EvalOps unfiltered #2: Evaluating LLM-based applications

Join us for EvalOps Unfiltered #2, an innovative event series designed for AI teams tackling the real-world intricacies of evaluating LLM and agentic applications. 🚀

Why Attend?
In the realm of LLM applications and agents, even the smallest changes in prompts or context can lead to unexpected outcomes. If you're in the business of building with LLMs, you're aware that surprises often don't come with the best outcomes! That's why effective testing is essential.

What to Expect:
This event will focus on practical insights and collaboration rather than theoretical discussions. Our sessions will showcase speakers sharing the challenges they've faced, what has actually worked for them, and the lessons they've learned along the way.
✨ No panels, no pitches: just builders engaging in honest dialogue about what’s genuinely broken and strategizing on potential fixes.

🔧 Lightning Talks
Hear from experts including:

• Giulia van den Winkel, AI Conversation Designer @ GetYourGuide
• Rouven Glauert, Founder @ Lelia, previously Senior Applied Scientist @ Parloa: “You rerun your simulations - your results don't hold. Now what?”
• tbd

🧠 Breakout Sessions
Dive deep into specific challenges, share experiences, and discuss viable solutions with fellow builders in the field.

🍺 Enjoy some drinks while the conversations flow!
Whether you’re an AI engineer, a technical lead, a data scientist, or a product owner, you'll find valuable insights as we focus on making LLM & agentic applications reliable in practice.

🔗 Location: Berlin, Germany; further details will be provided upon registration.
📝 Note: Attendance is confirmed only through registration.
🏢 Hosted proudly by Rhesis AI in collaboration with AI NATION.
🎟️ Get your tickets here!