# Introduction to AgentQ Source: https://userguide.qualytics.io/agentq/deep-dive/introduction/ AgentQ is the AI assistant built into Qualytics. It answers questions about your workspace, explains what it finds, and carries out platform actions on your behalf, all from a chat. The Deep Dive explains AgentQ in depth. Here you will learn what AgentQ is and what it does, where it appears and how a single turn runs, which AI providers can run it and how to connect them, what it is allowed to see and share with the model, how its actions are governed and recorded, and how to get good results from it. It explains the machinery rather than the clicks. For step-by-step instructions, such as connecting a provider or managing your chats, see the How-tos. ## Where to Start Read **How It Works** first. It sets out the surfaces AgentQ appears on, what happens during a single turn, and the two limits that decide what it can reach. Everything else here goes deeper on one piece of that picture. From there the section falls into four groups, the same ones you see in the navigation. - **Using AgentQ.** **The Chat Interface**, **Conversations, Responses & Context**, and **AgentQ Limits** cover the chat controls, writing good prompts and reading the answers, and the ceilings you will meet. - **Tools.** **AgentQ in Action**, **Tool Catalog**, and **Semantic Reporting** cover what AgentQ can do. External clients connect through the separate [Qualytics MCP server](https://userguide.qualytics.io/using-the-platform/mcp/). - **AI Providers.** **Supported AI Providers** and **Amazon Bedrock Authentication** cover what can run AgentQ and how to authenticate to it. - **Governance.** **Access Controls** and **AgentQ Audit** cover how much of your data AgentQ may send to the model, and what is recorded. The section closes with **Examples** of worked scenarios, **Best Practices** for getting good results without burning through your provider budget, and **Permissions**, which covers who may use and configure AgentQ. To build your own applications on the same capabilities, see the [AgentQ API](https://userguide.qualytics.io/agentq/api/). ## What This Section Covers - **How It Works** Where AgentQ appears, how a turn runs, what it is allowed to see, and its built-in features, including description suggestions. [How It Works](https://userguide.qualytics.io/agentq/deep-dive/how-it-works/) ### Using AgentQ - **The Chat Interface** Every control in the full-page and floating chat, and what the input accepts. [The Chat Interface](https://userguide.qualytics.io/agentq/deep-dive/chat-interface/) - **Conversations, Responses & Context** How to write prompts, read AgentQ responses, and work with context-aware chats. [Conversations, Responses & Context](https://userguide.qualytics.io/agentq/deep-dive/conversations/) - **AgentQ Limits** Rate limits, token usage, timeouts, SQL constraints, and scope constraints. [AgentQ Limits](https://userguide.qualytics.io/agentq/deep-dive/limits/) ### Tools - **AgentQ in Action** Worked examples of AgentQ, its tools, and the steps shown in chat. [AgentQ in Action](https://userguide.qualytics.io/agentq/deep-dive/in-action/) - **Tool Catalog** Every tool AgentQ can call, what each one does, and what it shares with the model. [Tool Catalog](https://userguide.qualytics.io/agentq/deep-dive/tool-catalog/) - **Semantic Reporting** The structured query interface AgentQ uses to count, filter, and inspect platform resources. [Semantic Reporting](https://userguide.qualytics.io/agentq/deep-dive/semantic-reporting/) ### AI Providers - **Supported AI Providers** Every provider you can connect and which ones support file attachments. [Supported AI Providers](https://userguide.qualytics.io/agentq/deep-dive/supported-ai-providers/) - **Amazon Bedrock Authentication** The three ways to authenticate to Bedrock, and what an IAM role setup expects. [Amazon Bedrock Authentication](https://userguide.qualytics.io/agentq/deep-dive/bedrock-authentication/) ### Governance - **Access Controls** How an administrator chooses what chat may share with the model, and what each level unlocks. [Access Controls](https://userguide.qualytics.io/agentq/deep-dive/access-controls/) - **AgentQ Audit** What each audit entry holds, how cost estimates work, and what the period summary reports. [AgentQ Audit](https://userguide.qualytics.io/agentq/deep-dive/audit/) - **Examples** Worked scenarios showing what you ask AgentQ, what it does, and the shape of the answer. [Examples](https://userguide.qualytics.io/agentq/deep-dive/examples/) - **Best Practices** Prompt design, cost management, guardrail behavior, rate limits, and async operation patterns. [Best Practices](https://userguide.qualytics.io/agentq/deep-dive/best-practices/) - **Permissions** The user roles behind chatting with AgentQ, configuring it, and reading the audit. [Permissions](https://userguide.qualytics.io/agentq/deep-dive/permissions/) ## See Also - **How It Works** Where AgentQ appears, how a turn runs, what it is allowed to see, and its built-in features, including description suggestions. [How It Works](https://userguide.qualytics.io/agentq/deep-dive/how-it-works/) - **The Chat Interface** Every control in the full-page and floating chat, and what the input accepts. [The Chat Interface](https://userguide.qualytics.io/agentq/deep-dive/chat-interface/) - **Conversations, Responses & Context** How to write prompts, read AgentQ responses, and work with context-aware chats. [Conversations, Responses & Context](https://userguide.qualytics.io/agentq/deep-dive/conversations/) - **AgentQ Limits** Rate limits, token usage, timeouts, SQL constraints, and scope constraints. [AgentQ Limits](https://userguide.qualytics.io/agentq/deep-dive/limits/) - **AgentQ in Action** Worked examples of AgentQ, its tools, and the steps shown in chat. [AgentQ in Action](https://userguide.qualytics.io/agentq/deep-dive/in-action/) - **Tool Catalog** Every tool AgentQ can call, what each one does, and what it shares with the model. [Tool Catalog](https://userguide.qualytics.io/agentq/deep-dive/tool-catalog/) - **Semantic Reporting** The structured query interface AgentQ uses to count, filter, and inspect platform resources. [Semantic Reporting](https://userguide.qualytics.io/agentq/deep-dive/semantic-reporting/) - **Supported AI Providers** Every provider you can connect and which ones support file attachments. [Supported AI Providers](https://userguide.qualytics.io/agentq/deep-dive/supported-ai-providers/) - **Amazon Bedrock Authentication** The three ways to authenticate to Bedrock, and what an IAM role setup expects. [Amazon Bedrock Authentication](https://userguide.qualytics.io/agentq/deep-dive/bedrock-authentication/) - **Access Controls** How an administrator chooses what chat may share with the model, and what each level unlocks. [Access Controls](https://userguide.qualytics.io/agentq/deep-dive/access-controls/) - **AgentQ Audit** What each audit entry holds, how cost estimates work, and what the period summary reports. [AgentQ Audit](https://userguide.qualytics.io/agentq/deep-dive/audit/) - **Examples** Worked scenarios showing what you ask AgentQ, what it does, and the shape of the answer. [Examples](https://userguide.qualytics.io/agentq/deep-dive/examples/) - **Best Practices** Prompt design, cost management, guardrail behavior, rate limits, and async operation patterns. [Best Practices](https://userguide.qualytics.io/agentq/deep-dive/best-practices/) - **Permissions** The user roles behind chatting with AgentQ, configuring it, and reading the audit. [Permissions](https://userguide.qualytics.io/agentq/deep-dive/permissions/) *Last updated: November 7, 2026.*