Reference
Prompt Engineering Glossary
Every term you need, with working example prompts and practical notes on when each technique earns its keep.
2 terms starting with "G"
Applied
Grounding
Constraining an LLM's response to information provided in the prompt -- typically retrieved documents -- rather than the model's parametric (trained-in) knowledge.
SecurityGuardrails
Programmatic checks -- before, during, or after LLM generation -- that enforce policy, block unsafe outputs, or validate shape / content independent of what the model would produce on its own.