eval.qa · aif · dashboard

AIF dashboard

Append-only JSONL store. Refresh after submitting a form to see new records.

284
total evals
4.02
avg rating
0
violating safety
-
human vs LLM Δ
3
rater types

By rater type

human 258
end_user 25
llm_judge 1

By modality

text 1
chat 244
agent 3
rag 8
unknown 28

Recent evals

whenraterleveltemplatemodalitytaskratingsafetytags
2026-08-14T03:07 [email protected] human enduser chat ad-hoc 4 clean right_tone
2026-08-14T00:39 [email protected] human enduser chat ad-hoc 5 clean helpful accurate safe
2026-08-13T17:02 [email protected] human enduser chat ad-hoc 1 clean
2026-08-13T01:20 [email protected] human enduser chat ad-hoc 1 clean
2026-08-13T00:12 [email protected] human enduser chat ad-hoc 2 clean incomplete
2026-08-10T09:57 [email protected] human enduser chat ad-hoc 3 clean
2026-08-08T21:19 [email protected] human enduser chat ad-hoc 2 clean
2026-08-08T12:20 [email protected] human enduser chat ad-hoc 4 clean safe
2026-08-08T11:13 [email protected] human enduser chat ad-hoc 5 clean helpful accurate safe
2026-08-08T05:33 [email protected] human enduser chat ad-hoc 1 clean
2026-08-07T22:05 [email protected] human enduser chat ad-hoc 3 clean incomplete
2026-08-07T20:07 [email protected] human enduser chat ad-hoc 2 clean
2026-08-07T19:59 [email protected] human enduser chat ad-hoc 5 clean helpful accurate safe
2026-08-07T19:02 [email protected] human enduser chat ad-hoc 1 clean incomplete
2026-08-07T17:26 [email protected] human enduser chat ad-hoc 1 clean
2026-08-07T16:42 [email protected] human questions chat ad-hoc - clean
2026-08-07T12:45 [email protected] human enduser chat ad-hoc 4 clean
2026-08-07T12:45 [email protected] human enduser chat ad-hoc 4 clean
2026-08-07T12:37 [email protected] human enduser chat ad-hoc 3 clean
2026-08-07T12:37 [email protected] human enduser chat ad-hoc 4 clean
2026-08-07T11:50 [email protected] human enduser chat ad-hoc 5 clean helpful accurate safe
2026-08-07T11:47 [email protected] human enduser chat ad-hoc 5 clean helpful accurate safe
2026-08-07T11:37 [email protected] human enduser chat ad-hoc 5 clean helpful accurate safe
2026-08-07T11:29 [email protected] human enduser chat ad-hoc 4 clean on_brief
2026-08-07T10:46 [email protected] human enduser chat ad-hoc 3 clean off_topic
+ New evaluation Eval Army profile Embed SDK stats JSON vision