# Quick Look: Example Prompt Repository

The following list the various prompting examples that showcase different data analysis techniques discussed above. Below are sample prompts that combine use case categories to give a quick overview of how Lumi can be prompted.

{% hint style="info" %}
The output quality is correlated to the quality of the prompt. Learn more about [prompting best practices](/using-lumi/best-practices/prompting-best-practices.md).
{% endhint %}

<details>

<summary><mark style="color:blue;"><strong>Performance Metrics Analysis</strong>:</mark> Evaluate various business metrics across dimensions.</summary>

<mark style="color:green;">**Example Prompt:**</mark> *Show me total purchase quantity and total purchase cost for every item in 2023. Also, list the number of distinct suppliers we bought from. Output: item\_id, description, Total Purchase Quantity, Total Purchase Cost, Currency Code, Distinct Supplier Count. Sort by total purchase cost.*

<mark style="color:red;">**Bad Prompt Example:**</mark> *Show me purchases for 2023.*

</details>

<details>

<summary><mark style="color:blue;"><strong>Time Series Analysis</strong>:</mark> Analyze and track trends over time.</summary>

<mark style="color:green;">**Example Prompt:**</mark> *Can you show me gross profit for every month over the past 12 months for customer C000322?*

<mark style="color:red;">**Bad Prompt Example:**</mark> *Tell me how much money xyz customer paid every month.*

</details>

<details>

<summary><mark style="color:blue;"><strong>Comparative Analysis</strong>:</mark> Compare metrics across different time periods.</summary>

<mark style="color:green;">**Example Prompt:**</mark> *Which customers have experienced the largest decline in gross profit when comparing the last 3 months to the previous 3 months? Output: Customer, Customer Name, Currency Code, Last 3 Months, Previous 3 Months.*

<mark style="color:red;">**Bad Prompt Example:**</mark> *Which customers lost money?*

</details>

<details>

<summary><mark style="color:blue;"><strong>Cumulative Analysis:</strong></mark> Calculate cumulative totals or running sums.</summary>

<mark style="color:green;">**Example Prompt:**</mark> *Calculate gross profit in 2024 YTD for each customer.*

<mark style="color:red;">**Bad Prompt Example:**</mark> *What are the profits this year?*

</details>

<details>

<summary><mark style="color:blue;"><strong>Segmentation</strong>:</mark> Divide data into meaningful segments based on common characteristics.</summary>

<mark style="color:green;">**Example Prompt:**</mark> *What are the top purchased items in April 2024 that were bought from multiple suppliers? Include relevant details*

<mark style="color:red;">**Bad Prompt Example:**</mark> *What were the top items in April?*

</details>

<details>

<summary><mark style="color:blue;"><strong>Correlations</strong>:</mark> Explore relationships between two variables.</summary>

<mark style="color:green;">**Example Prompt:**</mark> *What is the marketing spend and sales revenue, by month in 2023. Include relevant details.*

<mark style="color:red;">**Bad Prompt Example:**</mark> *Show me marketing and sales numbers.*

</details>

<details>

<summary><mark style="color:blue;"><strong>Anomaly Detection</strong>:</mark> Detect unusual data patterns or outliers.</summary>

<mark style="color:green;">**Example Prompt:**</mark> *What are the top 5 orders with the lowest margin percentage.*

<mark style="color:red;">**Bad Prompt Example:**</mark> *Are there any weird orders?*

</details>

<details>

<summary><mark style="color:blue;"><strong>Market Basket Analysis</strong>:</mark> Analyze purchasing patterns.</summary>

<mark style="color:green;">**Example Prompt:**</mark> *What are the finished goods with the highest average sales volume in July (across all years) that are currently out of stock?*

<mark style="color:red;">**Bad Prompt Example:**</mark> *What sold the most in July that's out of stock?*

</details>


---

# 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.lumi-ai.com/using-lumi/lumi-use-cases/quick-look-example-prompt-repository.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.