> For the complete documentation index, see [llms.txt](https://docs.ccv.brown.edu/ai-tools/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ccv.brown.edu/ai-tools/services/ask-oscar.md).

# Ask Oscar

{% hint style="info" %}
Note: This CCV AI service is still under development and may undergo substantial changes without any notice.
{% endhint %}

## Overview

The Ask Oscar service is envisioned to be an AI assistant powered by the Retrieval Augmented Generation (RAG) technique with access to specific knowledge about Brown University. Currently, as a proof-of-concept, the AI assistant has access to a version of the documentation of OSCAR, Brown's high-performance computing (HPC) cluster. The vision is for it to become a more general-purpose AI assistant with access to various Brown resources, such as the OIT Knowledge Base.

## Getting started

To get started, simply type a question or click on one of the sample questions. The assistant will respond to the question with the knowledge it can find within the OSCAR documentation. The response will also contain 2 links to the source pages where the info is located. Even with the RAG technique, the AI assistant can still "halluciate" (generate false information), so please make sure to check the sources to validate the information.


---

# 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.ccv.brown.edu/ai-tools/services/ask-oscar.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.