ClickHouse Meetup in Raleigh

About this event

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 **About the speaker** **Marc Klingen** is Co-Founder of **Langfuse** (YC W23), the open-source platform for tracing, evaluating, and improving LLM applications and AI agents. More than 50,000 companies use Langfuse, including 21 of the Fortune 50, and its SDKs are installed 50 million times a month.…