InfoQ: Elena Samuylova on Large Language Model (LLM) Based Application Evaluation and LLM as a Judge

Elena Samuylova dives into the nuts and bolts of keeping LLM-based apps honest—from picking the right evaluation metrics to setting up continuous monitoring pipelines—and even experiments with asking an LLM to grade its own output. She shares practical tips and tool recommendations to make sure AI-powered features stay reliable and drift-free.

If you want the full lowdown, check out the transcript link, subscribe to InfoQ’s Software Architects’ Newsletter, and explore upcoming events like the InfoQ Dev Summit and QCon series. Plus, don’t miss their weekly podcasts for more hands-on insights into software and AI.

Watch on YouTube