Creating a dashboard with AI
To access AI features, an Organization Admin must enable Generative AI assistance in Organization Settings.
-
In the Create with AI dialog, you can enter an optional natural language text prompt to let Neo4j create a customized dashboard.
-
Once you are happy with the prompt, Create the dashboard.
|
When creating a dashboard with AI, the AI analyzes your database schema, that is, the node labels and relationship types of your database. It cannot read the actual data in your database. |
The intelligent prompting happens in the background. AI is going to analyse the schema, and it will try to make up some questions, and then it will convert each of these questions into a chart.
If you do not enter a prompt, Neo4j AI will still make use of your database schema and come up with a suitable dashboard.
Note that the following examples might differ when you reproduce them. This is due to the nature of how LLM processing works.
Creating a data-focused dashboard
Copy the following prompt or create your own and use it to create a dashboard:
Create a dashboard on my retail database, giving me an overview over recent top customers, top selling products, currently available stock, a category overview and sales volume per quarter.The more information you include, the better the result. This holds for information about the database itself as well as entities in the data model.
Here is a sample result:
Creating a visualization-focused dashboard
Copy the following prompt or create your own and use it to create a dashboard:
Create a dashboard with only graph visualizations to analyze my graph.
Here is a sample result:
Combining data- and visualization focus
Copy the following prompt or create your own and use it to create a dashboard:
Create a dashboard with 5 bar charts analyzing products for categories and 5 graph visualizations for these categories.
Here is a sample result:
Quality of the data model
AI provides a great starting point, but the quality of your underlying data model still matters.
A graph model that has been thought out well, leads to a dashboard that tells more meaningful stories.
AI infers nodes and relationships, but you might like to refine the model based on your specific questions - that way you will be able to reference entities directly from your schema (like Customer, Order, or Category) to guide AI towards more relevant charts.