​Theme

​Building with AI agents presents unique challenges and opportunities. In this meetup, we'll explore practical solutions, lessons learned, and real world insights for using agents to supercharge your software engineering workflows.

​Tentative Event Agenda

​​Tentative Agenda

• ​6:00 pm: Networking and Food

• ​7:00 pm: Welcome and Community Announcements

• ​7:05 pm: Sponsor Presentation from Datadog: Practical Observability for Agents and LLMs

  • ​Speaker: Marina Petzel, Senior GenAI Advocate at Datadog

• ​7:25 pm: Competitive Subjective Agent Evals

  • ​Speaker: Kai Ase Siren, Senior Software Engineer at Kapwing

  • ​Talk Description: I have an agent roles and personality system. I let Claude run evals with a subagent across 100 role and personality questions over 2 hours, and it came back 100% successful. Later I discovered: Claude had spent the entire 2 hours making the tests as easy as possible, so they'd all pass, and there wasn't ever any actual grading going on. So I had to figure out how to actually do evals, and now you will too!

• ​7:55 pm: Talk TBD

• ​8:15 pm: Networking

• ​9:00 pm: End of event

​​​Event Sponsors

• ​Datadog

​​Code of Conduct

​Please review and agree to adhere to our Code of Conduct to participate in our community.