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.

Can AI agents delegate tasks to other agents?

Yes. Modern AI agent frameworks such as LangGraph, AutoGen, and CrewAI support explicit delegation — an orchestrator agent breaks a task into subtasks and assigns each to a specialized subagent. The three main patterns are boss-worker (hierarchical), pipeline (sequential), and voting (parallel consensus). Learn more in our [multi-agent orchestration guide](/blog/ai-agent-orchestration/).

What is the supervisor pattern in multi-agent AI?

The supervisor (boss-worker) pattern uses one orchestrator agent to decompose a task, assign subtasks to worker agents, and aggregate their outputs. Workers only communicate with the supervisor, never with each other. This gives strong control but adds latency because every routing decision requires an LLM call from the supervisor.

When should I use a pipeline vs. a hierarchical agent pattern?

Use a pipeline when the steps in your workflow are fixed and sequential — think "assembly line." Use a hierarchical (boss-worker) pattern when the number or order of subtasks is dynamic and must be decided at runtime by an orchestrator. Pipelines are cheaper and more predictable; hierarchical patterns are more flexible.

What is the voting pattern in multi-agent AI systems?

The voting pattern runs multiple agents on the same task in parallel, then aggregates their outputs through a majority, weighted, or unanimous vote. It improves reliability for high-stakes decisions by reducing the chance that any single agent's error becomes the final answer.

What are the risks of AI agent delegation chains?

Delegation chains amplify errors — a mistake by the orchestrator propagates to all workers. They also increase token costs (every routing step burns context), introduce latency, and can create security risks if subagents inherit excessive permissions. See our [AI agent security guide](/blog/ai-agent-security/) for mitigation strategies.

AI Agent Delegation Patterns: Boss-Worker, Pipeline & Voting

COMPLETE guide to AI agent delegation patterns: boss-worker, pipeline & voting. Learn which architecture fits your workflow. Compare now.

Frequently Asked Questions

Can AI agents delegate tasks to other agents?: Yes. Modern AI agent frameworks such as LangGraph, AutoGen, and CrewAI support explicit delegation — an orchestrator agent breaks a task into subtasks and assigns each to a specialized subagent. The three main patterns are boss-worker (hierarchical), pipeline (sequential), and voting (parallel consensus). Learn more in our [multi-agent orchestration guide](/blog/ai-agent-orchestration/).
What is the supervisor pattern in multi-agent AI?: The supervisor (boss-worker) pattern uses one orchestrator agent to decompose a task, assign subtasks to worker agents, and aggregate their outputs. Workers only communicate with the supervisor, never with each other. This gives strong control but adds latency because every routing decision requires an LLM call from the supervisor.
When should I use a pipeline vs. a hierarchical agent pattern?: Use a pipeline when the steps in your workflow are fixed and sequential — think "assembly line." Use a hierarchical (boss-worker) pattern when the number or order of subtasks is dynamic and must be decided at runtime by an orchestrator. Pipelines are cheaper and more predictable; hierarchical patterns are more flexible.
What is the voting pattern in multi-agent AI systems?: The voting pattern runs multiple agents on the same task in parallel, then aggregates their outputs through a majority, weighted, or unanimous vote. It improves reliability for high-stakes decisions by reducing the chance that any single agent's error becomes the final answer.
What are the risks of AI agent delegation chains?: Delegation chains amplify errors — a mistake by the orchestrator propagates to all workers. They also increase token costs (every routing step burns context), introduce latency, and can create security risks if subagents inherit excessive permissions. See our [AI agent security guide](/blog/ai-agent-security/) for mitigation strategies.