# Google Project Mariner Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/google-project-mariner
> Markdown URL: https://aitinkerers.org/technologies/google-project-mariner.md
> Technology record last updated: 2026-03-24T15:30:37Z
> Generated: 2026-08-25T07:23:23Z

Project Mariner is a Google DeepMind AI agent that automates complex, multi-step web tasks by observing the browser, planning actions, and executing them (Observe-Plan-Act).

Project Mariner is a research prototype from Google DeepMind, built on the Gemini 2.0 model, designed to automate time-consuming, web-based tasks. Operating as an experimental Chrome extension, it can manage up to 10 simultaneous tasks on Virtual Machines, freeing up user time. The agent handles multi-step processes like filling out job applications, comparing prices, or hiring a Tasker for furniture assembly. Mariner achieved a state-of-the-art 83.5% on the WebVoyager benchmark for end-to-end web tasks. It is currently available to Google AI Ultra subscribers in the US and is being integrated into the Gemini API and Vertex AI for broader developer access.

- Official technology site: https://labs.google.com/mariner
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Self-reflection in agentic workflows](https://zurich.aitinkerers.org/talks/rsvp_4jGx0MOTPXE)

My demo will explore self-reflection in agentic workflows. You will learn how structured self-reflection enhances agentic process quality and prevents system deviations. I will act as an agentic system that executes actions and an AI verifier will monitor my actions and assess my execution. Perhaps I will even be able to trick the verifier ;) Some more details about the demo: I will be impersonating a browser interaction agent (similar to Google's Project Mariner or OpenAI's Operator) and the verifier (based on an LLM with vision) will use natural language description of my actions and screenshots of the webpage as input for verification.

- Event context: AI Tinkerers Zurich - February 6 — 2025-02-06 — Zürich
- Public talk page: https://zurich.aitinkerers.org/talks/rsvp_4jGx0MOTPXE

## Related Technologies

- [Computer Vision](https://aitinkerers.org/technologies/computer-vision) ([Markdown](https://aitinkerers.org/technologies/computer-vision.md)) — 22 public demos
- [Large Language Model](https://aitinkerers.org/technologies/large-language-model) ([Markdown](https://aitinkerers.org/technologies/large-language-model.md)) — 9 public demos
- [OpenAI Operator](https://aitinkerers.org/technologies/openai-operator) ([Markdown](https://aitinkerers.org/technologies/openai-operator.md)) — 3 public demos
- [Vision-Language Model](https://aitinkerers.org/technologies/vision-language-model) ([Markdown](https://aitinkerers.org/technologies/vision-language-model.md)) — 1 public demo