OpenAI Operator Review: ChatGPT That Actually Uses Your Browser
OpenAI Operator can browse the web, fill forms, and book reservations on your behalf. We gave it 20 real tasks. Here's what happened.
OpenAI Operator is the consumer face of agentic AI: a ChatGPT mode that controls a real browser to complete tasks for you. After two weeks of daily use across 20 real tasks, here's what works and what doesn't.
What Operator does well
Booking restaurant reservations (OpenTable, Resy). Comparing prices across e-commerce sites. Filling out form-heavy web apps (visa applications, expense reports). Scheduling meetings through online booking pages. Researching products and assembling a comparison table.
What it struggles with
Sites that aggressively detect bots (some banks, ticketing sites). Anything requiring 2FA from your phone (it can't read your texts). Tasks requiring judgment ('book me a hotel that feels romantic' — too subjective).
Speed
about 3-5x slower than a human doing the same task. The win is asynchrony — you set it off and do other things.
Safety
Operator pauses and asks for confirmation before payments, irreversible actions, or anything sensitive. Good design — it failed safe in our testing.
Pricing
included with ChatGPT Pro ($200/mo). Not yet available on the $20 Plus tier as of June 2026.
Compared to alternatives
Anthropic's Computer Use is more flexible (can operate any application, not just browsers). Manus is open-beta and surprisingly capable. Google's Project Mariner is the most polished but tied to Chrome.
Use cases that actually pay off
Anything you do repeatedly on a website — expense reports, weekly research, lead enrichment, repetitive form filling.
The bigger picture
Operator is a glimpse of how all software will be used by 2028. The browser is becoming the universal API. Build products and workflows that make sense to AI agents, not just humans.
Related Stories
View all in Artificial Intelligence →
GPT-5 Is Here: Everything You Need to Know About OpenAI's Most Powerful Model Yet
OpenAI just unveiled GPT-5 with breakthrough reasoning, vision, and agentic capabilities. Here's how it changes the AI landscape forever.
Will AI Coding Agents Replace Developers? We Asked 100 Engineers
Devin, Cursor, GitHub Copilot Workspace, and Claude Code are reshaping software engineering. Here's what's actually happening on the ground.
The 27 Best AI Tools in 2026 (Tested for 90 Days)
We spent 90 days testing every major AI tool released in 2026. Here are the 27 winners across writing, coding, image, video, voice, and productivity — and the ones to skip.
ChatGPT vs Claude 4: Which AI Should You Actually Pay For in 2026?
We ran 50 head-to-head prompts on ChatGPT (GPT-5) and Claude 4 Opus across coding, writing, math, and reasoning. Here's the honest verdict.
Google Gemini 3 Ultra Review: Has Google Finally Caught Up?
Google's Gemini 3 Ultra promises GPT-5-level performance with native 2M context. After two weeks of daily use, here's what's real and what's hype.
Midjourney vs DALL-E 4 vs Flux 1.1: The Definitive AI Image Generator Comparison
We generated the same 30 prompts across Midjourney v7, DALL-E 4, Flux 1.1 Pro, and Stable Diffusion 3.5. The results surprised us.
The Daily Pulse
Get the 5 biggest tech stories in your inbox every morning. Free, no spam, unsubscribe anytime.
Join 50,000+ tech professionals reading every day.