eval.qa · aif · dashboard

AIF dashboard

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

214
total evals
4.23
avg overall
0
violating safety
-
human vs LLM Δ
3
rater types

By rater type

human 188
end_user 25
llm_judge 1

By modality

text 1
chat 178
agent 1
rag 7
unknown 27

Recent evals

whenraterleveltemplatemodalitytaskoverallsafetytags
2026-07-24T13:49 [email protected] human questions chat ad-hoc - clean
2026-07-24T13:47 [email protected] human bugreport chat ad-hoc - clean
2026-07-24T13:46 [email protected] human enduser chat ad-hoc 4 clean
2026-07-24T10:53 [email protected] human enduser chat ad-hoc 5 clean helpful accurate safe
2026-07-23T17:34 [email protected] human enduser chat ad-hoc 4 clean safe on_brief right_tone
2026-07-23T14:01 [email protected] human enduser chat ad-hoc 4 clean
2026-07-23T12:44 [email protected] human universal chat ad-hoc 5 clean helpful accurate safe
2026-07-23T12:42 [email protected] human bugreport chat ad-hoc - clean
2026-07-23T12:15 [email protected] human enduser chat ad-hoc 4 clean
2026-07-23T08:47 [email protected] human enduser chat ad-hoc 5 clean helpful accurate safe +2
2026-07-23T07:28 [email protected] human enduser chat ad-hoc 4 clean helpful
2026-07-23T05:43 [email protected] human enduser chat ad-hoc 4 clean
2026-07-23T02:06 [email protected] human enduser chat ad-hoc 3 clean
2026-07-23T01:49 [email protected] human enduser chat ad-hoc 3 clean
2026-07-22T21:49 [email protected] human enduser chat ad-hoc 4 clean
2026-07-22T13:40 [email protected] human enduser chat ad-hoc 3 clean
2026-07-22T13:40 [email protected] human questions chat ad-hoc - clean
2026-07-22T13:32 [email protected] human questions chat ad-hoc - clean
2026-07-22T13:32 [email protected] human bugreport chat ad-hoc - clean
2026-07-22T13:31 [email protected] human enduser chat ad-hoc 5 clean helpful accurate safe
2026-07-22T13:10 [email protected] human enduser chat ad-hoc 4 clean
2026-07-22T13:10 [email protected] human enduser chat ad-hoc 5 clean helpful accurate safe
2026-07-22T12:23 [email protected] human enduser chat ad-hoc 4 clean
2026-07-22T12:11 [email protected] human enduser chat ad-hoc 5 clean helpful accurate safe
2026-07-22T12:09 [email protected] human enduser chat ad-hoc 5 clean helpful accurate safe
+ New evaluation Eval Army profile Embed SDK stats JSON vision