Direct text-to-SQL is hard to trust in production because raw schemas do not capture governed metrics or business meaning. This post walks through a local, open-source proof of concept that puts a semantic layer between the language model and the lakehouse, combining Strands, WrenAI, Trino, Iceberg, and long-term agent memory.

Provisioning a local data platform usually means fighting dependency conflicts, port clashes, and brittle Docker Compose files. odctl is a small CLI that turns Kafka, Flink, Spark, Trino, Iceberg, Airflow, and a full MLOps and observability suite into a cohesive stack you can launch with a single command. Now available on PyPI.

Providing direct access to big data engines like Spark and Flink often creates chaos. A gateway-centric architecture solves this by introducing a robust control plane. This article presents a detailed blueprint using Apache Kyuubi, a multi-tenant SQL gateway, to provision and manage on-demand Spark, Flink, and Trino engines. Learn how this model delivers true self-service analytics with centralized governance, finally resolving the conflict between user empowerment and platform stability.