# Prompting Best Practices

To get accurate and structured answers, guide the Assistant with clear, task-focused prompts.

| Goal              | Prompt Style                     | Example                                               |
| ----------------- | -------------------------------- | ----------------------------------------------------- |
| **Summarize**     | Ask for a format or length       | “Summarize these notes in 3 bullets.”                 |
| **Compare**       | Use contrast verbs               | “Compare how each Seed defines staking rewards.”      |
| **Extract Data**  | Use ‘List,’ ‘Find,’ or ‘Extract’ | “List all validators mentioned.”                      |
| **Synthesize**    | Combine ideas                    | “Merge these three research briefs into one summary.” |
| **Create Briefs** | Give explicit structure          | “Generate a 500-word AI-ready brief.”                 |

Avoid vague prompts like “Summarize everything.”\
Be specific about what you want — myNeutron Assistant performs best when given focused, clear instructions.

***

#### Example Prompts

**Research**

> “Compare sentiment across my AI market reports.”\
> “List the most frequent topics in my dataset Seeds.”

**Content Creation**

> “Draft three tweet ideas based on my research Seeds.”\
> “Create a short paragraph for a press release.”

**Knowledge Management**

> “Summarize investor emails and meeting notes.”\
> “Find overlaps between these three documents.”

**Technical Use**

> “Extract API endpoints from the integration docs.”\
> “List key dependencies mentioned in these project files.”


---

# 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://neutron-4.gitbook.io/neutron-docs/getting-started/myneutron-assistant/prompting-best-practices.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.