\n<\/p>\n
We think of agents as systems that combine the intelligence of advanced AI models with access to tools, so they can take actions on your behalf and under your control.<\/p>\n
Our early research prototype, Project Mariner, is an early step forward in agents with computer-use capabilities to interact with the web and get stuff done for you. We released it as an early research prototype in December, and we\u2019ve made a lot of progress since with new multitasking capabilities \u2014 and a method called \u201cteach and repeat,\u201d where you can show it a task once and it learns plans for similar tasks in the future. We’re bringing Project Mariner\u2019s computer use capabilities to developers via the Gemini API. Trusted testers like Automation Anywhere and UiPath are already starting to build with it, and it will be available more broadly this summer.<\/p>\n
Computer use is part of a broader set of tools we\u2019ll need to build for an agent ecosystem to flourish.<\/p>\n
Like our open Agent2Agent Protocol, so that agents can talk to each other, or the Model Context Protocol introduced by Anthropic, so agents can access other services. And today, we’re excited to announce that our Gemini API and SDK are now compatible with MCP tools.<\/p>\n
We\u2019re also starting to bring agentic capabilities to Chrome, Search and in the Gemini app. For example, a new Agent Mode in the Gemini app will help you get even more done. If you\u2019re apartment hunting, it will help find listings that match your criteria on websites like Zillow, adjust filters and use MCP to access the listings and even schedule a tour for you. An experimental version of Agent Mode in the Gemini app will be coming soon to subscribers. And it\u2019s great for companies like Zillow, bringing in new customers and improving conversion rates.<\/p>\n
This is a new and emerging area, and we\u2019re excited to explore how best to bring the benefits of agents to users and the ecosystem more broadly.<\/p>\n<\/div>\n