> that sub-agent can go consume 250k+ context to return an answer that might be a couple of words
How can the parent agent verify the answer without reading some of the context of the sub-agent?
> that sub-agent can go consume 250k+ context to return an answer that might be a couple of words
How can the parent agent verify the answer without reading some of the context of the sub-agent?
It doesn't have to.
But usually verifying the answer is cheaper than finding the answer, so it can be done. The prompt given to the sub-agent can be a question with "and explain your answer", the answer to which will still consume far less context than figuring out the answer.