Agent Q Overview
Agent Q is the AI assistant built into the Qualytics platform. Powered by the Model Context Protocol (MCP) and your choice of LLM provider, Agent Q turns natural language into action — exploring datastores, building transformations, creating quality checks, investigating anomalies, and more.
You can interact with Agent Q in several ways: through the full-page chat opened from the left sidebar, the floating chat widget available on every page (toggle with Q), the Agent Q API for custom integrations, and any external MCP-compatible client (Claude Desktop, ChatGPT, Cursor, and others) connected to the Qualytics MCP server.
Built-In Intelligence
- Smart Suggestions — When you start a new conversation, Agent Q generates personalized prompt suggestions based on your data assets and active anomalies.
- Context Awareness — Agent Q automatically detects the page you're on and injects relevant context (datastore, container, field, check, or anomaly) into the conversation.
- Co-Authorship Tracking — All changes made through Agent Q are stamped with a co-author record in the audit trail, so you always know which actions were AI-assisted.
- Conversation Memory — Long conversations are automatically managed through context compression, keeping recent messages in full detail while summarizing older context. See Conversations, Responses & Context for details.
- Background Streaming — If you navigate away while Agent Q is generating, the stream continues in the background. The response is waiting when you return to that session.
- PDF Export — Export any Agent Q response as a PDF for sharing and reporting.
Deep Dive
-
MCP
What is the Model Context Protocol — how it works, key concepts, and why it matters.
-
Agent Q in Action
How Qualytics implements MCP — endpoint, tools, and tool step labels.
-
Conversations, Responses & Context
How to write prompts, understand Agent Q responses, and use context-aware conversations.
-
Best Practices
Prompt design, cost management, guardrail behavior, rate limits, and async operation patterns.
-
Agent Q Limits
Rate limits, token usage, timeouts, SQL constraints, and scope constraints.
-
Agentic API
Building custom applications with the Agentic API — integration patterns, best practices, and code examples.
Managing
-
Connecting External AI Clients
Connect ChatGPT, Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, or Amazon Q Developer to the Qualytics MCP server.
-
Add Integration
Configure your LLM provider to power Agent Q's built-in chat.
-
Update Integration
Change your LLM provider, model, or API key.
-
Remove Integration
Disconnect your LLM provider from Agent Q.
-
Start a New Conversation
Create a fresh conversation from the sidebar, chat header, or floating chat.
-
Resume a Conversation
Return to a previous conversation and continue from where you left off.
-
Rename a Conversation
Give a conversation a descriptive title for easier navigation.
-
Archive a Conversation
Move a conversation out of the active list into the archived section.
-
Restore a Conversation
Bring an archived conversation back to the active list.
-
Delete a Conversation
Permanently remove an archived conversation.
-
Search Conversations
Filter active conversations by title or message content to find a specific conversation.
-
Chat Interface Tips
Refresh the chat list, collapse the sidebar, attach files, paste large content, stop a response, and use prompt suggestions.