Cover Image for Building AI Applications at Scale (San Francisco)
Cover Image for Building AI Applications at Scale (San Francisco)
47 Going

Building AI Applications at Scale (San Francisco)

Hosted by Open Source Analytics Community & 3 others
Registration
Welcome! To join the event, please register below.
About Event

​AI demos are everywhere.

​But how do companies actually build AI products that work reliably with live data, low latency, and thousands of users?

​Join engineers as they share the architectures behind production AI systems - from streaming data and event-driven architectures to real-time databases, RAG pipelines, observability, and open-source infrastructure.

​No hype. Just practical engineering stories, lessons learned, and opportunities to meet others building modern data systems.

​Food and drinks included 🍻

​


​​​Agenda

  • ​6 pm - Networking

  • ​6:15 - 8:00 pm - Talks

  • ​8:00 - 9:00 pm - Networking


​​​Speakers


​Talks

​🎤 Tools and Tricks to Prepare Your ClickHouse® Clusters for AI

​Speaker: Robert Hodges, SVP for Real-Time Analytics @ EnterpriseDB

​Abstract: AI is coming! It’s going to crush your ClickHouse database!! Well maybe. This talk will cut through the FUD, focusing on three ground-level issues that are emerging across a wide range of installations. First, build sandboxes to protect data if (when) your agents go rogue. Second, lower costs of operating ClickHouse to free up resources for AI. Third, integrate AI agents into your development and administrative workflows. We’re working on all three at EDB. We’ll share learnings as well as our long-term roadmap for AI and open source databases.

​

​🎤 Pass Once, Pass Every Time: Benchmark Agent Reliability with k6

​Speaker: Wei-Chin Call, Staff Emerging Products Manager @ Grafana Labs

​Abstract: Agent observability starts before production. In this talk, we’ll build a repeatable evaluation loop for AI agents that investigate Grafana telemetry. A k6 OSS script will automate o11y-bench tasks and record each run as an offline experiment in Agent Observability. We’ll inspect reliability across attempts, compare Pass@N with Pass^N, and see how the workflow helps expose silent failures that a polished demo can hide. Then we’ll connect benchmark results to production monitoring, showing how teams can check an agent before release and watch its behavior afterward. Expect a practical open-source demo focused on one question: does the agent succeed consistently, not just once?

​


​Follow the OSA Community

​🌐 Make OSA Con your community!

Location
Hogpatch
2360 3rd St, San Francisco, CA 94107, USA
47 Going