tau-bench
Benchmark for customer service agent scenarios
Episodes
-
#6135: How Many Runs Does Your AI Eval Actually Need?Reruns shrink one kind of noise and leave another untouched — so where should your eval budget really go? -
#2404: What Tool-Calling Benchmarks Miss About Production FailuresBFCL, tau-bench, and Nexus each reveal different failure modes. None of them test what actually kills production agents. -
#2178: How to Actually Evaluate AI AgentsFrontier models score 80% on one agent benchmark and 45% on another. The difference isn't the model—it's contamination, scaffolding, and how the te...