senior-prompt-engineer

Run the prompt_optimizer.py script with your input data and output path to process prompt configurations. The references/prompt_engineering_patterns.md guide covers few-shot learning, chain-of-thought, and structured output patterns to apply.

Use the rag_evaluator.py script with a target project path to analyze retrieval-augmented generation behavior. The llm_evaluation_frameworks.md reference describes evaluation workflows, monitoring, and troubleshooting procedures.

Agentic system design structures LLMs as agents that orchestrate tools and multi-step workflows. The agent_orchestrator.py script coordinates agent execution, and the agentic_system_design.md reference covers scalability, reliability, and observability principles.

No external packages are required. The scripts use only Python standard library modules such as argparse, logging, json, and pathlib, so they run in any standard Python 3 environment.

The scripts provide scaffolding with configuration validation and structured logging, but their core execution logic is a placeholder. You must implement the actual optimization, evaluation, or orchestration logic inside the _execute methods.