What does this research mean for the field?

A new conceptual framework for Agentic Data Engineering, centered on the 'Quality of Agentic Data Use' and integrating specialized artifacts like Agentic Data Contracts and Expectations, provides an operational foundation for ensuring trustworthy AI agent-mediated data processes. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.ESTABLISHES_NEW_DIRECTION.

What question did this study set out to answer?

To establish a conceptual framework for Agentic Data Engineering centered on Quality of Agentic Data Use, addressing risks when autonomous agents execute end-to-end data workflows.

September 8, 2026Applied SciencesOpen Access

From Data Quality to Quality of Agentic Data Use: A Conceptual Framework for Agentic Data Engineering

View Full Paper

Ask AI

Bookmark

Authors

ACAnia Cravero JDJorge Díaz

Discussion

Member takes

Overview

Benchmark evaluation demonstrates framework feasibility for governing autonomous data agents across automated workflows, highlighting the critical need to separate generation from validation.

Key Points

To establish a conceptual framework for Agentic Data Engineering centered on Quality of Agentic Data Use, addressing risks when autonomous agents execute end-to-end data workflows.
Synthesized principles across data contracts, semantic layers, guardrails, AI governance, and provenance into an execution lifecycle, failure taxonomy, and reference architecture.
Implemented a controlled Databricks prototype tested across a benchmark comprising 10 cases and 40 executions within a governed sales-analysis scenario.
Demonstrated technical feasibility of the framework and enabled the independent computation of operational enforcement indicators.
Showed clear performance advantages from separating data generation from validation, while identifying that automated-repair mechanisms need further calibration.

Cite This Study

Cravero et al. (2026) studied this question.

synapsesocial.com/papers/6a9fd72a58e84d0ff5b459df https://doi.org/10.3390/app16178887

View Full Paper

Ask AI

Bookmark

September 8, 2026Applied SciencesOpen Access

From Data Quality to Quality of Agentic Data Use: A Conceptual Framework for Agentic Data Engineering

View Full Paper

Ask AI

Bookmark

Authors

ACAnia Cravero JDJorge Díaz

Discussion

Member takes

Overview

Benchmark evaluation demonstrates framework feasibility for governing autonomous data agents across automated workflows, highlighting the critical need to separate generation from validation.

Key Points

To establish a conceptual framework for Agentic Data Engineering centered on Quality of Agentic Data Use, addressing risks when autonomous agents execute end-to-end data workflows.
Synthesized principles across data contracts, semantic layers, guardrails, AI governance, and provenance into an execution lifecycle, failure taxonomy, and reference architecture.
Implemented a controlled Databricks prototype tested across a benchmark comprising 10 cases and 40 executions within a governed sales-analysis scenario.
Demonstrated technical feasibility of the framework and enabled the independent computation of operational enforcement indicators.
Showed clear performance advantages from separating data generation from validation, while identifying that automated-repair mechanisms need further calibration.

Cite This Study

Cravero et al. (2026) studied this question.

synapsesocial.com/papers/6a9fd72a58e84d0ff5b459df https://doi.org/10.3390/app16178887

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark