Over the past decade, the Modern Data Stack has built a rich ecosystem of tools for data engineers, covering data ingestion, lakehouse architecture, orchestration, governance, BI, and AI. However, in the Agentic era, data platforms need to evolve further: from “humans operating tools” to “humans defining goals, and Agents orchestrating execution.”

This talk will explore a new platform paradigm: Harness Engineering for Data. It will discuss how data ingestion, ETL/ELT, SQL development, orchestration, data quality, metadata, lineage, monitoring, and enterprise ontology can be unified and packaged as engineering capabilities that Agents can understand, invoke, and govern.

By injecting business ontology, technical metadata, and execution context into Agent workflows, enterprises can enable Agents to better understand data objects and business relationships, execute Skills more efficiently, reduce context guessing and token consumption, and improve the accuracy of ETL pipeline generation, SQL output, data modeling, and visualization analysis.

Ultimately, data engineering platforms will evolve from traditional collections of tools into a Data Engineering Harness designed for human-Agent collaboration, helping enterprises achieve more efficient, trustworthy, and governable data engineering delivery in the Agentic era.

Speakers:

William Guo: Apache Software Foundation Member

• Apache Software Foundation Member
• Apache IPMC Member
• PMC of Apache DolphinScheduler
• Mentor of Apache SeaTunnel(incubating)
• Founder of ClickHouse China Community
• Track Chair of Workflow/Data Governance of Apache Con Asia 2021/2022

William used to be the CTO of Analysys and the Senior Big Data Director of Lenovo, general manager of bid data in Wanda. He worked as Big Data Director/manager at CICC, IBM, and Teradata. He has more than 20 years of experience in big data technology and data management.