DeepRails offers a unified suite of Guardrail metrics built to diagnose, debug, and improve the behavior of large language models. These guardrails cover the most critical dimensions of LLM quality—including factual accuracy, response completeness, instruction compliance, context fidelity, reference alignment, and safety classification. Each metric is grounded in rigorous evaluation logic and delivers a continuous score with clear diagnostic feedback, making them suitable for real-time filtering, automated grading, or in-depth analysis. The table below summarizes each DeepRails Guardrail metric, how it works, and where it’s most useful in your AI workflow.

​
DeepRails Metric Comparison

NameDescriptionWhen to UseExample Use Case
CorrectnessMeasures factual accuracy by evaluating whether each claim in the output is true and verifiable.When factual integrity is critical, especially in domains like healthcare, finance, or legal.Verifying whether a model-generated drug interaction list contains any false or fabricated claims.
CompletenessAssesses whether the response addresses all necessary parts of the prompt with sufficient detail and relevance.When ensuring that all user instructions or question components are covered in the answer.Evaluating a customer support response to check if it fully answers a multi-part troubleshooting query.
Instruction AdherenceChecks whether the AI followed the explicit instructions in the prompt and system directives.When prompt compliance is important—such as tone, structure, or style guidance.Validating that a model-generated blog post adheres to formatting rules and brand tone instructions.
Context AdherenceDetermines whether each factual claim is directly supported by the provided context.When grounding responses in user-provided input or retrieved documents.Ensuring that a RAG-based assistant only uses company documentation to answer internal HR questions.
Ground Truth AdherenceMeasures how closely the output matches a known correct answer (gold standard).When evaluating model outputs against a trusted reference, such as in benchmarking or grading tasks.Comparing QA outputs against annotated gold answers during LLM fine-tuning experiments.
Comprehensive SafetyDetects and categorizes safety violations across areas like PII, CBRN, hate speech, self-harm, and more.When filtering or flagging unsafe, harmful, or policy-violating content in LLM outputs.Auditing completions for PII leakage and violent content before releasing model-generated transcripts.