> For the complete documentation index, see [llms.txt](https://api.docs.blockbrain.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://api.docs.blockbrain.ai/concepts/knowledge-bots/prompts.md).

# Prompt Library

The **Prompt Library** (also referred to as the **Agent Library**) is the curated collection of reusable prompts, agent system messages, tool configurations, and patterns that power your Knowledge Bots. It standardizes how agents reason, retrieve, and act.

<figure><img src="/files/didpLXBnfwRmUQ7U71KL" alt=""><figcaption></figcaption></figure>

#### What it is

* **Reusable components**: System prompts, instruction blocks, retrieval and tool patterns, and example dialogues.
* **Prompt templates**: Parameterized bot definitions that can be instantiated as concrete bots in Cortex.
* **Governed catalog**: A single place to review, version, and approve prompts and agent behaviors.

#### Why use a Prompt Library

* **Consistency**: Ensure agents follow shared guidelines for tone, safety, and retrieval.
* **Reusability**: Avoid copy–paste drift by centralizing common patterns and instructions.
* **Velocity**: Compose new bots quickly from vetted building blocks.
* **Compliance**: Review and audit agent behavior from a single source of truth.

### Typical lifecycle

1. Draft or update a prompt/agent template in the library.
2. Review and test the prompt in your specific Use-Case.
3. Publish a template; dependent bots are automatically updated to inherit changes.


---

# 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:

```
GET https://api.docs.blockbrain.ai/concepts/knowledge-bots/prompts.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.