A live demo, with real runs in it. Start free to connect your own →

SupportBotQuality

App\Evals\SupportBotQuality

demo Six healthy weeks, then a drop. The last run is the interesting one.

83.1% ▼ 12.0 vs baseline
Latest score · 24 samples across 8 rows · 4 days ago
7 runs ―― baseline 95.1% now
Pass rate
75.0%
Cost, last run
$0.0071
Baseline
DACZHZPC
Jul 9
Test cases

8 cases · v1

View and edit →

Runs

Run Score vs baseline Environment Cost Duration
7CN4RVCP
Aug 20, 04:02 a50e928 · main
83.1%
24 samples
-12.0 ci $0.0071 4m 0s
47JP8EFZ
Aug 13, 10:02 bf07d53 · main
95.5%
24 samples
+0.4 ci $0.0143 4m 0s
XRVERDPZ
Aug 6, 10:02 7072baa · main
94.4%
24 samples
-0.7 ci $0.0143 4m 0s
8TB358SX
Jul 30, 10:02 4bbd68b · main
95.8%
24 samples
+0.7 ci $0.0143 4m 0s
QREP6GJY
Jul 23, 10:02 99e0194 · main
96.2%
24 samples
+1.1 ci $0.0143 4m 0s
Z8YQRQNB
Jul 16, 10:02 0b04ab6 · main
94.8%
24 samples
-0.3 ci $0.0143 4m 0s
DACZHZPC ★ baseline
Jul 9, 10:02 bd10bfe · main
95.1%
24 samples
reference ci $0.0143 4m 0s