In this case, the LLM isn't generating the output. It's only generating the sequence of actions to implement the user input.
Think less "make a signature for me" and more "here's the signature I want to use, make it my default."
Then the model would map to either Outlook / Options / Signature / fields or directly to whateverSetSignature().
From that more modest routing requirement, it seems a slam dunk for even current models (retrained to generate options paths / function calls rather than English text).
Think less "make a signature for me" and more "here's the signature I want to use, make it my default."
Then the model would map to either Outlook / Options / Signature / fields or directly to whateverSetSignature().
From that more modest routing requirement, it seems a slam dunk for even current models (retrained to generate options paths / function calls rather than English text).