# Comment Cat Engine

**Table of Contents**

* [Prompt Engineering](/home/using-prompts.md)
* [Per Video Analysis](/home/per-video-analysis.md)
* [Aggregate Analysis](/home/main.md)
* [Teminology](/home/terminology.md)

<figure><img src="/files/zDC7kCUIAeZUblE6zAjG" alt=""><figcaption></figcaption></figure>

## Bulk Comment Analysis

The Comment Cat Engine (CCE) is a set of tools and software to gain insight into bulk comment data.  Visit [YourComments.ai](http://yourcomments.ai/) to request access.&#x20;

### Purpose of this document

Provide a manual and documentation on how to use the Comment Cat engine.

### About the Application

All data, outputs, and results are stored as static files accessible to end users.&#x20;

Data is a snapshot of the comment stream for a given asset and timeframe.

### Your Dashboard

Dashboards are secured using randomized strings, which is most similar to Google Docs' "anyone with the link" sharing style. &#x20;

We can reset the link on request, but we are using double 128-bit strings, and access to your dashboard results from sloppiness in handling the URL, not from reverse engineering.

#### System Helpers

You may see "helpers" on the dashboard. These unavoidable artifacts enable us to build dynamic, interactive reports.  They can't be hidden, and there is nothing an end user can do with these fields.

<figure><img src="/files/DIV3OuTCAaQKsaA7viEB" alt=""><figcaption></figcaption></figure>

#### Sentiment Scoring

Sentiment scores in CCE range from `-5.0` to `5.0` in `0.1` increments.

* `-5.0` is the most negative
* `5.0` is the most positive
* `0.0` is neutral

#### Sentiment Grouping

The CCE platform often groups sentiment into more useful groups.  The most common grouping is a 5-bin system of:

* `-5 to -3`  Negative
* `-3 to -1`  Somewhat negative
* `-1 to 1`  Neutral
* `1 to 3`  Somewhat positive
* `5 to 3`  Positive

#### Application Output

We deliver JSON, .csv, or any file that makes our customers happy.  No claim to the data exists; our users own all the data produced.

#### Subscription Plan

The application watches a single stream of comment data, such as a YouTube channel, and provides date-over-time analysis.&#x20;

* Subscription
* Serialized to a social channel
* Jobs run automatically
* Access to a channel-level prompt: Yes
* Access to a channel job (asset) prompt: Yes
* Delivery: many sets of data
* Analysis: Aggregate, one deliverable per video

#### "One-off" Plan

Gain a "right now" snapshot of the comment data. One dataset.

* Pay as you go.
* Not serialized to a social channel
* Manually trigger jobs spending "comment analysis tokens" aka `CAT`.
* Access to a channel-level prompt: No
* Access to a channel job (asset) prompt: Yes
* Delivery: One set of files
* Analysis: One video/result set

### Metabase.com

We are currently using Metabase.com to provide analysis on the static data.  Customers opt-in to further process their data.&#x20;


---

# 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://yourcomments.gitbook.io/home/comment-cat-engine.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.