Modern LLMs have 100k+ token contexts. 100 samples over 24h gives ~15 minute resolution while adding minimal token overhead. This lets the LLM see fine-grained patterns, short spikes, and accurately distinguish anomalies from normal behavior. |
||
|---|---|---|
| .. | ||
| builder.go | ||
| builder_test.go | ||
| formatter.go | ||
| formatter_test.go | ||
| trends.go | ||
| trends_test.go | ||
| types.go | ||