# Agentic Data Engineering Is Here -- But Can It Close the Loop?

DevFeed: [Agentic Data Engineering Is Here -- But Can It Close the Loop?](<https://devfeed.tech/articles/agentic-data-engineering-is-here-but-can-it-close-the-loop-38703.md>)

Original publisher: [Read original article](<https://dataengineeringcentral.substack.com/p/agentic-data-engineering-is-here>)

Author: Daniel Beach

Published: 2026-07-22T14:05:27Z

Content type: article

Language: en

Sources: [Data Engineering Central](<https://devfeed.tech/sources/data-engineering-central.md>)

Topics: [data-engineering](<https://devfeed.tech/topics/data-engineering.md>), [Orchestration](<https://devfeed.tech/topics/orchestration.md>), [data observability](<https://devfeed.tech/topics/data-observability.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [DuckDB](<https://devfeed.tech/topics/duckdb.md>), [Apache Iceberg](<https://devfeed.tech/topics/apache-iceberg.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [data-engineering](<https://devfeed.tech/tags/data-engineering.md>), [duckdb](<https://devfeed.tech/tags/duckdb.md>), [orchestration](<https://devfeed.tech/tags/orchestration.md>), [pipelines](<https://devfeed.tech/tags/pipelines.md>)

## AI overview

A podcast conversation with Hugo Lu about agentic data engineering and the infrastructure needed for data platforms to execute work, observe outcomes, validate changes, and improve pipelines safely. It examines why production data systems remain difficult for AI, including schema changes, realistic testing, business semantics, and secure execution.

## Source excerpt

a conversation with Hugo Lu