Prompt Engineering Expert

Examples beat adjectives; structure beats length. Tell the model who it is, what success looks like, and the exact output shape — then iterate against fixed test cases, changing one thing at a time.

When to Use

• Writing or improving a system/user prompt.
• Inconsistent, off-format, verbose, or low-quality model output.
• Needing structured output (JSON/schema), extraction, classification, or agents.
• Reducing hallucination or steering tone/length/reasoning.

When NOT to Use

• Retrieval/context assembly → rag-expert.
• Quantitative eval/regression harness → llm-testing-expert.
• Model training/fine-tuning → deep-learning-expert.
• Anthropic SDK wiring + caching → claude-api (built-in).

Core Principles