> For the complete documentation index, see [llms.txt](https://help.tellius.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.tellius.com/tellius-6.2/data/data-architect-agent.md).

# Data Architect Agent

Use the Tellius Data Architect Agent to build governed data models—automate schema discovery, joins, and validation to create analytics-ready semantic layers fast.

Setting up a Business View is normally a multi-step, multi-module workflow. You connect to a data source, profile the tables, configure joins in the data preparation interface, create calculated columns, enrich metadata, and validate the result. Each step has its own screen, and the process can take anywhere from 10 to 25 hours depending on schema complexity, particularly when derived tables, custom formulas, and thorough validation are involved.

**Data Architect** collapses this entire workflow into a single Kaiya conversation. It is a Kaiya agent that creates, edits, and validates Business Views conversationally from raw data sources. The agent handles schema analysis, join inference, calculated column creation, metadata enrichment, and pre-publish validation without requiring you to navigate between modules or write SQL.

#### Two modes of operation

Data Architect supports two starting points. You can create a new Business View from scratch by selecting tables from a connected data source, or you can open an existing Business View for editing. When editing an existing BV, the agent loads the current YAML configuration and makes it available for conversational modification, including adding tables, adjusting joins, creating columns, or running validation.

{% hint style="info" %}
Snowflake and Redshift (in Live mode) are the only supported data sources for direct table discovery. For all other data sources, the datasets must be pre-loaded into Tellius before starting a Data Architect conversation.
{% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://help.tellius.com/tellius-6.2/data/data-architect-agent.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.