OpenAI says the proactive research of a dot uses read-only tools that cannot send messages, change app content or control the browser or computer, and that its monitoring system can pause or stop the work of a dot when it detects a safety risk. Quote (German copy): "Wenn unser Überwachungssystem ein Sicherheitsrisiko erkennt, kann es die Arbeit des Dots pausieren oder stoppen."

The exact words it rests on

It does this by using the apps you’ve already connected with tools that are restricted to be read-only, which means that they can’t send messages, change app content, or control your browser or computer. Security safeguards built into dots help defend against malicious instructions and monitor for potentially harmful behavior. If our monitoring system detects a safety concern, it can pause or stop the dot’s work.

What the source said when we opened it, on 30 Sep 2026.

The source

Introducing dots
OpenAI · 2026-09-29

Open the sourcearchived copy

Checked

Checked by the notis newsroom on 30 Sep 2026, against the source above.

In the story

OpenAI launches dots, always-on agents with their own cloud computers 30 Sep 2026