ChatGPT agent System Card

OpenAI released the ChatGPT agent System Card detailing the capabilities and limitations of ChatGPT agents. This document helps users understand how these agents operate and their intended use cases. It is important for transparency and responsible deployment of AI agents.

ArchiveLaunch

Signal trust

Single sourceEarly signal

PublishedThursday, July 17, 2025 at 12:00 PMJul 17, 12:00 PM

FreshnessArchive

Story ID#350

Back to feed Original report

Original article excerpt

Server-side extracted preview paragraphs from the original source.

ChatGPT agent System Card: OpenAI’s agentic model unites research, browser automation, and code tools with safeguards under the Preparedness Framework.

ChatGPT agent is a new agentic model in the same family as OpenAI o3, that combines the strengths of deep research and Operator. It brings together:

From the outset, we've prioritized safety as an inherent part of the system, expanding on robust controls from Operator’s research preview and adding additional safeguards to address new risks like broader user reach and terminal access. See the section on Product-Specific Risk Mitigations below for more detail.

Opening the briefing

ChatGPT agent System Card

Original article excerpt