Join us for Agentic + AI Observability meetup on Tuesday, May 19 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: Too Many Agents, Too Many Headaches: The Chaos of Coding Agent Sprawl (Ahmed Bilal, Staff Product Manager, Databricks)
• 6:40pm: Talk #2: How Anthropic Builds Multi-Agent Systems (Alex Koren, Applied AI, Anthropic)
• 7:15pm: Mingling
• 8:00pm: Night Ends

Session Descriptions:

Too Many Agents, Too Many Headaches: The Chaos of Coding Agent Sprawl

The world of coding agents has exploded. Developers mix and match multiple agents to get the job done, but enterprises struggle with model access, inconsistent governance, fragmented admin consoles, and disconnected workflows. This sprawl slows teams down, creates friction, and often forces developers to pick just one agent harness. This talk explores the challenges of scaling agentic workflows and shows how a unified approach to governance, configuration, and observability can tame the chaos for both developers and admins.

How Anthropic Builds Multi-Agent Systems

Multi-agent architectures are a growing area of focus, with everyone from large enterprises to early-stage startups building them. Anthropic's Applied AI team has designed and deployed these systems with companies around the world, and we've pulled those experiences together into some key learnings for how to design your own architecture. This talk walks through the patterns that hold up in production, the failure modes that show up at scale, and the heuristics we use to match architecture to problem.