# Data steward agent

> Explain where a metric comes from, who owns it and why it changed, using lineage and tests. When a dashboard number looks wrong, people ask the data team.

Source: https://datanature.ai/use-cases/data-steward-agent-cross-industry
Publisher: Dlytica Inc. (DataNature is a Dlytica company)
Updated: 2026-11-05

Industry: Cross-industry. Function: Data platform. Built with: Voir, DataNature.

## What does the data steward agent do?

When a dashboard number looks wrong, people ask the data team. The steward agent traces the metric through Atlas lineage to its sources, reports recent dbt test failures and load gaps, and names the owner.

## How is the agent designed?

- **Pattern**: Single agent over catalog, lineage and run history.
- **Data scope**: Atlas catalog, lineage, run history and test results.
- **Human approval**: Re-runs and data fixes are performed by engineers.
- **Platform components**: Voir, Atlas, Data Engineering

## How does it work on DataNature?

1. **Ground it in governed data.** Certified Gold tables and semantic-layer cubes give the agent consistent numbers; DocuContext partitions give it documents with links to source; the knowledge graph gives it relationships between entities where the use case needs them.
2. **Scope the twin.** The Voir twin's data scope, document partitions and SQL allowlist are enforced by the Agent Meta-Harness inside every tool call, and Atlas applies masks and row filters for the user it acts for.
3. **Route the model.** The AI gateway sends requests to an approved model endpoint and logs tokens, cost and latency.
4. **Keep a human in the loop.** The agent recommends; people approve actions that change systems.
5. **Trace and evaluate.** Every turn is traced, and answer quality is evaluated against real questions before and after each change.

## What data does it use?

- Lineage
- dbt run results
- Pipeline monitoring
- Ownership metadata

## Why run it on a sovereign platform?

The data, prompts, retrieved passages, model inference and logs all stay inside your jurisdiction, so the agent can work on regulated data without sending it to a foreign service.

## How do we get started?

Dlytica Consulting can scope and build it, NeuralShore engineers can join your team, and Dlytica Academy-trained talent is ready to support it. Book a demo with Dlytica to see it on your own data.
