# Autofiling the Boring Semantic Layer: From Sakila to Chat-BI with dltHub

DevFeed: [Autofiling the Boring Semantic Layer: From Sakila to Chat-BI with dltHub](<https://devfeed.tech/articles/autofiling-the-boring-semantic-layer-from-sakila-to-chat-bi-with-dlthub-80258.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/building-semantic-models-with-llms-and-dlt>)

Author: Adrian Brudaru

Published: 2026-01-07T00:00:00Z

Content type: article

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [semantic-layer](<https://devfeed.tech/topics/semantic-layer.md>), [hybrid-search](<https://devfeed.tech/topics/hybrid-search.md>), [MSP MCP](<https://devfeed.tech/topics/msp-mcp.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [API Monetization](<https://devfeed.tech/topics/api-monetization.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [ai](<https://devfeed.tech/tags/ai.md>), [automation](<https://devfeed.tech/tags/automation.md>), [data-products](<https://devfeed.tech/tags/data-products.md>), [industry](<https://devfeed.tech/tags/industry.md>), [llms](<https://devfeed.tech/tags/llms.md>), [product](<https://devfeed.tech/tags/product.md>), [semantic-layer](<https://devfeed.tech/tags/semantic-layer.md>)

## AI overview

The article demonstrates a workflow that combines dlt schema discovery, LLM-generated semantic definitions, and the Boring Semantic Layer. It describes how one model can serve BI, APIs, notebooks, and MCP-enabled chatbots, with engineers reviewing generated relationships and metrics and managing definition changes through code review and CI/CD.

## Source excerpt

Build one semantic model and reuse it across APIs, chatbots, and apps. Let LLMs handle the tedious mapping so you can ship data products that quietly just work.