# Qualifire ## Docs - [Evaluate](https://docs.qualifire.ai/api-reference/endpoint/evaluations/evaluate.md): Evaluates given input, output, or messages using Qualifire's detectors. Supports checks for hallucinations, grounding, PII, prompt injections, content moderation, policy assertions, topic scoping, and tool use quality. - [Invoke](https://docs.qualifire.ai/api-reference/endpoint/evaluations/invoke.md): Invokes a pre-configured evaluation by its ID. The evaluation configuration (which checks to run, modes, assertions, etc.) is defined in the Qualifire dashboard. - [Compile Prompt](https://docs.qualifire.ai/api-reference/endpoint/studio/compile.md): Compiles a prompt by replacing variable placeholders ({VAR} or {{VAR}}) with the provided values. Returns the prompt with all variables substituted. - [Get Prompt](https://docs.qualifire.ai/api-reference/endpoint/studio/get.md): Retrieves a prompt with its messages and parameters. Supports lookup by prompt ID (cuid) or textId (deprecated). - [Introduction](https://docs.qualifire.ai/api-reference/introduction.md): An introduction to the Qualifire API - [Qualifire Concepts](https://docs.qualifire.ai/essentials/concepts.md): An introduction to the Qualifire main philosophy - [Evaluations](https://docs.qualifire.ai/essentials/evaluations.md): An introduction to the Qualifire evaluations - [Guardrails](https://docs.qualifire.ai/essentials/guardrails.md): An introduction to the Qualifire protection guardrails - [Notifiers](https://docs.qualifire.ai/essentials/notifiers.md): An introduction to the Qualifire notifiers - [Prompt Management](https://docs.qualifire.ai/essentials/prompt-management.md): An introduction to the Qualifire Prompt Management - [SDK](https://docs.qualifire.ai/essentials/sdk.md): Integrate Qualifire evaluations and tracing into your Node.js or Python application - [SLM Judges](https://docs.qualifire.ai/essentials/slms.md): Purpose-built Small Language Models for real-time AI evaluation, each fine-tuned for a specific task. - [Agent Tracing](https://docs.qualifire.ai/essentials/tracing.md): Gain deep visibility into your agent workflows and LLM interactions with OpenTelemetry-based tracing. - [Anthropic](https://docs.qualifire.ai/integrations/anthropic.md): Integrate your application with Anthropic - [Azure OpenAI](https://docs.qualifire.ai/integrations/azure.md): Integrate your application with Azure OpenAI - [Gemini](https://docs.qualifire.ai/integrations/gemini.md): Integrate your application with Gemini - [Hugging Face](https://docs.qualifire.ai/integrations/huggingface.md): Integrate your application with Hugging Face - [API keys](https://docs.qualifire.ai/integrations/integrations.md): Integrate your application with Qualifire - [Evals](https://docs.qualifire.ai/integrations/litellm-evals.md): Send LiteLLM logs to Qualifire for real-time evaluations, observability, and tracing - [Guardrails](https://docs.qualifire.ai/integrations/litellm-guardrails.md): Use Qualifire guardrails with LiteLLM to evaluate LLM outputs for quality, safety, and reliability - [OpenTelemetry](https://docs.qualifire.ai/integrations/litellm-otel.md): Send LiteLLM OpenTelemetry traces to Qualifire for observability and tracing - [n8n Integration](https://docs.qualifire.ai/integrations/n8n.md): Integrate your application with n8n - [OpenAI](https://docs.qualifire.ai/integrations/openai.md): Integrate your application with OpenAI - [Portkey](https://docs.qualifire.ai/integrations/portkey.md): Use Qualifire guardrails with Portkey to ensure your AI applications are safe, compliant, and high-quality - [Vercel AI SDK](https://docs.qualifire.ai/integrations/vercel.md): Integrate Qualifire with the Vercel AI SDK - [Guardrails and Evaluation for the Agentic Era](https://docs.qualifire.ai/introduction.md): Continuous evaluation, real-time guardrails, and pre-production agentic testing. Made for agents, RAG, and chatbots. - [Architecture](https://docs.qualifire.ai/rogue/architecture.md): Technical overview of Rogue's client-server architecture - [Using the CLI](https://docs.qualifire.ai/rogue/cli.md): How to run Rogue evaluations from the command line. - [AI Interviewer](https://docs.qualifire.ai/rogue/concepts/ai-interviewer.md): How Rogue uses an AI-powered interview to define the business context. - [Attack Techniques](https://docs.qualifire.ai/rogue/concepts/attacks.md): 30+ attack techniques for testing AI agent security - [Evaluator Agent](https://docs.qualifire.ai/rogue/concepts/evaluator-agent.md): The core component that interacts with your agent. - [Compliance Frameworks](https://docs.qualifire.ai/rogue/concepts/frameworks.md): Map security findings to industry standards like OWASP, MITRE, NIST, and more - [Evaluation](https://docs.qualifire.ai/rogue/concepts/policy-evaluation.md): How Rogue judges if an agent's response complies with a policy. - [Red Teaming](https://docs.qualifire.ai/rogue/concepts/red-teaming.md): Comprehensive security testing for AI agents using adversarial techniques - [Reporting & Observability](https://docs.qualifire.ai/rogue/concepts/reporting.md): Understanding the results of a Rogue evaluation. - [Risk Scoring](https://docs.qualifire.ai/rogue/concepts/risk-scoring.md): CVSS-based risk scoring for AI agent security vulnerabilities - [Scenario Generation](https://docs.qualifire.ai/rogue/concepts/scenario-generation.md): How Rogue creates test cases. - [Vulnerability Catalog](https://docs.qualifire.ai/rogue/concepts/vulnerabilities.md): Comprehensive catalog of 87+ vulnerability types tested by Rogue's red teaming engine - [T-Shirt Store Agent](https://docs.qualifire.ai/rogue/examples/tshirt-agent.md): A step-by-step example of how to use Rogue. - [How It Works](https://docs.qualifire.ai/rogue/how-it-works.md): Understand the workflow of the Rogue evaluation process. - [Introduction](https://docs.qualifire.ai/rogue/introduction.md): Welcome to Rogue - The AI Agent Evaluator & Red Team Platform - [Protocols & Transports](https://docs.qualifire.ai/rogue/protocols.md): How Rogue communicates with your AI agents - [A2A Protocol](https://docs.qualifire.ai/rogue/protocols/a2a.md): Using Google's Agent-to-Agent protocol with Rogue - [MCP Protocol](https://docs.qualifire.ai/rogue/protocols/mcp.md): Using MCO (Model Context Protocol) with Rogue - [Quick Start](https://docs.qualifire.ai/rogue/quickstart.md): A step-by-step guide to getting started with Rogue. - [Supported Models](https://docs.qualifire.ai/rogue/supported-models.md): Compatible AI models for use with Rogue evaluations ## OpenAPI Specs - [openapi](https://docs.qualifire.ai/api-reference/openapi.yaml) ## Optional - [Blog](https://qualifire.ai/blog)