# OpenAI Releases System Card for ChatGPT's New Agent Capabilities

OpenAI announced the release of a System Card documenting ChatGPT's new agentic features, marking a significant step toward AI systems that can perform complex, multi-step tasks autonomously.

The System Card details how ChatGPT's agent model combines three key capabilities: research tools, browser automation, and code execution. This integration allows the AI to complete sophisticated workflows that previously required human intervention at each step.

Crucially, OpenAI emphasizes that these expanded capabilities come with safety measures aligned with the company's Preparedness Framework. This framework is designed to identify and mitigate potential risks before deploying powerful AI systems.

**Why It Matters**

This release represents a major evolution in ChatGPT's functionality. Rather than simply answering questions, the agent can now autonomously navigate websites, write and execute code, and conduct research