# Use Case: Marketing data analytics

Using the AI significantly accelerates the processing of large volumes of marketing data.

Here are some examples of queries you can make to AI:

1. Show days when Fact CPA and Goal CPA gap more than 15%. Show date, campaign, and the gap.
2. Identify campaigns with bad performance. For every campaign find days when it runs. For every day show Conversions. Show days as columns and campaigns as rows. Show rows where cells in the dataset is zero at least 3 columns in a row.
3. Find pattern in Page URLs and show me patterns that saw the most decline in impression and clicks. I need a pattern only one level deeper than /content/. Ignore subsequent patterns in urls. For every pattern show the pattern, decline in Impressions, decline in Clicks. Sort by Impressions decline.
4. Create a dashboard. create a row for the "Impressions" metric. first column is for the most recent week. the second column is for the earlier week. 3rd column is comparison of the 1st and second columns. add a row for the "Clicks" metric. first column is for the most recent week. the second column is for the earlier week. 3rd column is comparison of the 1st and second columns.


---

# 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://docs.getconduit.app/use-cases/use-case-marketing-data-analytics.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.