# prompt-engineering

Advanced prompt engineering techniques including Anthropic's official best practices and research-backed persuasion principles.

**Includes:**

* **Few-Shot Learning** - Teach by showing examples
* **Chain-of-Thought** - Step-by-step reasoning
* **Prompt Optimization** - Systematic improvement through testing
* **Template Systems** - Reusable prompt structures
* **System Prompt Design** - Global behavior and constraints

**Persuasion Principles (from** [**Prompting Science Report 3**](https://arxiv.org/abs/2508.00614)**):**

| Principle        | Use For                    | Example                                     |
| ---------------- | -------------------------- | ------------------------------------------- |
| **Authority**    | Discipline enforcement     | "YOU MUST", "No exceptions"                 |
| **Commitment**   | Accountability             | "Announce skill usage", "Choose A, B, or C" |
| **Scarcity**     | Preventing procrastination | "IMMEDIATELY", "Before proceeding"          |
| **Social Proof** | Establishing norms         | "Every time", "X without Y = failure"       |
| **Unity**        | Collaboration              | "our codebase", "we both want quality"      |

**Key Concepts:**

* **Context Window Management** - The window is a shared resource; be concise
* **Degrees of Freedom** - Match specificity to task fragility
* **Progressive Disclosure** - Start simple, add complexity when needed


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://cek.neolab.finance/plugins/customaize-agent/prompt-engineering.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.