Prompting Best Practices

Effective prompting has a learning curve. Crafting clear, concise prompts can significantly enhance the quality of the results you receive from Lumi.

The following document sheds light on best practices to help improve the quality of user prompts, and in turn, the quality of the output.

1. The more clear and concise you are, the better

Large language models (LLMs) are very literate and will look to execute your exact commands. Providing clear and concise instructions will yield better performing results.

👎 Vague Prompt Example

"What are my top performing products?"

→ Less Likely to get desired insight 🔴

👍 Explicit Prompt Example

"What are the top 25 products that generated the most revenue in 2023? Please sort by descending revenues generated. Report output: SKU ID, Sku Name, Revenues 2023"

→ More Likely to get desired insight 🟢

Regardless of clarity, Lumi will attempt to provide a response to your data request; however, you are more likely to get the insight you are looking for with more clear and explicit instructions.

2. Spell attributes correctly!

Lumi does not know what the correct spelling of a product, brand, or category is. Misspelling an attribute in a data request will most likely return an empty response.

Consider an item catalog with the following categories:

Category_id	Category Name
1	Ultra-Premium Road Bikes
2	Premium Bike Accessories
3	Premium Bike Maintenance Kits
4	Mountain Bikes
5	Budget Road Bikes
6	Children's Bikes

🔴 Prompts that will not return results

How many items fall under bikes?

How many items fall under category bikes?

🟢 Prompts that will return results

How many items fall under category like ‘Premium Road Bike’

How many items fall under category ‘Ultra-Premium Road Bikes’

How many items fall under the category whose description contains ‘Road Bikes’

How many items fall under category ID = 1

Tips to Avoid Error

Option 1: Use Exact Spelling

Use the exact attribute name.

Example: What is the injury rate in 2024 for the 'AUSTIN (6Z, 3023)' market?

Option 2: General Search

Use language that generalizes the search criteria.

Example: What is the injury rate in 2024 for markets containing the name 'austin'?

Option 3: Use Two Prompts

1. Perform a separate query to obtain all potential variations.

Example: Can you show me all categories that contain any variation of 'bike' in the description?

1. Re-contextualize the prompt with the exact name

Example: How many items fall under category like ‘Premium Road Bike’?

3. Specifying which columns you want to see is helpful.

Explicitly specifying output requirements will help Lumi understand exactly what columns you want to see in the rendered output. You don’t need to do this with every prompt, but can be helpful if you are trying to generate a very specific report.

Can you give me the top 10 brands that saw the largest increase in revenues in Jan 2024 (Jan 1 to Jan 15) vs. Jan 2023 (Jan 1 to Jan 15)? Output should include brand, 2024 January revenues, 2024 January revenues, and the delta.

Alternatively, we’ve also realized that including the phrase “include relevant details” at the end of your prompt seems to work well - Lumi will use its best judgement to determine which columns are needed.

what are my top shipped items in June 2023? Include relevant details

4. Break up a request for multiple metrics into multiple sentences.

When constructing queries, especially those involving multiple metrics or dimensions, it's beneficial to simplify the query by breaking it into separate sentences. This approach helps in clearly defining each part of the request and ensures that each metric is accurately addressed.

For example, consider a prompt where you want to know about item performance within a specific time frame, along with current stock levels. Instead of a single complex query, breaking it down can make it clearer:

Who are the top 10 items with the highest order count in April 2024? Add another column that shows current inventory levels.

This prompt effectively separates the historical sales data request from the current inventory status, allowing Lumi to focus on discrete pieces of information sequentially.

5. Specify the filter criteria where possible.

Providing clear and specific filter criteria in your queries is helpful for accurately narrowing down the data and extracting meaningful insights. Ambiguity in query prompts can lead to incomplete or irrelevant data being retrieved.

👎 Vague Prompt Example

How many items fall under Dark Chocolates?

→ Less likely to get desired insight 🔴

👍 Explicit Prompt Example

How many items fall under category 'Dark Chocolates'?

→ More likely to get desired insight 🟢