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 the difference between a reactive and a proactive AI agent?

A reactive agent responds to explicit input — it waits for a user command or system event and then acts. A proactive agent monitors its environment continuously, anticipates needs, and takes action before being asked. Reactive agents are faster and more predictable; proactive agents deliver more value but require more trust and oversight.

Which is better — reactive or proactive AI agents?

Neither is universally better. Reactive agents are ideal for tasks where accuracy and predictability matter most (customer support, Q&A, alert response). Proactive agents excel at anticipating needs, monitoring for opportunities, and acting autonomously in complex environments. Most mature AI deployments combine both. See [types of AI agents](/blog/types-of-ai-agents/) for a full taxonomy.

What are examples of proactive AI agents?

Common examples include: Microsoft Copilot suggesting document layouts before you ask, Google Assistant recommending departure times based on your calendar and traffic, a sales CRM agent that proactively flags leads likely to churn, or a DevOps agent that detects rising error rates and scales infrastructure before the service degrades.

Can an AI agent be both reactive and proactive?

Yes — this is the hybrid model, and it's the approach most production systems use. The agent handles immediate requests reactively while also running background monitoring loops that trigger proactive interventions when conditions warrant. Platforms like [cowork.ink](https://cowork.ink) support both interaction modes in a single agent.

Are reactive agents the same as chatbots?

Not exactly. All chatbots are reactive (they respond to messages), but not all reactive agents are chatbots. Reactive agents include intrusion detection systems, API error handlers, and support triage bots — systems that respond to stimulus without necessarily having a conversational interface. See [AI agents vs. chatbots](/blog/ai-agents-vs-chatbots/) for a deeper breakdown.

Reactive vs. Proactive AI Agents: Understanding Agent Behavior Types

Reactive AI agents wait for commands. Proactive agents ANTICIPATE and act first. Learn the real differences, use cases, and which to build for your team.

Frequently Asked Questions

What is the difference between a reactive and a proactive AI agent?: A reactive agent responds to explicit input — it waits for a user command or system event and then acts. A proactive agent monitors its environment continuously, anticipates needs, and takes action before being asked. Reactive agents are faster and more predictable; proactive agents deliver more value but require more trust and oversight.
Which is better — reactive or proactive AI agents?: Neither is universally better. Reactive agents are ideal for tasks where accuracy and predictability matter most (customer support, Q&A, alert response). Proactive agents excel at anticipating needs, monitoring for opportunities, and acting autonomously in complex environments. Most mature AI deployments combine both. See [types of AI agents](/blog/types-of-ai-agents/) for a full taxonomy.
What are examples of proactive AI agents?: Common examples include: Microsoft Copilot suggesting document layouts before you ask, Google Assistant recommending departure times based on your calendar and traffic, a sales CRM agent that proactively flags leads likely to churn, or a DevOps agent that detects rising error rates and scales infrastructure before the service degrades.
Can an AI agent be both reactive and proactive?: Yes — this is the hybrid model, and it's the approach most production systems use. The agent handles immediate requests reactively while also running background monitoring loops that trigger proactive interventions when conditions warrant. Platforms like [cowork.ink](https://cowork.ink) support both interaction modes in a single agent.
Are reactive agents the same as chatbots?: Not exactly. All chatbots are reactive (they respond to messages), but not all reactive agents are chatbots. Reactive agents include intrusion detection systems, API error handlers, and support triage bots — systems that respond to stimulus without necessarily having a conversational interface. See [AI agents vs. chatbots](/blog/ai-agents-vs-chatbots/) for a deeper breakdown.