What AI models does the agent use?

The agent has access to Claude, DeepSeek, Gemini, and other top models. It automatically routes to the best model for each task — you never have to think about API keys or token limits.

Yes. Each agent runs in an isolated environment. We don't train on your data, and you can export or delete everything at any time. The underlying engine (GoGogot) is open-source, so you can audit exactly how it works.

What can the agent actually do?

Browse the web, process files (CSV, PDF, images), run scheduled tasks, remember context across sessions, and communicate via Telegram or Slack. Think of it as a capable junior employee, not a chatbot.

How does memory work?

The agent maintains persistent memory across sessions. It remembers your preferences, past conversations, and task context. You can also explicitly tell it to remember or forget things.

Can I self-host the agent?

Absolutely. GoGogot is 100% open-source. Run it on your own hardware for free. cowork.ink is the managed version — we handle servers, model costs, updates, and uptime so you don't have to.

Is there a free trial?

We offer a 7-day money-back guarantee. Spin up an agent, give it real tasks, and if it doesn't save you time, we'll refund you — no questions asked.

What is a personal AI digital twin?

A personal AI digital twin is an agent trained on your writing, calendar, emails, and past decisions to act on your behalf. Unlike a general chatbot, it's designed to represent your judgment — not just answer questions.

Can an AI digital twin attend meetings for me?

Yes. Tools like Read AI Ada and Zoom's AI companion can join meetings, take notes, and respond to messages as you. The harder question is whether your colleagues trust a proxy to represent you accurately — a recent CHI 2026 study found workers have serious reservations about manager clone agents.

What is the difference between an AI digital twin and an AI agent?

An AI agent is any autonomous software that completes tasks. An AI digital twin is specifically modeled on one person's behavior and communication style — designed to impersonate rather than just assist. See our guide to [how AI agents work](/blog/how-do-ai-agents-work/) for a broader overview.

Who owns your AI digital twin?

This is unsettled territory. The data you use to train the twin is yours, but the model and inference may run on a vendor's servers. Read your provider's terms carefully — especially around data retention after you close your account.

Are AI digital twins ethical at work?

The main concerns are misrepresentation (your twin says something you wouldn't), privacy (who else can query it), and accountability (you remain responsible for what it commits to). Transparency with colleagues about when they're talking to your twin is the ethical baseline.

AI Digital Twin Personal: Can an Agent Be Your Proxy?

An AI digital twin acts as your PERSONAL proxy — handling emails, meetings, and decisions in your style. Discover how it works, where it fails, and how to build one safely.

Frequently Asked Questions

What is a personal AI digital twin?: A personal AI digital twin is an agent trained on your writing, calendar, emails, and past decisions to act on your behalf. Unlike a general chatbot, it's designed to represent your judgment — not just answer questions.
Can an AI digital twin attend meetings for me?: Yes. Tools like Read AI Ada and Zoom's AI companion can join meetings, take notes, and respond to messages as you. The harder question is whether your colleagues trust a proxy to represent you accurately — a recent CHI 2026 study found workers have serious reservations about manager clone agents.
What is the difference between an AI digital twin and an AI agent?: An AI agent is any autonomous software that completes tasks. An AI digital twin is specifically modeled on one person's behavior and communication style — designed to impersonate rather than just assist. See our guide to [how AI agents work](/blog/how-do-ai-agents-work/) for a broader overview.
Who owns your AI digital twin?: This is unsettled territory. The data you use to train the twin is yours, but the model and inference may run on a vendor's servers. Read your provider's terms carefully — especially around data retention after you close your account.
Are AI digital twins ethical at work?: The main concerns are misrepresentation (your twin says something you wouldn't), privacy (who else can query it), and accountability (you remain responsible for what it commits to). Transparency with colleagues about when they're talking to your twin is the ethical baseline.