# Agents Every chat in Qolaba runs through an agent. By default, the **Personal Assistant** agent is active — giving you a capable, general-purpose AI assistant from the moment you open a chat. Agents define how the AI behaves: its role, expertise, tone, and the knowledge it draws from. Beyond the default, Qolaba gives you access to a library of **pre-built agents** for common professional roles, and the ability to build fully **custom agents** tailored to your specific workflows, domain knowledge, and behavioral requirements. *** #### What an Agent Does When an agent is selected, every prompt you send in that chat is processed through the agent's **system instructions** — a predefined set of behavioral guidelines that shape how the model interprets your request and constructs its response. This means the same prompt sent through a Marketing Strategist agent and a Legal Compliance agent will produce fundamentally different outputs. Agents can also carry **attached knowledge** — files and knowledge bases that the agent references automatically, without you needing to upload context in every session. *** #### Types of Agents 1. **Pre-built Agents** — Ready-to-use assistants with predefined roles and system prompts. Select one and the agent is immediately active — no setup required. 2. **Custom Agents** — Agents you build from scratch. Define the model, role, instructions, tone, expertise, and attach knowledge bases tailored to your workflow. *** #### What's in This Section 1. [**Pre-built Agents →**](/chatbot/agents/pre-built-agents.md) Browse and use ready-made agents for common roles — Marketing Strategist, Content Creator, HR Assistant, and more. 2. [**Creating an Agent →**](/chatbot/agents/creating-an-agent.md) Step-by-step guide to building a custom agent — model selection, naming, instructions, and knowledge attachment. 3. [**Using Agents in Chat →**](/chatbot/agents/using-agents-in-chat.md) How to select, switch, and get the most out of agents during a conversation. 4. [**Managing Agents →**](/chatbot/agents/managing-agents.md) How to edit, update, and delete your custom agents. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.qolaba.ai/chatbot/agents.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.