AI Workbench brings the power of machine learning to customer data, enabling you to analyze, enrich, and act on insights with ease. By leveraging built-in Jupyter notebooks, you can build and train machine learning models that enhance customer profiles, optimize segmentation, and unlock new CDP use cases.
Before you begin
Ensure you have the right user permissions to edit and view AI Workbench.
Types of AI notebooks
Prebuilt notebooks - AI notebooks that are ready-to-use and created by BlueConic, designed as a customizable starting point for non-technical users. Existing prebuilt notebooks include:
Custom notebooks - AI notebooks created from a blank template, designed for advanced users who need flexibility to code for specific use cases.
Navigate to AI Workbench
Navigate to More > AI Workbench in the main menu.
The AI Workbench page displays a table of AI notebooks that are configured in your tenant. Search, filter, and customize the columns.
Under the name column of the table, there is a notebook icon that shows each notebook's current status, including:
If a notebook is scheduled or not.
If a notebook is being edited.
If a notebook is being run or not.
Click the name of a notebook to open its details.
Create an AI Workbench notebook
To create a new notebook:
Click the Add notebook button.
Choose a notebook type from the pop-up window.
Give the notebook a name.
(Optional) Edit the notebook's metadata.
Save your settings.
Manage an AI Workbench notebook
Once you have created a notebook, you will notice it has three tabs:
Notebook editor - This is where you can view all of the technical details of an AI notebook and make changes to the code. It is not recommended to make changes to this page unless you are familiar with coding.
Parameters - This is where non-technical users can update the inputs or parameters to an AI model without writing any code.
Schedule and run history - This is where you can determine when and how often your notebook will run.
Next steps
Review the BlueConic Python API documentation site.
FAQs
What parameter types can be used in AI Workbench notebooks?
AI Workbench supports various BlueConic data types, including channel, connection, date, datetime, dialogue, external_tracker, int (integer), listener, objective, notebook, profile_property, profile_property_unique, segment, str (string), and text.
Why can't I see the changes that another user has applied to my notebook code?
While your notebook (kernel) is running, you and a colleague can work on separate versions. If they make changes and save, refresh your browser to see the updates.
If you leave without saving, the next time you open the notebook, the last saved version will load. If the kernel is terminated, manually or automatically, the most recent saved version will be displayed.
How does AI Workbench handle data for records that are not in the database yet?
AI Workbench runs on top of the full BlueConic database, including both anonymous and known data. In AI Workbench, you can also use data that’s not available in the profile, such as weather data or transactions from Shopify or Magento.
How can I be notified when notebooks run?
At the top of the configuration page for AI notebooks, in the metadata section, you can request that BlueConic notify one or more email addresses when the notebook is run.
Can I use Git in AI Workbench?
Yes, the AI Workbench container includes the Git command-line tool, enabling direct access to your Git repository. This improves productivity by eliminating manual copy-pasting, streamlining code reuse, and ensuring you work with the latest, most secure code.
Here are examples of how to set this up:
To install a package from a Git repository and specify a branch, use pip with the following syntax:
%pip install git+https://github.com/user/repo.git@branch#egg=package-name
Replace user, repo, branch, and package-name with the appropriate values for the Git repository and package you want to install.
If you don't need to specify a particular branch or package, use pip as such:
%pip install git+https://github.com/user/repo.git
Replace the URL with whatever Git host you want to use, along with the appropriate values for user and repo.
How can I add a custom parameter to a notebook?
If you want to add a custom parameter to your notebook that can be accessed and edited by non-technical users in the Parameters tab:
In the Notebook editor tab, scroll down to the Parameters section.
Paste your code for the new parameter.
Call the function of your new parameter (e.g.,
get_blueconic_parameter_value()
) to make it available for editing.Save your settings.
Why am I encountering a notebook validation error?
If you are seeing an AI Workbench 404 error, this may be occurring because of the version of the module jupyter-contrib-nbextensions. To remedy the issue, we recommend downgrading the version of this module once installed (or avoid using them). For example, if the version jupyter-contrib-nbextensions==0.7.0 causes an error, try using a version like jupyter-contrib-nbextensions==0.5.1
How does AI Workbench manage resource usage?
AI Workbench operates within a shared resource pool, meaning memory and computing power are shared among BlueConic customers, but your data remains private.