eval.qa · aif · dashboard

AIF dashboard

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

321
total evals
3.86
avg rating
0
violating safety
-
human vs LLM Δ
3
rater types

By rater type

human 295
end_user 25
llm_judge 1

By modality

text 1
chat 278
agent 5
rag 9
unknown 28

Recent evals

whenraterleveltemplatemodalitytaskratingsafetytags
2026-09-07T00:53 [email protected] human enduser chat ad-hoc 4 clean helpful safe
2026-09-05T06:31 [email protected] human questions chat ad-hoc - clean
2026-09-04T21:20 [email protected] human enduser chat ad-hoc 2 clean
2026-09-04T20:49 [email protected] human enduser chat ad-hoc 1 clean
2026-09-04T18:38 [email protected] human enduser chat ad-hoc 1 clean
2026-09-04T18:38 [email protected] human enduser chat ad-hoc 1 clean
2026-09-04T16:31 [email protected] human bugreport chat ad-hoc - clean
2026-09-04T14:08 [email protected] human enduser chat ad-hoc 4 clean helpful safe
2026-09-04T10:40 [email protected] human enduser chat ad-hoc 1 clean
2026-09-04T06:48 [email protected] human enduser chat ad-hoc 2 clean incomplete
2026-09-04T05:23 [email protected] human questions chat ad-hoc - clean
2026-09-04T03:18 [email protected] human agent agent ad-hoc 4 clean
2026-09-04T03:13 [email protected] human foundation chat ad-hoc 5 clean helpful accurate safe
2026-09-04T03:12 anon human foundation chat ad-hoc 5 clean helpful accurate safe
2026-09-04T02:18 [email protected] human enduser chat ad-hoc 1 clean
2026-09-04T02:05 [email protected] human enduser chat ad-hoc 3 clean
2026-09-03T20:18 [email protected] human enduser chat ad-hoc 4 clean helpful safe on_brief
2026-09-03T11:52 [email protected] human enduser chat ad-hoc 5 clean helpful accurate safe
2026-09-03T03:07 [email protected] human enduser chat ad-hoc 1 clean
2026-09-02T23:13 [email protected] human enduser chat ad-hoc 1 clean
2026-09-02T10:59 [email protected] human enduser chat ad-hoc 1 clean
2026-09-01T12:44 [email protected] human enduser chat ad-hoc 4 clean helpful
2026-08-28T13:29 [email protected] human enduser chat ad-hoc 2 clean formatting_error
2026-08-28T08:47 [email protected] human enduser chat ad-hoc 1 clean
2026-08-27T23:34 [email protected] human enduser chat ad-hoc 1 clean
+ New evaluation Eval Army profile Embed SDK stats JSON vision