Enables coding agents to publish interactive documents and forms that users can view, edit, comment on, and share, with feedback sent back to the agent.
Enables AI coding agents to publish work mid-task for real human review, collect pinned comments and verdicts, and iterate until the output is approved. It supports second opinions and human judgment on artifacts such as sites, videos, and text.
Enables coding agents to publish work mid-task and have a real human reviewer pin comments on what is off, returning a verdict the agent iterates against until approved. Supports review of built sites, videos, and other artifacts, plus text-only questions, from any directory.
Enables AI coding agents to publish their in-progress work and have a real human reviewer open it, pin comments to the exact elements that are off, and return a verdict. The agent then revises based on that pinned human feedback and refiles until a person approves.