Return this assistant's use-case scope: the datasets, models, and decisions it is limited to.

Call this first to learn which resources you may work with. If the assistant is not scoped to a use case, scoped is false and you have full access to the environment.

Executes the provided SAS code in the Viya environment and returns information about the completed Job. This will create a job definition for the SAS code, execute it, and then retrieve the results.

Render an interactive chart in the chat UI.

Use whenever the user asks to show / plot / visualize / graph / compare data, or when a chart makes the answer clearer than text. Call this AFTER fetching the rows with the data tools (e.g. get_castable_data) or computing them with execute_sas_code, then pass the rows in as data. Keep data small — aggregate or limit to just the rows you want to chart.

The chart is drawn by the user interface from this call; the tool itself does no plotting and returns the normalized chart spec.

List available CAS servers on the Viya environment.

List CAS libraries (caslibs) available on a CAS server.

List tables in a CAS library.

Get metadata for a CAS table (row count, column count, size, etc.).

Get column metadata for a CAS table (names, types, labels, formats).

Fetch rows from a CAS table with column names.

Upload CSV data into a CAS table.

Promote a CAS table to global scope (makes it visible to all sessions).

List files in the Viya Files Service.

Upload a file to the Viya Files Service.

Download file content from the Viya Files Service.

Generate a synthetic CAS table from a column specification.

Use this to create realistic mock data on request (e.g. a driver-risk dataset for a demo). Recommended flow: first PROPOSE the column schema to the user in chat and get their agreement, THEN call this tool. The rows are generated in SAS and saved to CAS as a promoted (global) table, immediately usable by the data, charting, AutoML, and scoring tools.

If a table with the requested name already exists, a numbered variant is created automatically (no error). Very large requests are capped to a safe maximum rather than failing.

Submit a SAS job for asynchronous execution via the Job Execution service.

Check the status of a submitted job.

List recent jobs from the Job Execution service.

Cancel a running job.

Retrieve the log of a completed job.

List AutoML pipeline automation projects.

Create a new AutoML pipeline automation project.

SAS auto-detects the target's measurement level from the data; for classification targets, target_event_level selects the modeled event level. The data table must be loaded in CAS.

Run an AutoML pipeline automation project.

Delete an AutoML pipeline automation project.

Use this to remove a project (for example, to start over with a different configuration) instead of calling the REST API from SAS code.

List models in the Model Repository.

List published scoring models and decisions (MAS modules).

Score data against a published model or decision (MAS module).

Explain a column of a CAS table in relation to the other columns (SAS Insights).

Returns natural-language descriptions of the variable, its outliers, and variable-screening results — useful for understanding which variables drive a target before exploring or modelling the data.