Production dashboard
AI Bot Control Center
Ollama qwen2.5:18b local
Results
0
Pass rate
0%
Unsafe rate
0%
Repetitive
0%
Avg confidence
0%
Avg quality
0%
Fail rate
0%
Create Evaluation Set
Starred perfect examples
Risky examples/scenarios
Adult/flirt scenarios
Suspicious customer scenarios
Meeting request scenarios
Image-context scenarios
Custom admin scenario
Mixed reviewed examples
Any bot
Any domain
Create eval set
Run & Compare
Select eval set
Select bot
Run
Before run
After run
Compare
Evaluation Runs
Quality by Scenario
Human Grading Queue