Gesuelli
@lgesuelli_p
working on the ai spectrum http://pampa.ai | building http://llmnative.dev 🇦🇷 | professor
the winning workflow:
Sharing an overview of the trace reviewer we developed at @FieldDataInc , thank you to the @LangChainAI team for the feedback! Some key points: * soft clustering of traces (promptable) * reasoning model running in bg * hybrid UX for discovery Code and more details in 🧵:…
Ayer tuvimos una nueva edición de LLM Native en las oficinas de @lemonapp_ar. Tremendo evento, potenciado por las increíbles personas que participaron! 🚀 Gracias a todos los que forman parte de la comunidad y, como siempre, a @lgesuelli_p, @fpingham y @PetralliLucas por idear…
Builders in Argentina are on fire. The energy, the inspiring conversations, the hunger to build and collaborate, truly impressive. Huge thanks to the organizers for making it all happen, and for the invite (@unfarol @belgonzalezm @0xKoller @FaustoR0 @arielmathov) Grateful to be…
July 26, 2025 Vibe a Startup 🇦🇷
Nos vemos mañana @vibeastartup 🧉 Los ayudaré para que sus output tokens se conviertan en Startup.
MENTOR @lgesuelli_p Professor. LLM community leader. When it comes to breaking down complex ideas, he’s your best guide.
Gold! It shows how multi-agent architectures and context engineering (effective prompting + tool design) improve performance and speed in open-ended research tasks, where one-shot pipelines fall short. My takeaways: • Multi-agent systems shine when tasks require heavy…
New on the Anthropic Engineering blog: how we built Claude’s research capabilities using multiple agents working in parallel. We share what worked, what didn't, and the engineering challenges along the way. anthropic.com/engineering/bu…
we just dropped an open source GEO platform - full saas kit with db, payments, auth built with @supabase @autumnpricing @better_auth @DrizzleORM see how your website ranks in the top LLM providers 🔥 powered by firecrawl. fork it below 👇
Introducing FireGEO - our open source Semrush for AI 🔥 Monitor your website's presence on the leading AI search platforms and compare to all your competitors. A SaaS kit built with @aisdk, @supabase, @DrizzleORM @autumnpricing, @better_auth and more. Fork the example today 👇
We hosted another LLM-Native meetup at @lemonapp_ar — a space where we bring together founders, engineers, researchers, and AI enthusiasts building frontier products with llms. Full house again, with 200+ on the waiting list. We dug into real-world technical challenges through 8…
This is going to be 🔥. Hopefully you can attend
AI-generated code is overwhelming traditional CI/CD systems. Tomorrow, we’re hosting a virtual workshop to show how platform teams are using agentic workflows to stay ahead. What you’ll learn: • How to reduce fragility in your delivery pipelines • How to use LLMs for more…
@gptcrosa 's talk at the LLM-Native meetup hit a topic I’m also obsessed with: local AI models. Took me back to when we pushed hard on serving self-hosted <7B models for ownership — privacy, uptime, versioning — plus way lower costs and latency. Fine-tuning? Cheap if you need…
Acá están el blog post de la charla de 15 minutos que di sobre modelos locales en #llmnativedev collectednotes.com/alejandro/the-…
Tremendo el trabajo que hacen los chicos de #LLMNative. Un grupo de gente que no son humo, no enceguecidos por la tecnología y con una mirada amplia y diversa. Todas las lighting talks excelentes, y destaco la de Ivana Figueroa sobre las vulnerabilidades en MCP.
Si están usando AI para buildear, este es el discord: llmnative.dev
MCP servers en prod by @lemonapp_ar , Seguridad @Mercadolibre, El futuro del SEO by Fardo #llmnative
AI visibility también es esto: estar donde se construye el futuro. Presentes en #LLMnative las oficinas de @lemonapp_ar