A pattern to dull the downside risk of agents: have them only write "drafts".

The drafts still need to be activated by a human before executing the action in the real world.

This provides a natural checkpoint to cap the most egregious downside risk.

But this now means that users have to constantly check back in when the agent has a proposed task to do.

If most of their useful actions (and research gathering ones) require actions that could plausibly be dangerous, the agent (and the user operating it) will alternate between being in twiddling-thumbs node while they wait for the other.

The amount of time the human spends actually doing the action gets smaller and smaller as the quality of recommendations and filters gets better.