And how exactly does the agent harness surface ALL the right places that need to be updated, and reason about functions and APIs?

I appreciate where you are coming from, as you have surfed the front of the wave of GenAI for years. From my point of view, there is interesting because something is SOTA, and there is interesting because there is still more to build. I definitely understand state of RAG tech. I also view it as barely utilized versus what we can do with it, hence my question.

Agent harnesses integrated into good search tools are definitely interesting. Knowledgebasing with partitions and similar structure also remains fruitful for applications, above and beyond standard ElasticSearch on a cache.

I generally agree with this, but would note that it assumes that the data is accessible from a web search. Some data sources will be private.