Add examples

[ggbetz]

Add examples for various use cases:

• Basic usage
• Artifacts & metrics zoo
• Score reasoning trace in task>draft>rate>choose workflow (deliberative prompting)
• Fact check the reasons in the argumentation (define your own metric based on argument graph)
• Score reasoning trace in reasoning-enhanced RAG workflow (deliberative prompting)
• Check reason responsiveness of AI agent (define your own metric based on argument graph)
• Monitor and train deliberating dspy agents
• Score all reasoning traces stored in an MLOps platform
• Build your own visualizations (artifacts)
• P-tuning LLMs for better reasoning quality