People use traces from the start to just tell what's going on under the hood. And it's way more impactful in agents than in single LLM applications because in single LM applications, you get some bad response from the LLM. You know exactly what your prompt is. You know exactly what the context that goes in is because that's determined by code and then you get something out. In agents, they're running and and and repeating and so you don't actually know what the context at step 14 will be because there's 13 ...