Language:JapaneseEnglish

oracle-ai-data-platform-workbench-engineer-agent Claude Code Plugin

Author
Oracle
Category
Development
Topics
Data Engineering & Analytics · Databases & Storage · Enterprise Business Platforms
First cataloged
2026-07-09 (UTC)
Explanation last updated
2026-09-23 (UTC)
Source (GitHub) last updated
2026-10-05 (UTC) (10 days ago)

The explanation below is AI-generated. Please verify it against the sources.

This plugin provides a Claude Code agent that operates Oracle AI Data Platform (AIDP) Workbench through natural language, organized into 37 skills covering the data engineering lifecycle. It builds a local cache of catalog metadata to ground requests and convert plain-language questions into accurate Spark SQL, supporting table lifecycle operations such as create, insert, update, delete, merge, optimization, vacuum, and time-travel queries. It also handles file ingestion, data profiling, quality rule configuration, pipeline authoring and repair, cluster provisioning, and job debugging through the Spark UI. Governance features include role and permission management, credential storage, data sharing, and audit logging, alongside Git version control, deployment bundling, and MLOps/MLflow tracking. It operates through Oracle's official aidp command-line tool, falling back to direct REST calls when necessary, without requiring a separate MCP server.

About the service

Oracle AI Data Platform Workbench is Oracle's cloud service for cataloging, ingesting, and analyzing data within a Spark/Delta lakehouse environment, providing the infrastructure for building data pipelines and running analytics workloads.

What you can do with oracle-ai-data-platform-workbench-engineer-agent

  • Discover data sources and organize catalog metadata into a local grounding cache
  • Ingest files, profile datasets, and configure data quality rules
  • Author and repair scheduled pipelines, provision compute clusters, and debug jobs via the Spark UI
  • Manage governance features such as roles, credential storage, data sharing, and audit logs
  • Use Git-based version control, packaging bundles, and MLOps/MLflow tracking
  • Build AI agent flows, knowledge base retrieval, and reusable tools within the platform

Sources

Back to list