In progress — we're building and shipping updates often. More features and insights for LLM evaluation and AI agent observability are on the way.

TraceDogTraceDog
DashboardRead docs

Data pipeline

Eval source plane: registry, fetch pipeline, and lineage on ingested traces.

Operational health for the eval data plane in this trace sample.

Eval points30Traces with fetch_ms
Avg fetch ms2725.6In loaded sample
Cache hits0 / 30When reported
Quarantined rows0Sum in sample

Source fetch latency

From eval_lineage.pipeline_stats.fetch_ms on the last 40 loaded rows. Not a substitute for central metrics.

Recent trace activity

Newest rows first (pipeline-enriched traces when available).

  • 109c9ccc…claude-opus-4-6
    3206.7601670278236 ms
  • 38f2ab9f…claude-opus-4-6
    3206.7601670278236 ms
  • 7851c8b1…claude-opus-4-6
    3206.7601670278236 ms
  • 6022146e…claude-opus-4-6
    3206.7601670278236 ms
  • 663a18f1…claude-opus-4-6
    3206.7601670278236 ms
  • c0163c5a…gpt-5.4
    2433.6223749560304 ms
  • 1544d3b1…gpt-5.4
    2433.6223749560304 ms
  • 5f752ec8…gpt-5.4
    2433.6223749560304 ms
  • 2b01aec6…gpt-5.4
    2433.6223749560304 ms
  • 2267d3ea…gpt-5.4
    2433.6223749560304 ms