All Posts

Master one-shot and multi-shot prompting techniques in Claude. Learn how to use examples to handle edge cases, define output formats, and improve response quality.

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 build a custom prompt evaluation workflow for AWS-specific code generation. This guide covers creating baseline prompts, automatically generating test datasets using Claude, and setting up a systematic evaluation framework for Python, JSON, and regex outputs.

Learn how to build hooks in Claude Code to intercept and control tool calls. Master PreToolUse and PostToolUse hooks, understand tool call data structures, and implement access control for sensitive files.

Learn how to use system prompts to customize Claude's responses for specific use cases. Build a math tutor chatbot and create flexible chat functions with role-appropriate interactions.