> For the complete documentation index, see [llms.txt](https://docs.reo.dev/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.reo.dev/agents/agent-columns/agent-library.md).

# Agent Library

### What is the Agent Library?

The Agent Library is a collection of ready-made prompts you can try with Reo Agents. Each prompt is built around a signal Reo can answer, so you don't have to start from a blank prompt box or guess what to ask.

Prompts are grouped by use case. Browse a use case from the left menu, or use **Search prompts** to find one by keyword.

At the top of the library, **Featured** prompts show signals picked for your product.

| Use case            | What it helps you find                                                                                    |
| ------------------- | --------------------------------------------------------------------------------------------------------- |
| Developer intent    | Signals that help you find accounts based on activity made by a developer on your product                 |
| Competitive intel   | Which accounts are using your competitor                                                                  |
| Technology Stack    | Signals about what an account runs today, and how mature each technology is                               |
| Technology Projects | What companies are building right now - AI projects, migrations underway and GPU compute                  |
| Hiring Radar        | Signals from open roles - who an account is hiring, how fast, hiring for a skill etc.                     |
| Org Chart           | Signals about engineering team size, leadership and internal moves                                        |
| Company DNA         | Size, funding and business model                                                                          |
| Newsflash           | Signals from announcements, incidents and public filings like layoffs, product launches, partnerships etc |

### How to use the Agent Library

You can open the Agent Library from **Enrich with Agent** in an account segment.

1. Go to **Segments** and open an account segment
2. Click **Enrich with an Agent**
3. Click “View prompts on agent library” to open the Agent Library

![Agent Library KB - 1.png](https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2FxlJtVkmUJKOYuzL1cnGZ%2FAgent%20Library%20KB%20-%201.png?alt=media\&token=ccab8332-58d2-4545-822a-bdc12bbeb416)

4. Browse a use case from the left menu, or search for a prompt
5. Click **Try it** on the prompt you want

![](https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2F1avbYoF4mXI4YjG7Z30W%2FAgent%20Library%20KB%20-%202.png?alt=media\&token=99bf085a-fd01-46cf-b9aa-a2775b2f64ee)

6. If you want, you can edit the prompt after clicking Try it. Change the prompt text as needed, then run it.

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2F1yoXVkV46WcB3qh2iZau%2FAgent%20Library%20KB%20-%203.png?alt=media&amp;token=844667b1-92c7-4832-af02-6b00edc90519" alt=""><figcaption></figcaption></figure>

7. Your prompt is now ready to run on the accounts in your segment.

{% hint style="info" %}
Enrich with an Agent is only available in segments with fewer than 10,000 accounts. If you don't see it, narrow your segment with filters.
{% endhint %}


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.reo.dev/agents/agent-columns/agent-library.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
