# Use Case: Track Ad Campaign Performance with Conduit

#### Identifying and Evaluating Low-Performing Campaigns

In this use case, we have a dataset that comprises lists of advertising campaigns and their daily metrics like marketing spend.

 

<figure><img src="https://storage.crisp.chat/users/helpdesk/website/39e5340fb975fe00/unnamed-7_1pw2ji8.png" alt=""><figcaption></figcaption></figure>

Our goal is to identify and track Ad Campaigns with the lowest performance. Let’s have the AI reformat the sheet, to display days, as separate columns:

&#x20;

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

Now, our task is to filter the campaigns with 0 conversions in the three days in a row. Click 'Reply' to refine the dataset from Copilot's response and input this prompt *‘Filter the campaigns that have 0 conversions for not less than 3 days’*

&#x20;

<figure><img src="/files/KDeeBld1agG1xDAfXAdd" alt=""><figcaption></figcaption></figure>

#### Automation capabilities

Now, we aim to optimize this process, enabling AI to automatically check the dataset of interest and notify us about low-performing campaigns via Slack. To achieve this, we would need to create a new Workflow on the corresponding tab:

${vimeo}Ask AI about a Dataset

1. Drag the 'Ask AI about the dataset' block.
2. Input the name of the dataset of interest from the Copilot tab.
3. Drag the 'Create Report / Aggregate' block and choose the source dataset.
4. Conclude the workflow with either the 'Send CSV to Slack' or 'Send CSV to Email' block.

There you have it – a fully equipped workflow at your fingertips!


---

# 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-track-ad-campaign-performance-with-conduit.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.