Agents can now ask clarifying questions without blocking and continue working while you respond.
How it works
With clarification questions from the agent, the agent can continue reading files, making edits, or running commands, then seamlessly incorporate your answer when it arrives.
Instead of stopping entirely when it needs clarification, the agent keeps making progress on parts of the task it can handle independently.
We’d love your feedback!
How will this change your interaction with agents?
Are the clarifying questions helpful and well-timed?
What improvements would make this more useful for your workflow?
If you’ve found a bug, please post it in Bug Reports instead, so we can track and address it properly, but also feel free to drop a link to it in this thread for visibility.
I would like a separate field at the end of agent questions section.
For example, I’ve just received five questions from him, but there were a couple of things he didn’t ask me about, even though I expected them. I could simply add “Also look at [this] and [this] and come back with additional questions” or “Regarding the fourth question [additional information].”
I think that’s already the case @Artemonim! You can answer questions and add additional thoughts where it says “Add more optional details”. Both your question answers and that additional data is submitted.
But initially, I felt like this approach was interrupting the agent’s work, so I think it’s better to embed the comment directly into the question box.