Observes
Identifies and understands web elements including text, code, images and forms, to build an understanding of what is displayed in the browser.
Project Mariner
Exploring the future of human-agent interaction, starting with browsers
Plans
Interprets complex goals and reasons to plan out actionable steps. The agent will also share a clear outline of its decision-making process.
Acts
Navigates and interacts with websites to carry out the plan, while keeping you informed. You can further prompt the agent at any time, or stop the agent entirely, and take over what it was doing.
Finding personalized jobs
Project Mariner uses information from a resume to find personalized job listings on Climatebase. The agent uses multi-step reasoning to automate a routine task and free up time to do other things.
Hiring a Tasker to build furniture
Project Mariner navigates to an email inbox, finds a recent furniture order, and then goes to taskrabbit.com to find a Tasker that can help assemble the item it found.
Ordering missing ingredients
Project Mariner looks through Google Drive to find a family recipe, notes which ingredients the user is missing, and navigates to Instacart.com to add missing ingredients to cart.
Coming to the Gemini API
We’re bringing Project Mariner’s computer use capabilities into the Gemini API, and we’re bringing more capabilities to other Google products soon.
Experience Project Mariner