> For the complete documentation index, see [llms.txt](https://docs.stackai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stackai.com/agentic-adoption-and-security/scalability/prompt-library.md).

# Prompt Library

<figure><img src="/files/AiVxLE4uL5NthnGBUoUQ" alt=""><figcaption></figcaption></figure>

When it comes to fine-tuning AI agent instructions, the page is extremely useful for saving custom personas. For example, if you'd like to create an agent that summarizes market-related trends in an executive report, you can **save a prompt** titled "Market Analyst Persona" with the following agent instruction:

> You are an analyst summarizing market-related news and trends. Only include information explicitly stated and cite the sources you use to provide specific numbers and dates.

<figure><img src="/files/uwwb6cZiSNpYSuuWKPUl" alt=""><figcaption></figcaption></figure>

As you iterate and test prompts to generate the best outputs from your AI Agents, you can also save specific prompts that you've tested in the past using the Prompt Library. Through this feature, you will be able to ensure that you keep track of all prompt variations you've tried and use the best-performing ones in your AI Agent node.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://docs.stackai.com/agentic-adoption-and-security/scalability/prompt-library.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.