Jan 23, 2025
OpenAI launches “Operator”
OpenAI launches “Operator”
OpenAI launches “Operator”
OpenAI released Operator as a research preview, an AI agent 🤖 that can perform web tasks by typing, clicking, and scrolling through its own browser interface. Currently available to Pro users in the U.S., this preview allows OpenAI to learn from user feedback while refining the technology.
OpenAI released Operator as a research preview, an AI agent 🤖 that can perform web tasks by typing, clicking, and scrolling through its own browser interface. Currently available to Pro users in the U.S., this preview allows OpenAI to learn from user feedback while refining the technology.
The details
The agent uses Computer-Using Agent (CUA) technology, combining GPT-4's vision capabilities with reinforcement learning to interact with website interfaces. It sets new record-breaking results in WebArena and WebVoyager benchmarks, operating without API integrations by directly interacting with browser elements.
Security includes three layers: user control features (takeover mode, confirmations, watch mode), privacy controls (training opt-out, data deletion), and defenses against adversarial websites through monitoring and threat detection systems.
Initial access is limited to Pro users in the U.S., with plans to expand. Users can save prompts for repeated tasks and run multiple tasks simultaneously. OpenAI is partnering with companies like DoorDash and Instacart, while also working with public sector organizations like the City of Stockton to improve civic services.
Why it matters
This release marks OpenAI's entry into browser-based AI agents, following Anthropic's introduction of computer use capabilities for Claude in October 2024. Both developments represent a shift toward AI systems that can actively interact with computer interfaces rather than just respond to prompts.
The details
The agent uses Computer-Using Agent (CUA) technology, combining GPT-4's vision capabilities with reinforcement learning to interact with website interfaces. It sets new record-breaking results in WebArena and WebVoyager benchmarks, operating without API integrations by directly interacting with browser elements.
Security includes three layers: user control features (takeover mode, confirmations, watch mode), privacy controls (training opt-out, data deletion), and defenses against adversarial websites through monitoring and threat detection systems.
Initial access is limited to Pro users in the U.S., with plans to expand. Users can save prompts for repeated tasks and run multiple tasks simultaneously. OpenAI is partnering with companies like DoorDash and Instacart, while also working with public sector organizations like the City of Stockton to improve civic services.
Why it matters
This release marks OpenAI's entry into browser-based AI agents, following Anthropic's introduction of computer use capabilities for Claude in October 2024. Both developments represent a shift toward AI systems that can actively interact with computer interfaces rather than just respond to prompts.
