For Data Teams
Curate context, monitor how the agents are used, and verify quality with evals, the governance loop behind trusted answers.
Sundial is built so business users get instant answers and the data team stays in control of how those answers are produced. This section covers the three surfaces you use to govern the platform: the Context Engine you curate, the Observability you monitor, and the Evals you use to verify quality.
The governance loop
These surfaces form a deliberate feedback loop rather than a set of disconnected tools:
- Business users ask questions and explore dashboards.
- Observability shows where answers are weak, usually missing or incomplete context.
- You improve the Context Engine: semantic definitions, AI context, or playbooks.
- Evals confirm the change improved quality and didn't regress anything else.
Over time this turns reactive firefighting into a proactive practice: you catch and fix gaps before business users hit bad answers.
What's here
| Surface | What it does |
|---|---|
| Context Engine | Curate the semantic layer, playbooks, AI context, and warehouse metadata every agent uses |
| Observability | See how the agents are used, drill into sessions, and act on trust signals |
| Evals | Define prompt/response sets that catch quality regressions before they ship |
To model the dimensions and measures the agents rely on, see the Semantic Reference.