The Inside Asana Blog - Company insights and updates • Asana

What this post added

This post describes the technical approach Asana took to build a custom LLM evaluation framework for their AI Teammates. It details the design of the framework, the metrics used for evaluation, and the challenges encountered in assessing LLM performance in the context of work management agents. The post highlights the importance of rigorous evaluation for ensuring the safety, reliability, and effectiveness of AI agents.