AI agents
Ask questions in plain language and get governed answers, charts, and dashboards from your metrics
AI agents are available as an add-on for all plans. View pricing
Qyra AI agents let your team ask questions in natural language and get answers built from your semantic layer — the saved dashboards, metrics, dimensions, joins, and descriptions you've already defined. An agent picks the relevant models and metrics, builds and runs the query with the right filters and parameters, and returns the result as the chart, table, or summary that fits the question. Because every answer runs through the semantic layer, it respects the same project permissions and user attributes as the rest of Qyra.
You can run agents in the Qyra app or in Slack, scope each one to a domain with tags, and improve them over time with verified answers, evaluations, and knowledge documents. The pages below cover setup, day-to-day use, governance, and the features that make agents more accurate.
Looking for Autopilot? Autopilot is a separate, admin-only agent that runs on a schedule to keep your project clean — fixing broken charts, flagging stale content, and suggesting new ones. It does not build charts or dashboards from user questions like the conversational agents described here.
Choosing your AI surface
Qyra exposes several AI surfaces, and the right one depends on who is asking, what they're trying to do, and how much governance you need. They share one foundation: the Qyra semantic layer — governed metrics, joins, descriptions, permissions, project context, verified answers, and evaluations. Investing there pays off no matter which surface a user picks.
Decision guide
Pick the first item that matches what you're trying to do:
- Let business users ask governed questions in natural language — use AI agents in the app, or in Slack when the answer belongs in a team conversation.
- Send an agent answer on a schedule — schedule a recurring delivery from a conversation so Qyra re-runs the agent on your chosen frequency and sends the refreshed chart plus an AI-written summary to Slack, email, or Microsoft Teams.
- Query Qyra from Claude, Cursor, Codex, ChatGPT, or a custom agent — use the Qyra MCP server.
- Give your agents tools from Notion, Linear, Confluence, or other services — connect external MCP servers.
- Teach your AI coding tool Qyra concepts and YAML syntax — add the Docs MCP and install agent skills.
- Build an interactive, shareable app from a prompt — use data apps.
- Create or edit saved charts and dashboards conversationally — use content editing. (Beta)
- Make bulk, reviewable dashboard changes — use dashboards as code with
qyra downloadandqyra upload. - Change a metric, dimension, join, or description — edit dbt or Qyra YAML through Git, or use AI writeback.
- Change code in another connected repository (not the dbt project) — use the AI coding agent to open a pull request on any repo your org can write to, with verification delegated to that repo's own CI. (Beta)
- Fix something the agent got wrong — improve descriptions, AI hints, project context, verified answers, evaluations, or Issues findings. (Issues is Beta.)
Compare the surfaces
| Surface | Best for | Typical user | Governance model |
|---|---|---|---|
| AI agents (app & Slack) | Governed self-serve questions and visualizations | Business user | Agent tag scope, project permissions, user attributes |
| Qyra MCP server | Querying Qyra from external AI clients | Power user, developer, analyst | OAuth, project permissions, user attributes |
| External MCP servers | Giving your agents tools from outside services | Agent builder | Per-project config, per-user or shared OAuth |
| Docs MCP + agent skills | Giving coding agents Qyra concept and YAML context | Developer with an AI IDE | Public docs, local to the developer |
| Data apps | Interactive, shareable apps generated from a prompt | Analyst, app builder | Project role and space access; queries run through Qyra |
| Content editing (Beta) | Conversational chart and dashboard creation and edits | Analyst, agent operator | Enabled per agent, scoped by agent permissions |
| Dashboards as code | Bulk, reviewable, version-controlled dashboard changes | Developer, analytics engineer | Git review, previews, validation |
| AI writeback | Agent-proposed changes to dbt / Qyra YAML | Analytics engineer | Git review, dbt / Qyra validation |
| AI coding agent (Beta) | Agent-proposed changes to any connected repository, not just the dbt project | Developer, analytics engineer | Feature flag, org's Git App install + user access intersection, denied-path commit gate |
A few principles hold across all of them: keep agents focused — several domain-scoped agents beat one project-wide agent; treat raw SQL as an escape hatch and fix the semantic layer when routine questions need it; and never upload sensitive material as knowledge documents unless everyone who can use the agent is allowed to see it. For the full treatment, see Effective analytics with agents.