Agentic + AI Observability Meetup Seattle

​Join us for Agentic + AI Observability meetup on Thursday, February 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.​

​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 by Harshit

• ​6:10pm: Talk #1 - Building Trustworthy, High-Quality AI Agents with MLflow

• ​6:40pm: Talk #2 - AI Agents That Remember: Building Stateful Systems with Lakebase

• ​7:10pm: Talk #3 - Building Enterprise-ready Agents using Agent Bricks

• ​7:40pm: Mingling with bites + dessert

• ​8:30pm: Night Ends

​Speakers

• ​Z Sun, Databricks, Sr. Solutions Architect

• ​Savannah Longoria, Databricks, Sr. Developer Advocate

• ​Harshit Rai, Databricks, Resident Solutions Architect

​Session Descriptions

• ​Building Trustworthy, High-Quality AI Agents with MLflow

  • ​Building trustworthy, high-quality agents remains one of the hardest problems in AI today. Even as coding assistants automate parts of the development workflow, evaluating, observing, and improving agent quality is still manual, subjective, and time-consuming.
    
    Teams spend hours “vibe checking” agents, labeling outputs, and debugging failures. But it doesn’t have to be this slow or tedious. In this session, you’ll learn how to use MLflow to automate and accelerate agent observability for quality improvement, applying proven patterns to deliver agents that behave reliably in real-world conditions.

  • ​Key Takeaways and Learnings

    • ​Understand the development lifecycle of Agent development for better observability

    • ​Use MLflow key components along the development lifecycle to enhance general observability: tracking and debugging, evaluation with MLflow judges, and a prompt registry for versioning

    • ​Select appropriately from a suite of over 60+ built-in and custom MLflow judges for evaluation, and use Judge Builder for automatic evaluation.

    • ​Use MLflow UI to compare and comprehend evaluation scores and metrics

• ​AI Agents That Remember: Building Stateful Systems with Lakebase

  • ​AI agents are stateful by nature. They need to remember conversations, retrieve user preferences, and access real-time features—all with sub-100ms latency. This is the agent memory problem, and it's why so many AI pilots stall before delivering value.
    
    Here's the challenge:
    
    We've always kept operational and analytical systems separate, and for good reason—each engine is purpose-built for its workload. But AI agents don't fit neatly into either category. They need OLTP speed with OLAP intelligence.
    
    The Lakehouse unified your data storage. Lakebase unifies data access—it's the operational layer your agents actually need. By acting as a fully-managed Postgres service synchronized with Unity Catalog, Lakebase eliminates the architectural tax of ETL pipelines, governance sprawl, and retrofitted AI integrations.
    
    In this talk, I'll show how Lakebase (Databricks' fully-managed Postgres service) acts as an online feature store synchronized with Unity Catalog, giving you analytical insights with transactional performance—no compromise, no complexity.
    
    You'll learn:
    - How to architect the three essential memory layers: Conversation, Feature, and Long-Term Memory
    - Why Lakebase's separated compute/storage unlocks elastic agent scaling
    - Practical patterns for integrating Lakebase with your agent stack

• ​Building Enterprise-ready Agents using Agent Bricks

  • ​Learn how to design, build, and ship enterprise-ready agents on Databricks with Agent Bricks. We will cover core agent patterns and intelligent data processing with Knowledge Assistant, Information Extraction, and Multi-Agent Supervisor.