GPT-5.6 has changed how we think about knowledge work. Your job shifts from handling individual tasks to tending systems with AI loops. Here’s what that looks like in @danshipper’s inbox: GPT-5.6 sweeps his email, decides what deserves his attention, researches the context, and presents each email with a short summary and proposed reply. Dan approves, edits, or reaches for @usemonologue to dictate what he wants changed. Then he moves on. At the end of each sweep, the agent learns from Dan’s revisions and decisions and remembers them for next time. Today we’re releasing Tend, an experiment that lets you build this kind of loop yourself. It’s an open-source prompt and repository for turning an inbox, hiring pipeline, or customer-support queue into a system you can tend in ChatGPT Work. Start by teaching Tend what deserves your attention. Then notice what happens: The inbox gets easier, the instructions get better, and another loop in your work begins to reveal itself.