> ## Documentation Index > Fetch the complete documentation index at: https://docs.dataframer.ai/llms.txt > Use this file to discover all available pages before exploring further. # Discovery > Investigate your AI traces at scale and surface patterns you didn't know to look for. When you don't yet know exactly what you're looking for, start with Discovery. **Discovery** is where you investigate your traces at scale. Describe in plain language what you want to look into, and Discovery scans your traces and groups related ones into findings, including patterns you didn't name. Pin the interesting ones to keep watching them in [Tracking](/findings/tracking). When you run a search you can set a few things: * **What to find:** describe the behavior in plain words. It does not have to be a failure. * **Sampling %:** run over a slice of your traces instead of all of them, to keep cost and time down. * **Trace-name regex:** limit the search to traces whose name matches a pattern. * **Model quality:** pick Cheapest, Balanced, or High-quality. Use a cost-efficient built-in system model to look for simpler patterns, or High-quality mode to catch issues that can be very hard to find. * **Explanations:** optionally get a short reason, with citations from the trace, for why each trace matched. Off by default since it costs more. ## Next steps Pin the patterns worth watching and get notified when they come back