Video

Your AI Agent Is Making Decisions. Who Pays When It's Wrong?

WorkOS (panel hosted by Claire Vo) · youtube.com

Your AI Agent Is Making Decisions. Who Pays When It's Wrong?

A panel on who owns an agent's work, where human review earns its keep, and how permissions keep mistakes small.

Watch on YouTube ↗

The question it answers

  1. How do I check what an AI agent actually did before I trust its work?

Read with it

  1. 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
  2. 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
  3. 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
  4. 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
  5. 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
  6. Why agent output is harder to check than chat output, and how Mollick verifies work he did not watch being done. oneusefulthing.org Article On Working with Wizards Ethan Mollick (One Useful Thing)
eChai Partner Brands The partnership →