ClickHouse Nc Meetup Group

We're thrilled to bring ClickHouse to the Triangle Tech Talk series at Deutsche Bank’s US Technology Center!

# Frontier models are more capable than ever. So why do so many agents still fall over in production?
There's still a big gap between what a model can do in a demo and what an agent can reliably deliver at scale. Join Triangle Tech Talks for a practical session on why that gap exists and how teams are closing it.
About the talk
Marc Klingen, Co-Founder of Langfuse, will cover the real challenges of turning capable models into useful agents: tool use, reliability, evaluation, monitoring, and handling how real users actually behave.
Marc will also explain why the Langfuse team started building open-source observability and evaluation infrastructure, what has changed since then, and what state of the art looks like today. Using Langfuse as a working example, he'll show how to:

• 🔍 Trace agents in production so you can see what's happening inside them
• 🧩 Learn from failures and find out why an agent went wrong
• 📊 Turn real interactions into evaluation datasets that reflect how users behave
• 🔁 Keep improving prompts, models, tools, and agent architectures

The main idea: production agents aren't built once. They get useful through an ongoing loop of observing, experimenting, and iterating, and you'll use a lot of AI along the way to keep that loop running.
Who should attend

• AI and ML engineers building or running LLM apps and agents
• Platform, MLOps, and observability engineers
• Engineering leaders and architects taking agents from pilot to production
• Anyone curious about what it takes to make AI agents dependable