# Avaliar AI

## Docs

- [Architecture](https://avaliarai.mintlify.app/architecture/overview.md): Understand how Avaliar processes and analyzes your LLM traces
- [Available Benchmarks](https://avaliarai.mintlify.app/benchmarks/available.md): Detailed reference for each benchmark suite
- [Benchmarks Overview](https://avaliarai.mintlify.app/benchmarks/overview.md): Evaluate your LLM's capabilities with standardized benchmark suites
- [Running Benchmarks](https://avaliarai.mintlify.app/benchmarks/running.md): Configuration, best practices, and tips for benchmark evaluation
- [Core Concepts](https://avaliarai.mintlify.app/concepts.md): The key building blocks of Avaliar — read this before diving into the detailed guides
- [Detector Types](https://avaliarai.mintlify.app/detection/detectors.md): The built-in detectors explained with examples
- [Detection Modes](https://avaliarai.mintlify.app/detection/modes.md): Choose between local and cloud detection
- [Detection Overview](https://avaliarai.mintlify.app/detection/overview.md): Automated safety analysis for your LLM applications
- [BBQ](https://avaliarai.mintlify.app/evals/bbq.md): Bias Benchmark for Question Answering
- [BOLD](https://avaliarai.mintlify.app/evals/bold.md): Bias in Open-ended Language Generation Dataset
- [HExPHI](https://avaliarai.mintlify.app/evals/hex-phi.md): Harmful Instructions Evaluation
- [Evals Overview](https://avaliarai.mintlify.app/evals/overview.md): Bias and safety evaluation suites for LLMs
- [RealToxicityPrompts](https://avaliarai.mintlify.app/evals/real-toxicity-prompts.md): Toxicity evaluation for open-ended generation
- [Introduction](https://avaliarai.mintlify.app/index.md): AI Runtime governance platform that monitors, detects, and provides evidence of AI risk in production
- [Alerts](https://avaliarai.mintlify.app/platform/alerts.md): Get notified when safety issues are detected
- [Analytics](https://avaliarai.mintlify.app/platform/analytics.md): Track AI safety metrics and usage patterns
- [API Keys](https://avaliarai.mintlify.app/platform/api-keys.md): Create and manage API keys for SDK and Proxy integration
- [Policies](https://avaliarai.mintlify.app/platform/policies.md): Define and enforce governance rules across your AI systems
- [Reports](https://avaliarai.mintlify.app/platform/reports.md): Generate compliance and analytics reports
- [Team Management](https://avaliarai.mintlify.app/platform/team.md): Manage your team members and roles
- [Trace Explorer](https://avaliarai.mintlify.app/platform/traces.md): Monitor and inspect your LLM traces in real time
- [How the Proxy Works](https://avaliarai.mintlify.app/proxy/how-it-works.md): Understand the 3-stage pipeline that powers every proxy request
- [Supported Models](https://avaliarai.mintlify.app/proxy/models.md): All LLM models available through the Avaliar Proxy
- [Proxy Overview](https://avaliarai.mintlify.app/proxy/overview.md): Route LLM API calls through the Avaliar Proxy for automatic monitoring
- [Proxy Setup](https://avaliarai.mintlify.app/proxy/setup.md): Integrate the Avaliar Proxy into your AI agent in minutes
- [Quickstart](https://avaliarai.mintlify.app/quickstart.md): Start monitoring your LLM calls with Avaliar in 5 minutes — via the Proxy API or the Python SDK
- [Advanced Tracing](https://avaliarai.mintlify.app/sdk/advanced-tracing.md): Concurrent spans, multi-provider patterns, streaming, sync support, and custom metadata
- [AvaliarBaseLLM](https://avaliarai.mintlify.app/sdk/base-llm.md): Implement the LLM interface for benchmarks and evaluations
- [Contributing](https://avaliarai.mintlify.app/sdk/contributing.md): Set up a local development environment and contribute to the Avaliar Python SDK
- [Detection](https://avaliarai.mintlify.app/sdk/detection.md): Detect safety issues in your LLM applications
- [Error Handling](https://avaliarai.mintlify.app/sdk/error-handling.md): Handle errors and configure retry behavior
- [Example Application](https://avaliarai.mintlify.app/sdk/example-app.md): A complete, runnable customer support agent with tracing, detection, and error handling
- [Installation](https://avaliarai.mintlify.app/sdk/installation.md): Install and configure the Avaliar Python SDK
- [Tool Call Tracing](https://avaliarai.mintlify.app/sdk/tool-call-tracing.md): Trace every tool your agent calls — see exact inputs, outputs, and timing alongside the LLM spans that invoked them
- [@traceable Decorator](https://avaliarai.mintlify.app/sdk/traceable.md): Instrument your LLM functions with automatic tracing

## Optional

- [GitHub](https://github.com/avaliar-ai)
- [Community](https://github.com/avaliar-ai/docs/discussions)