I'm not Salesforce obviously, but a combination of LLM as an input interface and the deterministic APIs doing the recurring automation behind would work.
For instance you talk with the LLMs for a while, they give you a workable set of DSL commands, you check what they do and make sure they match your needs, and set them to run as frequently as needed.
This pretty much matches my preferred workflow for scripting with LLMs: don't ask it to do the task, ask it to write a script that does the task, then validate and execute or refine.
For instance you talk with the LLMs for a while, they give you a workable set of DSL commands, you check what they do and make sure they match your needs, and set them to run as frequently as needed.