Skip to main content

DataGOL Documentation Hub

Welcome to DataGOL Documentation Hub

DataGOL is an AI-native Data and Agents platform. DataGOL helps teams launch governed AI agents on enterprise data in days, not months. DataGOL does this by providing the infrastructure to launch AI agents—combining the unified data stack, context management, and agentic capabilities into a single platform that enables organizations to deploy AI internally and build AI-native products externally. It has two main components - AgentOS and DataOS. DataOS enables agentic creation of semantic data model and context both from structured and unstructured data. AgentOS is a composable AI platform, which sits on top of DataOS and accelerates creation of Agents using multi-agent orchestration. Agents can be embedded in client's products as well. With DataGOL, in just a few weeks, you can unify your data sources, automate complex data management workflows and build AI agents tailored to specific business needs.

This introduction page orients you to the entire doc set and suggests where to start, whether you are a data engineer wiring up sources, an analyst building dashboards, or a product team embedding AI‑powered insights in your app.

How the docs are organized​

TopicWhat you will findWhy it matters
Getting StartedOne‑page setup, quick tour, and your first workbookFast path from zero to an interactive, AI‑ready workspace.
DataGOL conceptsKey objects (Lakehouse, Workbooks, Lineage, Agents) and how they fitShared mental model before you dive deep.
LakehouseConnecting data sources, building Pipelines, managing tables and partitionsCentral, governed store that feeds everything else
PlaygroundAd‑hoc SQL + AI Copilot for query generation and optimizationRapid exploration and SQL assistance without leaving the browser
AI AgentsChart/BI agent, Data‑extraction agent, custom agentsGuided, persona‑based analysis that speeds up discovery
BI AnalyticsDrag‑and‑drop charts, AI‑generated dashboardsTurn data into executive‑ready visuals in clicks
Data LineageSource, pipeline, and workbook‑level lineage views plus impact analysisTrace every field end‑to‑end for trust, compliance, and blast‑radius checks
Machine Learning (ML)Model training, prediction APIs, and MLOps hooksUse the same data foundation for predictive workflows
Workspaces and WorkbooksMulti‑team tenancy, versioning, API access, export optionsStructure projects and share results at scale
Best PracticesOpinionated guidance on security, performance, and governanceAvoid rookie mistakes and design for scale from day one
Release NotesWhat’s new, changed, deprecatedStay aligned with platform evolution

Suggested first steps​

  • Read Getting Started topic. Set up your first Lakehouse, connect a data source, and publish a Workbook in under 15 minutes.

  • Explore the Playground. Run a sample query and test the SQL Copilot.

  • Generate a dashboard with AI. Pick the Business Executive persona and watch DataGOL auto‑build KPIs.

  • Inspect Lineage. Open the Lineage tab in your workbook to see upstream sources and downstream consumers.

  • Review Best Practices before pushing to production.

Who should use these docs​

  • Business users - for workbooks, visualizer, dashboards and insights
  • Data engineers – for connectors, pipelines, and API automation
  • Analysts and domain experts – for Playground queries, BI visualizations, and AI Agents
  • ML engineers – for ML module, feature sourcing, and model deployments
  • Developers/ISVs – for embedding analytics via the Workbook REST API
  • Governance and security teams – for data lineage, audit controls, and role‑based access
Keep the feedback loop tight

Every page has a Was this helpful? widget. Drop a note any time. Your input directly shapes the docs. Happy building.

The DataGOL Documentation Team

Was this helpful?