> ## Documentation Index
> Fetch the complete documentation index at: https://docs.galileo.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Out-of-the-box Metric Categories

> Learn about the available out-of-the-box metric types and when to use them

Out-of-the-box metrics can be broken down into the following key categories, each addressing a specific aspect of AI system performance. You may benefit from using metrics from more than one category.

Galileo also supports [custom metrics](https://docs.galileo.ai/concepts/metrics/custom-metrics/custom-metrics-ui-llm.md) that you can implement in addition to out-of-the-box metrics.

The [Metrics Comparison](https://docs.galileo.ai/concepts/metrics/metric-comparison.md) provides a full list of the out-of-the-box metrics for each category.

## 1. Agentic performance metrics

[Agentic Performance Metrics](https://docs.galileo.ai/concepts/metrics/agentic/agentic-overview.md) evaluate how effectively AI agents perform tasks, use tools, and progress toward goals.

| When to Use | Example Use Cases |
| :- | :- |
| When building and optimizing AI systems that take actions, make decisions, or use tools to accomplish tasks. | <ul><li>Evaluating a travel planning agent's ability to book complete itineraries</li><li>Assessing a coding assistant's appropriate use of APIs and libraries</li><li>Measuring a data analysis agent's tool selection effectiveness</li></ul> |

## 2. Expression and readability metrics

[Expression And Readability Metrics](https://docs.galileo.ai/concepts/metrics/expression-and-readability/expression-and-readability-overview.md) assess the style, tone, clarity, and overall presentation of AI-generated content.

| When to Use | Example Use Cases |
| :- | :- |
| When the format, tone, and presentation of AI outputs are important for user experience or brand consistency. | <ul><li>Ensuring a luxury brand chatbot maintains a sophisticated tone</li><li>Verifying educational content is presented at the appropriate reading level</li><li>Measuring clarity and conciseness in technical documentation generation</li></ul> |

## 3. Multimodal quality metrics

[Multimodal Quality Metrics](https://docs.galileo.ai/concepts/metrics/multimodal-quality/multimodal-quality-overview.md) evaluate whether multimodal inputs and outputs (such as images and audio conversations) are usable and compliant for the task at hand.

| When to Use | Example Use Cases |
| :- | :- |
| When your AI workflow includes images or audio conversations and you need quality/compliance signals. | <ul><li>Gating blurry document photos before extraction</li><li>Enforcing brand rules on generated marketing images</li><li>Detecting turn-taking issues in voice agents (overlap/barge-in)</li></ul> |

## 4. Response quality metrics

[Response Quality Metrics](https://docs.galileo.ai/concepts/metrics/response-quality/response-quality-overview.md) help you evaluate how correctly, consistently, and in line with ground truth your AI follows instructions and answers user queries in any setting — with or without RAG (correctness, instruction adherence, ground truth adherence).

## 5. RAG metrics

[RAG Metrics](https://docs.galileo.ai/concepts/metrics/rag/rag-overview.md) help you evaluate retrieval and generation quality in RAG pipelines, including retrieval quality (chunk relevance, context relevance, context precision, Precision @ K) and generation quality (context adherence, completeness).

| When to Use | Example Use Cases |
| :- | :- |
| When evaluating how well retrieval systems find relevant context and how well models use that context to produce accurate, complete, and well-grounded responses. | <ul><li>Measuring factual accuracy in a medical information system</li><li>Evaluating how well a RAG system uses retrieved information</li><li>Assessing if customer service responses address all parts of a query</li></ul> |

## 6. Safety and compliance metrics

[Safety And Compliance Metrics](https://docs.galileo.ai/concepts/metrics/safety-and-compliance/safety-and-compliance-overview.md) identify potential risks, harmful content, bias, or privacy concerns in AI interactions.

| When to Use | Example Use Cases |
| :- | :- |
| When ensuring AI systems meet regulatory requirements, protect user privacy, and avoid generating harmful or biased content. | <ul><li>Detecting PII in healthcare chatbot conversations</li><li>Identifying potential prompt injection attacks in public-facing systems</li><li>Measuring bias in hiring or loan approval recommendation systems</li></ul> |

## 7. Text-to-SQL metrics

[Text-to-SQL metrics](https://docs.galileo.ai/concepts/metrics/text2sql/text2sql-overview.md) evaluate the accuracy and effectiveness of SQL queries generated by AI models from natural language inputs.

| When to Use | Example Use Cases |
| :- | :- |
| Use these metrics to evaluate the quality of SQL queries generated from natural language inputs. They're essential when building Text-to-SQL systems that need to produce syntactically correct queries grounded in your database schema. | <ul><li>A data analytics assistant where users ask questions in natural language and expect accurate query results</li><li>A customer-facing data analytics chatbot that must prevent injection attacks from user inputs</li><li>A business intelligence platform where ad-hoc queries must not impact database availability</li></ul> |