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 human-in-the-loop and human-on-the-loop AI?

Human-in-the-loop (HITL) means the AI pauses and waits for explicit human approval before proceeding. Human-on-the-loop (HOTL) means the AI acts autonomously while humans monitor outputs and intervene only when something goes wrong. HITL trades speed for control; HOTL trades control for scale.

When should an AI agent require human approval before acting?

Use HITL when actions are irreversible (deleting data, sending communications), involve regulatory liability (medical, financial, legal), or when the agent is new to a domain with a limited track record. As agents demonstrate reliability, you can gradually relax those gates.

Is human-in-the-loop still necessary as AI agents improve?

Yes, for high-stakes or irreversible actions — but the scope narrows as agents mature. The goal is a progressive trust model: tight gates early, loosened over time as the agent builds a track record. Tools like [cowork.ink](https://app.cowork.ink) let teams configure approval gates per workflow and adjust them as agents earn trust.

What are the risks of removing humans from the loop entirely?

Removing oversight entirely risks compounding errors (an agent that makes a wrong assumption keeps building on it), regulatory non-compliance, and loss of accountability. The practical answer is HOTL — not no-loop — where humans stay supervisory but don't block every step.

How do multi-agent systems handle human oversight?

In [multi-agent systems](/blog/multi-agent-systems/), an orchestrator agent often takes on the HOTL role for sub-agents — monitoring their outputs and escalating only the highest-stakes decisions to humans. This creates a layered oversight model where human attention is reserved for the most consequential choices.

AI Agent Human in the Loop: HITL vs HOTL Explained

HITL vs HOTL for AI agents — EXPLAINED. Learn when to gate decisions, when to let agents run free, and how to shift control as trust grows. Read now.

Frequently Asked Questions

What is the difference between human-in-the-loop and human-on-the-loop AI?: Human-in-the-loop (HITL) means the AI pauses and waits for explicit human approval before proceeding. Human-on-the-loop (HOTL) means the AI acts autonomously while humans monitor outputs and intervene only when something goes wrong. HITL trades speed for control; HOTL trades control for scale.
When should an AI agent require human approval before acting?: Use HITL when actions are irreversible (deleting data, sending communications), involve regulatory liability (medical, financial, legal), or when the agent is new to a domain with a limited track record. As agents demonstrate reliability, you can gradually relax those gates.
Is human-in-the-loop still necessary as AI agents improve?: Yes, for high-stakes or irreversible actions — but the scope narrows as agents mature. The goal is a progressive trust model: tight gates early, loosened over time as the agent builds a track record. Tools like [cowork.ink](https://app.cowork.ink) let teams configure approval gates per workflow and adjust them as agents earn trust.
What are the risks of removing humans from the loop entirely?: Removing oversight entirely risks compounding errors (an agent that makes a wrong assumption keeps building on it), regulatory non-compliance, and loss of accountability. The practical answer is HOTL — not no-loop — where humans stay supervisory but don't block every step.
How do multi-agent systems handle human oversight?: In [multi-agent systems](/blog/multi-agent-systems/), an orchestrator agent often takes on the HOTL role for sub-agents — monitoring their outputs and escalating only the highest-stakes decisions to humans. This creates a layered oversight model where human attention is reserved for the most consequential choices.