Article
On Working with Wizards
Ethan Mollick (One Useful Thing) · oneusefulthing.org
Why agent output is harder to check than chat output, and how Mollick verifies work he did not watch being done.
The question it answers
Read with it
- Lists what a dot may do alone, what needs your approval each time, and what it must hand back to you, such as moving money. openai.com Article How we build safety, security, and privacy into dots OpenAI
- OpenAI's launch post: what a dot is, which plans get one, how approvals work and what counts against your usage. openai.com Article Introducing dots OpenAI
- Google's guide to tasks in Gemini: who can use them, how its local and remote browsers work, and how to take over. support.google.com Guide Manage your tasks & workflows in Gemini Apps Google Gemini Help
- Explains read tools against write tools, why that split decides your risk, and how to keep an eye on a running task. support.claude.com Guide Use Claude Cowork safely Claude Help Center
- What the merged Claude app can take on from any conversation, and how the Auto and Manual permission settings differ. support.claude.com Guide Claude Cowork and chat are one Claude Claude Help Center
- Mollick's way to decide when to delegate (your time against the time to brief and check) and the six questions a good brief... oneusefulthing.org Article Management as AI superpower Ethan Mollick (One Useful Thing)
eChai Partner Brands
The partnership →
