Introduction
Large language model agents increasingly automate data workflows, but end-to-end cloud data engineering and analytical execution require reliable coordination across code, data, infrastructure, and runtime environments.
Zero-Trust Frameworks
We present two zero-trust frameworks:
- Zero-Trust Agentic Data Engineering generates, deploys, and verifies complete cloud data-engineering solutions from natural-language tasks, with completion conditioned on repository, deployment, runtime, and policy evidence.
- Zero-Trust Agentic OLAP combines governed Data Preparation with verified Online Analytical Processing (OLAP), permitting production promotion only after validation and evidence-bound approval, and releasing analytical answers only after Same-Snapshot Execution, Exact Result Equivalence, deterministic grounding, and reflection.
Shared Abstractions
Both frameworks share three abstractions:
- Graph engineering for evidence-gated workflow structure.
- Loop engineering for bounded recovery.
- Agent-harness engineering for zero-trust execution.
Evaluation
We evaluate both frameworks under nominal execution, controlled failures, bounded recovery, and policy-constrained conditions, measuring verified completion, recovery, authorization enforcement, production promotion, and verified OLAP execution.