AgentQ Overview
AgentQ is the AI assistant built into the Qualytics platform. It gives people and AI systems natural-language access to shared, governed context and the actions available through their Qualytics permissions. Powered by the Model Context Protocol (MCP) and the LLM provider configured for your deployment, AgentQ can help you explore datastores, build transformations, create quality checks, investigate anomalies, and take other supported actions.
AgentQ supports your data quality work, but it does not replace your judgment. Review generated interpretations and platform changes before relying on them, especially when they affect business-critical or regulated data.
You can interact with AgentQ through the full-page chat opened from the left sidebar, the floating chat widget available on every page (toggle with Q), and the assistant embedded in quality check and check template dialogs. The AgentQ API supports custom integrations, while external MCP-compatible clients (Claude Desktop, ChatGPT, Cursor, and others) can connect to the Qualytics MCP server.
Built-In Intelligence
- Smart Suggestions: when you start a new conversation, AgentQ generates personalized prompt suggestions based on your data assets and active anomalies.
- Context Awareness: AgentQ automatically detects the page you're on and injects relevant context (datastore, container, field, check, or anomaly) into the conversation.
- Review-Before-Save Proposals: In quality check and check template dialogs, AgentQ can propose settings from a plain-language request. Nothing is saved until you apply the proposal to the form, review the highlighted changes, and save the item.
- Permission-Aware Actions: AgentQ uses your Qualytics identity and permissions, so it can only access data and perform actions available to your account.
- Co-Authorship Tracking: changes made through AgentQ are stamped with a co-author record in the audit trail, providing a record of AI-assisted actions.
- 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 AgentQ is generating, the stream continues in the background. The response is waiting when you return to that session.
- PDF Export: export any AgentQ response as a PDF for sharing and reporting.
Description Suggestions
The sparkle control next to any description editor lets you request an AI-generated description built from the asset's metadata. It is only visible when an LLM provider is configured under AgentQ.
Click the sparkle, review the suggestion in the preview area, and either accept it (Use this), regenerate for a different take, or dismiss it. The suggested text only enters the description field when you click Use this; regenerating, dismissing, or navigating away leaves the current description untouched.
Where the sparkle appears
| Where | What the suggestion is based on |
|---|---|
| Datastores | The datastore's connection type, the containers it exposes, and its tags. |
| Tables | The table's fields, sample field types, and any tags on the table. |
| Computed Tables | The source containers or SQL definition, the resulting fields, and any tags on the computed table. |
| Files | The file's fields and any tags on the file. |
| Computed Files | The source containers or SQL definition, the resulting fields, and any tags on the computed file. |
| Fields | The field's data type, profile statistics, and neighboring fields in the same table. |
| Computed Fields | The transformation type, source fields, target type or SQL expression, and the parent container's field schema. |
| Computed Joins | The source containers, join keys, the resulting fields, and any tags on the computed join. |
| Anomalies | The anomaly's rule type, the fields it flagged, and the messages from failed checks. |
| Quality Checks | The rule type, target fields, filter, and coverage settings. |
| Quality Check Templates | The template's rule type and default settings. |
The suggestion draws on the metadata Qualytics already stores about the asset. It does not read live data rows.
What to expect
- Length. Suggestions are capped at 255 characters and cut on a word boundary, so the text you see is always a complete phrase, never a mid-word truncation.
- Same across surfaces. The interaction (sparkle to preview to Use this / Regenerate / Keep mine or Discard) is identical whether you are on a datastore, a field, or a quality check template.
- Language. The suggestion follows the language behavior of the LLM provider and model you have configured. If you need to translate the result, edit the accepted text after using it.
- Retries. Each Regenerate click starts a new AI request and can use a different framing, such as the audience, business process, downstream impact, or consequence of missing data. Results vary by provider and model, so two attempts may still produce similar suggestions. Usage is subject to the provider and commercial terms configured for your deployment.
When suggestions are not available
Even with an LLM provider configured, the platform can still refuse a suggestion in a few cases:
| Situation | What the platform does |
|---|---|
| LLM provider not configured | The sparkle is hidden. See Add Integration to connect a provider. |
| Not enough context | Very sparse assets (for example, an empty datastore with no containers yet) do not have enough metadata to produce a useful description. Add or connect data first, then try again. |
| Too much context | Very large assets (for example, a container with hundreds of fields) can exceed the request budget. Narrow the scope by suggesting on a smaller asset (a field instead of the whole table, for example). |
| Provider timeout | If the LLM provider takes too long, the platform returns a timeout error. Retry, or use a faster model in your AgentQ provider configuration. |
| Provider error | If the provider itself rejects the request (rate limit, quota, invalid API key), the error message from the provider is surfaced verbatim. See Update Integration to change model or credentials. |
On most surfaces (Computed Tables, Computed Files, Computed Fields, Computed Joins, and Quality Checks), the sparkle uses the same permission as editing the description manually: if you can edit, you can also request a suggestion. Anomalies are an exception: the sparkle appears for anyone with the Reporter team permission (or above), even though editing the anomaly description itself requires Editor. Archived anomalies never show the sparkle.
Deep Dive
-
MCP
What is the Model Context Protocol: how it works, key concepts, and why it matters.
-
AgentQ in Action
How Qualytics implements MCP: endpoint, tools, and tool step labels.
-
Conversations, Responses & Context
How to write prompts, understand AgentQ responses, and use context-aware conversations.
-
Best Practices
Prompt design, cost management, guardrail behavior, rate limits, and async operation patterns.
-
AgentQ Limits
Rate limits, token usage, timeouts, SQL constraints, and scope constraints.
-
Agentic Endpoints
Building custom applications with the agentic endpoints: integration patterns, best practices, and code examples.
How-tos
-
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 AgentQ's built-in chat.
-
Update Integration
Change your LLM provider, model, or API key.
-
Remove Integration
Disconnect your LLM provider from AgentQ.
-
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.