Template Library
The Library provides example Evaluators, Prompts and Tools which you can customize for your use cases.
To help you get started, we provide a library of example Evaluators, Prompts, Tools and Datasets. These examples have been designed for common AI use-cases like RAG, customer service, and agents. Each example can be duplicated to your workspace and customized for your use cases.
The Template Library includes various examples built for common AI application needs, including:
Pre-built evaluators for measuring semantic similarity, cost, latency, and other key metrics. Quickly assess your AI’s performance with ready-made evaluators that are suited for RAG. Measure response accuracy, prompt quality, and user satisfaction with tools designed for reliable and consistent evaluation.
Example prompts for common use cases including classification, question-answering, content generation, conversational agents, and RAG (Retrieval-Augmented Generation).
Ready-to-use tools for tasks like retrieval, data extraction, and calling external functions with JSON Schema function calling.
Example datasets for common use cases including classification, question-answering, and content generation.
Example agent templates designed for common use cases like customer support, guided workflows, and RAG applications. These templates demonstrate best practices for building AI agents that can classify queries, answer questions, generate content, and provide context-aware responses by retrieving and incorporating relevant information.
Once you’ve added a template to your workspace, you can modify it to match your specific requirements. Learn more about customizing your files in our guides for Evaluators, Prompts, and Tools.