Luzmo IQ is designed to work with any data source, data structure, and within any industry or context. While this is a great starting point, there are several options to influence how Luzmo IQ answers questions. Tweaking your Luzmo IQ setup to match the expectations of your customers will greatly improve its effectiveness.
Before tuning IQ specifically, make sure your data is set up well for AI in general — unambiguous names, correct column types, prepared formulas, descriptions, and AI Context. That foundation benefits every AI feature, not just IQ. See Preparing your data for AI and Improve Luzmo IQ answers with AI Context before continuing here.
With descriptions, AI Context, and the custom prompt all available, it can be unclear where a given piece of context should go. There is no strict priority order between layers — a dataset-level rule does not override a column-level one, both are simply included. Instead, think of it as choosing the right scope for each piece of context:
iq.context): general IQ behavior (response style, business background), or end-user-specific detail (sub-org, job role, preferred filters).As a rule of thumb: put broad rules at the dataset level, and specific rules at the column or formula level. If a rule spans two related columns, either place it at the dataset level or duplicate it on both columns — there's no dependency mechanism between columns today.
Luzmo IQ allows you to programmatically add context to the LLM prompt through the embed token. This gives you tremendous control in steering Luzmo IQ towards specific outcomes, without exposing these instructions to your users. The following tips will help to write an effective prompt:
Example 1: Adding business context
Example 2: Add context to help to select columns for common questions.
Assume a "Projects" dataset with has several columns with cost information, like actualCost, budgetedCost, or billedCost, you can prevent Luzmo IQ to make unexpected selections.
Option 1: Prescribe a default
Option 2: Force follow-up questions
Example 3: Add instructions on how to create text and chart answers
Set default periods for displaying time-based data
Provide instructions for writing large numbers
You can personalize the custom prompt for individual users through the embed token. In the above example, this allows you to instruct the use of long-scale or short-scale number notation depending on localization settings.
Luzmo IQ is set up to generate answers as fast as possible without sacrificing accuracy and consistency. The speed with which answer are generated depends a great deal on the size of the datasets connected. There are a few options to positively influence answer speed:
In most cases, Luzmo IQ serves a different purpose than dashboards. Often, users want to understand events that are happening now. With that in mind, it might not be necessary to feed the full data history of your datasets to Luzmo IQ. Consider setting an embed filter on the embed token to limit your data to, for example, the past year.
Alternatively, consider adding a custom prompt that instructs Luzmo IQ to only consider a recent period by default. This will still allow users to ask questions outside that default period.
A data source that's not optimized for analytical queries will have a bigger negative impact on Luzmo IQ than other Luzmo charts. To formulate a single answer, Luzmo IQ might do multiple queries.
Consider using Warp to speed up queries made by Luzmo IQ.
Luzmo IQ requires at least "use" access to a dataset. Datasets where the embed token only has "read" access are silently excluded from IQ, even if the end user can see them elsewhere in your product.
Luzmo IQ cannot correlate or combine data across datasets that aren't linked. If you expect cross-dataset questions (for example, "which reps with the highest win rate completed the most training"), link those datasets wherever the relationship allows it.