Documentation
Understand Lantide Data's design and operations
Getting Started
Learning Center
Role-based onboarding paths from first try to advanced practice
User Guide
Workspace, SQL, Agent, Plan/Report, Memory, and full product operations
Welcome to Lantide Data
Lantide Data is a desktop application that lets you query data files on your computer with SQL—without installing databa…
Quick Start
The walkthrough below uses Agent project analysis (order funnel example). For manual SQL only, see §2.8.
Workspace Management
A workspace is your independent working environment. Each workspace has its own SQL tabs, cached data, and data folder s…
Data Browser (Sidebar)
The sidebar is your main entry for browsing and managing data. It is built from expandable / collapsible sections (an ac…
SQL Editor and Tabs
- New tab: Click the ＋ button at the far right of the tab bar.
Query Results
After a query completes, results appear in a table below the editor. You can:
Cache and Data Reuse
Caching lets you "stage" a query result as a queryable table so other queries can reference it directly.
Source Run and Lineage
When your query references cached results from other tabs, those upstream tabs may not have run yet or their data may be…
Export Query Results
1. Run a query first so the results panel has data.
HTML Report Output
Beyond exporting query results as CSV / Excel and other formats, Lantide Data can also convert a Report document into a …
Project Management and Markdown Annotations
This chapter covers the UI operations and annotation features for Plan / Report. For an overview of the analysis flow, s…
AI Assistant
Lantide Data includes a built-in AI copilot (Agent) that understands your work state and operates the IDE directly (crea…
External AI Agents & MCP Server
Lantide Data can also act as a local MCP Server, letting your preferred external AI Agent (for example Cursor, Codex, Cl…
Skills (Skill Library)
A Skill is a reusable package of methodology and expertise: it tells the Agent how to think about a class of work, what …
Agent Memory (Knowledge Base)
When Agent Memory is enabled, the AI can generate reusable business knowledge suggestions from conversations (terminolog…
Appearance and Interface Settings
Click the theme toggle (sun / moon icon) in the top title bar to switch between dark and light themes. The editor and al…
Memory Monitoring and Management
While running, Lantide Data keeps query results, cached tables, and engine data in memory. To avoid performance issues f…
Frequently Asked Questions (FAQ)
The on-screen result preview is capped at 500 rows to keep the interface responsive. If you need the full query result, …
Appendix: Keyboard Shortcuts
Reference for keyboard shortcuts
Check for Updates and Version
1. Open the menu Help → Check for Updates...
Report an Issue
1. (Optional) Add screenshots related to the error in the dialog.
Product Design Series
Category positioning, design rationale, architecture layers, and engineering trade-offs
Series Guide and Product Positioning
Suggested order: Series Guide and Product Positioning → Agent-Era Data Analysis Workflow → Governable Agent Memory → Pro…
Agent-Era Data Analysis Workflow: Reviewable Deliverables, Collaboration, and Execution Authorization
For the complete guide, see Series Guide and Product Positioning.
Governable Agent Memory: Layering, Approval, and Catalog Injection
For the complete guide, see Series Guide and Product Positioning.
Prompt and Context Engineering: What the Model Sees and How It Thinks
For the full introduction, see Series Introduction and Product Positioning.
AI Agent Architecture: ReAct, State Routing, and UICommand
For the full introduction, see Series Introduction and Product Positioning.
Unified Query Layer: Logical Table Names, Tab Cache, and Source Run
For the full introduction, see Series Introduction and Product Positioning.