Creating a dashboard with AI
For AI features to be accessible, an organization admin must enable Generative AI assistance under 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 prompt is processed in the background. The AI analyzes your database schema and tries to come up with useful queries about the data while taking your prompt into account. Then it creates a suitable visualization for each query.
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 yields more meaningful insights. AI infers nodes and relationships. You can leverage this by using the exact node and relationship identifiers from the schema in your promps to guide AI towards more relevant charts.