Browse skills

Langsmith Evaluator assesses LLM outputs against predefined criteria, streamlining feedback and improving model performance through structured analysis.

Eval Harness allows you to systematically test and evaluate AI model outputs against a defined set of criteria for consistent performance & reliability.

Build custom RAG agents quickly using Qodex AI's tool, defining data sources, prompts, and actions for tailored knowledge retrieval.

The Guardrails Reviewer analyzes your AI model’s outputs against predefined guardrails, ensuring safety and compliance – crucial for responsible AI deployment.

Validates Claude plugin functionality and responses against defined criteria to ensure accuracy and reliability.

Evaluates a core system’s performance against a predefined scorecard, identifying key strengths and weaknesses for targeted improvement.

Evaluates if a language model’s responses stay within defined boundaries, ensuring safety and relevance for reliable outputs.

RefoundAI's ai-evals automatically assesses AI model outputs against defined criteria, providing objective performance insights.