This can be useful in a few situations:
1. To reduce the number of GitHub API calls (thus avoiding hitting the rate limit)
2. When the trigger for the agent is an external process (e.g. some external CI job), so there is no need to publish a message like "preparing review..." because it's not a part of a natual conversation with the user
This can help teams compare the review of the PR agent with that of a human reviewer, and fine-tune a score threshold for automatic approval where they decide the agent's review is satisfactory.
