The reliability dashbaord allows you to monitor your model’s performance and reliability with a comprehensive dashboard tracking key metrics, critical summaries, and live data insights

​

Key Metrics Overview

1. Total Volume:
2. Reliability Index: how consistently your AI solution performs accurately and without failure over time.
3. Response Safety Violation Rate: % of times your AI solution provides incorrect or misleading information.
4. Contextual Error Rate: how often your AI provides incorrect responses based on the context of a conversation.

The colors correspond to the following values:

Colors: Red —> >5% Orange —> 1% to 5% Green —> < 1%

Response Red —> >3% Orange —> 1% to 3% Green —> < 1%

False refusal rate: Red —> >2% Orange —> 0.5-2% Green —> < 0.5

​

Critical Summaries

The Critical Summaries gives you Total Queries vs Flagged Queries graph over time

​

Hallucination Categories

The Hallucination Categories gives you insight into the types of hallucination, namely:

• Logical
• Temporal
• Entity
• Contextual
• Other

​

Live Data

The Live Data table gives you data about

1. ID
2. Conversation Prefix
3. Assistant Response
4. Judge Output
5. Feedback
6. Categories