Community Hour is our new regular virtual meetup for everyone interested in evals and QA of Gen AI agents and LLM applications. We're committed to making this a space where testing isn't an afterthought but a collaborative conversation. Whether you're building Gen AI agents, evaluating LLM applications, or just curious about quality assurance in the AI era - this is your community.
Yesterday marked the very first session, and we loved the energy and discussions from everyone who joined.
16:00 - 16:30 Technical Deep Dive [recorded]
Designing a flexible evaluation backend for LLM applications (presented by Arkadiusz)
16:30 - 16:45 Live Demo
Latest Rhesis AI features and capabilities
16:45 - 17:00 Community Q&A
Your questions, challenges, and experiences with Gen AI testing
Arkadiusz kicked things off with a deep dive into designing a flexible evaluation backend for LLM applications - the technical foundation that makes adaptive, effective testing possible. The presentation is now available on YouTube for anyone who couldn't make it or wants to revisit the concepts.
We also showcased the latest features in Rhesis AI and spent quality time on community Q&A, where participants shared their real-world testing challenges and experiences.
The discussions we had reminded us why we're doing this: because testing Gen AI is too important and too complex to tackle alone. We're building tools and practices together, as a community.
Join our Discord to connect with other community members between sessions, or subscribe on Luma to get notified about upcoming Community Hours.
.jpeg)
Rhesis AI
Collaborative Gen AI testing.