Prompting
How to get useful output from a model without changing its weights: chain-of-thought, few-shot examples, structured output, and the failure modes each one has.
10 technologies
- In-Context Learning concept A model performing a task from examples in the prompt, with no weight update.
- Function Calling technique Letting a model request a tool by name with structured arguments.
- Zero-Shot concept Performing a task with no examples and no training for it.
- Prompt Engineering technique Shaping a model's instructions and context to get the output you actually want.
- Few-Shot Learning technique Putting examples in the prompt instead of training on them.
- Context Engineering technique Deciding what goes into the context window, not just how it is worded.
- Self-Consistency technique Sampling several reasoning paths and taking the majority answer.
- Structured Output technique Constraining a model to emit valid JSON or a schema-conforming object.
- Chain of Thought technique Prompting a model to reason step by step before answering.
- Tree of Thoughts technique Searching over intermediate reasoning states instead of one linear chain.