Explore / Build the product / AI agents

AI agents · How Founders Use AI

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

Read the result, then the trail. Each agent keeps one: a dot shows ongoing and background work in Activity View, and you can open its own computer to watch; a Gemini task's work panel lists every step and the files it read or changed; Claude keeps tasks in Recents and past runs under Scheduled. Check the parts that would hurt if wrong: open the links it cites, recount totals, and confirm the date, amount and recipient before anything goes out. Ask it to say what it skipped, guessed or could not reach. Keep approvals on for anything that sends, buys or deletes until it has done that job well a few times. OpenAI's own advice is to review consequential work, and if checking takes longer than doing, do it yourself.

On the AI map, 29 October 2026 Agents that do tasks for youAI browsersNo-code automation with AI stepsMeeting notes and everyday productivity

Go deeper8 sources

  • How we build safety, security, and privacy into dots

    OpenAI · Article · Sep 2026

    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.

  • Introducing dots

    OpenAI · Article · Sep 2026

    OpenAI's launch post: what a dot is, which plans get one, how approvals work and what counts against your usage.

  • Manage your tasks & workflows in Gemini Apps

    Google Gemini Help · Guide · Oct 2026

    Google's guide to tasks in Gemini: who can use them, how its local and remote browsers work, and how to take over.

  • Use Claude Cowork safely

    Claude Help Center · Guide · Oct 2026

    Explains read tools against write tools, why that split decides your risk, and how to keep an eye on a running task.

  • Claude Cowork and chat are one Claude

    Claude Help Center · Guide · Oct 2026

    What the merged Claude app can take on from any conversation, and how the Auto and Manual permission settings differ.

  • On Working with Wizards

    Ethan Mollick (One Useful Thing) · Article · Sep 2025

    Why agent output is harder to check than chat output, and how Mollick verifies work he did not watch being done.

  • Management as AI superpower

    Ethan Mollick (One Useful Thing) · Article · Jan 2026

    Mollick's way to decide when to delegate (your time against the time to brief and check) and the six questions a good brief answers.

All 8 sources