Luzmo's AI features — Luzmo IQ, AI-powered chart generation, and the dashboard agent — are designed to work with any data source, data structure, and industry or context. But how you set up your data has a big impact on how well they perform. This article covers three foundations: unambiguous names, correct column types, and prepared formulas. For descriptions and AI Context, see Improve Metadata: Generate Column Descriptions and AI Suggestions and Improve Luzmo IQ answers with AI Context.
The first step for any of Luzmo's AI features — whether it's answering a question or generating a chart — is to select the datasets and columns relevant to the request. This selection is performed based on the dataset names and column names. Using descriptive column names that prevent confusion with other columns will help a great deal in selecting the correct columns.
Examples of descriptive column names:
order quantity instead of countorder date instead of datacustomer full name instead of nameproduct category instead of catA useful rule of thumb: When a (smart) human is able to explain the difference between your dataset columns just by looking at their names, Luzmo's AI features will be able to do the same.
We recommend using human readible names, so order quantity instead of order_quantity. Your column names will be used as labels in the charts, for example for the tooltips.
Luzmo's AI features take into account the data types of your columns when selecting columns or formatting data in charts and text. It's important to set these types correctly. For example: when asking questions about a certain timeframe, Luzmo IQ will look for a date or datetime column. Dates stored as hierarchy type can't be used to answer such questions.
Setting correct subtypes is also important. When a column contains currency values, make sure the column's type is set as currency rather than just numeric. The same applies to numeric data that represents durations.
Luzmo IQ is able to create formulas to answer questions. For example, Luzmo IQ will easily answer questions about profit margin when a dataset contains only revenue and cost information. However, many metrics have different methods to be calculated, resulting in a different outcome. For profit margin, one could calculate gross profit margin, net profit margin, operating profit margin, etc.
To improve the success rate and consistency of formulas, you can add your own formulas to a dataset. Luzmo IQ will automatically prioritize existing formulas over creating its own, and a well-named formula is also easier for any of Luzmo's AI features to pick up correctly as a candidate metric.
It's wise to add a formula for each commonly used metric that's not present in one of the dataset columns. Make sure to give them a descriptive name. When your customers are used to using abbreviations, it's most effective to add the full and abbreviated name. Example: Net Profit Margin (NPM)
Note that AI Context is not available on formulas, so any business rules around how a formula should be used should go in the AI context of a related column (e.g. the column used to build the formula), the AI context of the dataset, or — for Luzmo IQ specifically — the custom prompt.