[BDPW]

Its unclear how they intend to fix these fundemantal problems tbh. Things like "Automate the 'must not fail' moments with rules, APIs, and triggers." And "Use policies, templates, function calling, and explicit do/don't constraints." Make sense but if you have deterministic workflows, what do the llms still add?

Using APIs makes sense but isnt the whole point of these things that they can automate away stuff, it feels like we're building really big complicated frameworks to put these things in. Does it still have any actual benefit for stuff like this?

[makeitdouble]

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.

[jgwil2]

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.

[d0liver]

To save face and make it look like an iteration rather than a reversal.