A general rule in optimization: auto-tightening systems.
Invest effort to optimize it in proportion to how often it's used.
For example, in V8, the first pass is a quick-and-dirty compile.
But hot code paths (for example, in a loop) get another pass of optimization to make them faster.
This insight comes from the original HotSpot Java compiler.
Optimize it from generalized/sloppy to specific/tight in proportion to how many times it runs.
The same is true for workflows that use LLMs.
If it's going to run once, just have an LLM execute an english language prompt.
But if you're going to run it thousands of times, have the LLM write deterministic code.
Right now we don't have enough real-world last-mile use of AI workflows so we're in the cheap/sloppy phase of deployment, not yet to the auto-tightening parts.