Agreed. The spec file is context. Writing acceptance criteria before you prompt provides the context the agent needs to not go off in the wrong direction. Human leverage just moved up and the plan/spec is the most important step.
Parallelism on top of bad context just gets you more wrong answers faster
Sorry but isn't the bottleneck then simply to do even relevant things? Like how much of a qualified backlog do you have that your pipeline does not run dry?
The cognitive architecture, so to speak, for the LLM can make a huge difference - triggers and skills go a long way when combined with shell scripts that dual-write.
