chore(talks): Add recent ones

next/content/talks/2025_Botify.md

+---
+title: "\"1 Million Tokens Trust Me Bro\" - Testing Your Vendors' Claims Before They Break Production"
+description: "\"Our LLM supports 1M tokens!\" \"400K context window!\" Cool story, but does it actually work on production use-cases? When evaluating Gemini and GPT models for Algolia's Agent Studio, I chose to trust, but verify. This talk shows how anyone can empirically test vendor claims using simple experiments, reproducibility tests, and a healthy dose of skepticism. It doesn't take a PhD: just curiosity, and the stubbornness to run the same test 10 times."
+slides: alg.li/trust-me-bro
+date: '2025-11-19'
+context: "Botify EngWeek2025 Conference"
+event: https://engweek25.botify.com/
+---

next/content/talks/2025_DevCon.md

+---
+title: "The Fellowship of AI: Why you need both Galadriel and Gandalf to build great AI apps"
+description: "Everyone's building AI apps, but great ones require both Gandalf's technical innovation and Galadriel's user wisdom. You've seen the extremes: brilliant POCs with terrible UX, or beautiful experiences that lag behind latest capabilities. Join Maria Lungu (UX engineer) and PLN (Staff ML engineer) as they battle through real design trade-offs, showing how the friction between ML ambition and UX wisdom creates AI that users actually love."
+date: '2025-10-01'
+video: https://www.youtube.com/watch?v=AQWrJlqJiA8&pp
+context: "Algolia DevCon 2025"
+event: https://www.algolia.com/devcon/
+with: Maria Lungu
+withLink: "https://www.linkedin.com/in/angelamarialungu"
+---

next/content/talks/2025_MICES.md

+---
+title: "The Human Element: how we collaborate to build trustworthy AI"
+description: "In this talk, we share learnings from building together an AI-powered Shopping Guides feature for thousands of Algolia customers, bringing shopping guides to millions of end-users. The talk will focus not on the product we built, but rather on the friends we made along the way: how we learned to navigate this collaboration between UX experts and AI teams, each having different priorities and vocabularies. Two distinct perspectives, often complementary, sometimes at odds, on crafting AI shopping experiences that truly empower users."
+date: '2025-06-18'
+slides: https://alg.li/mices25
+video: https://www.youtube.com/watch?v=pnt-0pS-bNo
+context: "MICES: MIx-Camp E-commerce Search Conference, Berlin"
+event: https://mices.co
+with: Maria Lungu
+withLink: "https://www.linkedin.com/in/angelamarialungu"
+---

next/content/talks/2025_RenderATL.md

+---
+title: "\"This search result is perfect... but for whom?\" Questioning Alignment in AI Systems"
+description: "You're building a new feature and face the classic choice: optimize for user goals or business metrics. Easy, right? Just balance them. But then AI enters the picture, and suddenly there's a third party with its own agenda. Who is this feature _actually_ serving? Could some frameworks help think about user goal alignment? How can you spot when systems optimize for the wrong goals? Because building features that users stick with turns out to be good business."
+date: '2025-06-12'
+slides: https://alg.li/renderatl25
+context: "RenderATL 2025, Main Stage"
+event: https://www.renderatl.com/
+---
\ No newline at end of file