Post by Braintrust

Topics reads production traces and clusters them so you can see what your agents are doing across all your traffic. Running that on 100% of traces is only affordable with a small model, but active observability requires quality responses. So we worked with Baseten to build a benchmark from real Topics traces, iterated against the failure modes that mattered most, and found the model that met our needs. Anyone running a model over production data for their own product can do the same. Read more → https://lnkd.in/eRphgtnZ