All Posts

Learn how to implement code-based grading for AI-generated code evaluation. This guide covers syntax validation for Python, JSON, and regex, combining code and model graders, and using objective metrics to measure prompt engineering progress.

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 use hooks in Claude Code to address common AI development weaknesses. Implement TypeScript type checking and query duplication prevention with practical examples and code.

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 to use the Claude Code SDK to run Claude programmatically from your applications and scripts. Available for TypeScript, Python, and CLI with practical examples and use cases.