About us
A group for people interested in talking about and hacking on Kubernetes, Google’s solution for scheduling and orchestrating containers at scale. We’re excited about microservices, containers, the distributions that run them and the solutions that deploy, manage, and extend them. Any skill level is welcome; we’re all new to Kubernetes and we want to create an open, welcoming environment for other Kubernauts. Contact us if you are interested in speaking at or sponsoring the meet-up. We welcome content and demos.
Upcoming events
1
Aug: Agentic on K8s + swag
90 Broadway, Cambridge, MA, USKomodor is sponsoring food & bev this time - thank you Komodor!!
As usual:
- RSVP's close 48 hrs before the event. Please make it easy on us by RSVP'ing only if you intend to show up.
- Don't be late! You'll get locked out, and that's no fun!
===
Agenda
6:00 pm: food / drinks / networking
6:20 pm: Talk #1: Building Agentic AI with Mickael Alliel
7:00 pm: Who is hiring? Who is looking?
7:10 pm: Talk #2: TBD
7:50 pm: Talk #3: Build an AI agent, win a prize with Harout Parseghian
8:30 pm: FinishSpeakers & topics
1. How to Build Quality-Driven Agentic AI in Noisy Big Data Environments, Mickael Alliel, Komodor
Building reliable agentic AI systems in production environments presents unique challenges when dealing with massive, noisy datasets. This talk shares hard-won lessons from developing Klaudia, Komodor's AI agent that processes millions of Kubernetes events daily to deliver autonomous troubleshooting with 95%+ accuracy.
The fundamental challenge isn't LLM capability—it's building systems that maintain reliability when 90% of your data is noise. We'll explore why most agentic AI fails in production: hallucinations masquerading as insights, inability to validate reasoning chains, and the brittle nature of RAG systems when dealing with complex, interconnected failure modes.
This session covers practical know-how learned through painful production iterations: how to build validation frameworks that catch LLM errors before they reach users, architectural patterns for constraining problem spaces without losing effectiveness, and techniques for creating evidence-based reasoning that can be audited and improved systematically.
You'll learn specific strategies for LLM validation in high-stakes environments, including confidence scoring systems, multi-agent verification patterns, and iterative investigation loops that prevent runaway reasoning. We'll cover the hard-earned lessons about what works and what spectacularly fails when building trustworthy AI agents that must deliver accurate results rather than plausible-sounding explanations.
2. TBD, TBD
3. Build an AI agent, win a prize with Harout Parseghian
Harout was 1 of 2 winners of our first AI Agent Build Contest. He has created an agent that scans container images and then rationalizes the result, making a decision about whether to admit the images or not. Check it out! https://github.com/haroutp/k8s-supply-chain-agent
Harout can share a lot about his journey and his use of AI, including:
- the architecture of the agent
- the model calls made
- the tool calls made by the agent
- everything he learned building this
- everything that broke along the way!About our sponsors
Hybrid/Remote option
Sorry, this event is in-person only, so please join us in Cambridge!
89 attendees
Past events
43
Group links
Members
2,843
