All Posts

Learn how to implement grading systems for prompt evaluation workflows. This comprehensive guide covers code graders, model graders, and human graders, with detailed examples of building LLM-as-judge systems that provide objective quality scores and actionable feedback.

Learn how to build tool functions in Claude to give AI access to real-time information and actions. Master best practices for validation, error handling, and function design.

Learn how to build the core evaluation pipeline for prompt testing. This guide covers the three essential functions—run_prompt, run_test_case, and run_eval—that process test cases through Claude and collect structured results for analysis.

Learn how semantic search uses text embeddings to find the most relevant chunks in a RAG pipeline. Understand embeddings, implement VoyageAI for generating embeddings, and discover how to match user queries with the right content.

Learn how to use Claude's built-in web search tool to access current information. Understand schema setup, domain restrictions, response structure, and citation rendering.