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

# AI As Data

Models often sit outside the warehouse, so every prediction needs a separate service. The page treats them instead as AI tables you query with SQL, through MindsDB: what the server does, who it is for, and the article that introduces the idea.

The tool behind the idea is [MindsDB](https://mindsdb.com/?utm_medium=community\&utm_source=github\&utm_campaign=mindsdb%20repo) ML-SQL Server enables machine learning workflows for the most powerful databases and data warehouses using SQL. The code is on [GitHub](https://github.com/mindsdb/mindsdb). Both addresses now present the company's newer product, MindsHub, a unified workspace for choosing among AI models and providers.

The same server serves three audiences. Developers can quickly add AI capabilities to your applications. Data Scientists can streamline MLOps by deploying ML models as AI Tables. Data Analysts can easily make forecasts on complex data (like multivariate time-series with high cardinality) and visualize them in BI tools like Tableau.

The AI-table idea itself is explained in Javi's [Medium article](https://medium.com/data-science/introduction-to-ai-tables-a719251e1a58), Introduction to AI Tables, which shows how to integrate ML inside databases using MindsDB. The same Medium article is also at its original address: <https://towardsdatascience.com/introduction-to-ai-tables-a719251e1a58>


---

# 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://www.mlcompendium.com/ai-engineering/ai-as-data.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.