Agentic + AI Observability Meetup Seattle

​Join us for Agentic + AI Observability meetup on Wednesday, April 22 from 5pm - 8pm PST at the Databricks Bellevue office, an evening focused on agentic architectures and AI observability: how to design, ship, and monitor AI agents that actually work in production.

​This meetup is built for engineers, ML practitioners, and AI startup founders who are already experimenting with agents (or planning to) and want to go deeper into the tech. We’ll cover real-world patterns, failure modes, and tooling for building reliable agentic systems in the broader open-source ecosystem.

​Whether you’re at an early-stage startup or an established company, if you care about getting AI agents into production, and keeping them healthy, this meetup is for you.​

​You’ll hear from the following leaders in the AI space: Databricks and Anthropic.

​Why you should attend

• ​See real architectures: Learn how teams are designing agentic systems on top of data/feature platforms, retrieval, and tools, not just calling a single LLM endpoint.​

• ​Learn how to observe what agents are doing: Go beyond logs and dashboards to structured traces, evals, and metrics that help you understand and improve agent behavior over time.​

• ​Get hands-on with MLflow and observability tools: Watch live demos of MLflow, tracing integrations, and evaluation workflows for agentic systems.​

• ​Connect with other builders: Meet engineers, founders, and practitioners working on similar problems, swap patterns, and find collaborators and potential hires.​

​Agenda

• ​5:00pm: Registration/Mingling

• ​6:00pm: Welcome Remarks

• ​6:10pm: Talk #1 What Your Agent Did While You Weren't Looking (Ben Lehrburger, Applied AI, Anthropic)

• ​6:40pm: Talk #2 From Models to Agents: Building a Unified AI Governance Layer (David Nasi, Director, Product Management, Databricks)

• ​7:40pm: Mingling

• ​8:00pm: Night Ends

​​Session Descriptions:

• ​What Your Agent Did While You Weren't Looking

  • ​The best feeling in agentic AI: waking up to a finished PR. The worst: waking up to a prod database you don't recognize. Same capability, different architecture. This talk covers what separates "autonomous" from "unsupervised": auth, sandboxing, permission scoping, and the observability you need to reconstruct what happened at 3am. I'll share war stories from building on the Claude Agent SDK, including how we run agents internally at Anthropic today - what we've handed over, what still makes us nervous, and where we think agents are headed.

• ​From Models to Agents: Building a Unified AI Governance Layer

  • ​AI governance is no longer just about controlling datasets or approving models—it must extend to autonomous agents that access data, call tools, and take actions. In this session, we explore how governance evolves in the age of agentic AI and how Databricks unifies governance across the entire AI stack using Unity Catalog, AI Gateway, and MLflow. We’ll show how identity, permissions, lineage, and auditability are enforced consistently—from a user prompt all the way to downstream data access and external API calls—enabling organizations to scale AI safely without slowing innovation.

​Parking Info:

• ​Paid parking is available in the office building’s garage.

• ​Use apps like SpotHero to find nearby parking options.