Artificial Intelligence Create Your Own AI Agent Eval Framework Working with large language models (LLMs) to build an AI agent, dealing with their inherent non-deterministic outputs can be a challenge.
Development Practices How to Evaluate an Unfamiliar Codebase in 15 Minutes You’ve got 15 minutes and an unfamiliar codebase to evaluate… what next? Try looking for these 7 red flags to help evaluate the health of the codebase.