# GoPie

> GoPie is a data intelligence platform: upload or connect datasets, query
> them with SQL or plain English, chat with an AI SQL agent, and build
> dashboards and reports on top of your data.

Documentation index for LLMs. Human docs live at https://gopie.ai/docs/.
Append `llms.txt` to any docs URL for that page as raw markdown.

## Getting started

- [What is GoPie](https://gopie.ai/docs/getting-started/what-is-gopie/): GoPie turns files and databases into queryable, chat-ready datasets — every AI answer grounded in real SQL against your data.
- [Quickstart](https://gopie.ai/docs/getting-started/quickstart/): Sign in, get your bearings, and create your first project in a few minutes.
- [Upload your first dataset](https://gopie.ai/docs/getting-started/upload-your-first-dataset/): Walk a CSV through the four-step upload wizard and land on a queryable dataset with AI-ready columns.
- [Query with SQL](https://gopie.ai/docs/getting-started/query-with-sql/): Run SQL against a dataset in the built-in editor, and let AI draft queries from plain English.
- [Chat with your data](https://gopie.ai/docs/getting-started/chat-with-your-data/): Ask questions in plain language and get grounded answers with citations, runnable SQL and charts.
- [Generate your first dashboard](https://gopie.ai/docs/getting-started/generate-your-first-dashboard/): One click turns your dataset into a live dashboard of validated KPIs and charts.
- [AI in GoPie](https://gopie.ai/docs/getting-started/ai-in-gopie/): How the SQL agent answers questions, where AI assists you across GoPie, and what keeps answers grounded in your data.

## Datasets & sources

- [Datasets in GoPie](https://gopie.ai/docs/datasets/introduction/): What a dataset is, the two ways to create one, and the lifecycle from upload to version history.
- [Uploading files](https://gopie.ai/docs/datasets/uploading-files/): Formats, size limits, the upload wizard in Manual and Auto-pilot modes, and what happens after you select Create.
- [Database & cloud sources](https://gopie.ai/docs/datasets/sources/): Import query results from PostgreSQL, MySQL, Snowflake, or MotherDuck — or files from Amazon S3 — as refreshable datasets.
- [Connect to PostgreSQL](https://gopie.ai/docs/datasets/sources/postgresql/): Import the result of a SQL query from a PostgreSQL database as a GoPie dataset, with optional incremental refresh.
- [Connect to MySQL](https://gopie.ai/docs/datasets/sources/mysql/): Import the result of a SQL query from a MySQL database as a GoPie dataset, with optional incremental refresh.
- [Connect to Snowflake](https://gopie.ai/docs/datasets/sources/snowflake/): Import the result of a SQL query from Snowflake as a GoPie dataset, with optional incremental refresh.
- [Connect to MotherDuck](https://gopie.ai/docs/datasets/sources/motherduck/): Import the result of a SQL query from MotherDuck as a GoPie dataset, with optional incremental refresh.
- [Connect to Amazon S3](https://gopie.ai/docs/datasets/sources/amazon-s3/): Import a Parquet, CSV, JSON, or TSV file from Amazon S3 or any S3-compatible store as a GoPie dataset.
- [Refresh & scheduled refreshes](https://gopie.ai/docs/datasets/refresh/): Update a dataset from a new file or its source — replace or append, full or incremental — and put database imports on a schedule.
- [Schema & column descriptions](https://gopie.ai/docs/datasets/column-descriptions/): Document your dataset and its columns — by hand or with AI — and keep the search index that grounds AI answers fresh.
- [Dataset settings](https://gopie.ai/docs/datasets/settings/): A tour of the five settings tabs — General, Columns, Metadata, Access, and Maintenance — and the conventions they share.
- [Version history & time travel](https://gopie.ai/docs/datasets/version-history/): Every ingest, append, refresh, and restore records a version — preview any of them, compare two, restore one, and control how long history is kept.
- [Data cleaning](https://gopie.ai/docs/datasets/data-cleaning/): Standardise messy files on the way in — AI schema inference, assisted value fixes, dedupe, and enrichment, all behind a reviewable plan.
- [Deleting & managing datasets](https://gopie.ai/docs/datasets/deleting-datasets/): Rename, export, and delete datasets — including what a delete cascades to and who can do it.
- [Troubleshooting uploads](https://gopie.ai/docs/datasets/troubleshooting-uploads/): The upload errors you're most likely to meet, what causes each, and the fastest fix.

## Query & analyze

- [SQL playground](https://gopie.ai/docs/query/sql-playground/): Write and run read-only SQL against any dataset or view — with column autocomplete, live validation, and instant results.
- [Natural language to SQL](https://gopie.ai/docs/query/natural-language-sql/): Describe the query you want in plain English and get runnable SQL in the playground — grounded in your schema, descriptions, and documents.
- [The SQL GoPie speaks](https://gopie.ai/docs/query/sql-dialects/): GoPie runs a single, rich analytical SQL dialect everywhere — the playground, view definitions, and the API. Here's what's guaranteed and the conveniences worth knowing.
- [Saved views](https://gopie.ai/docs/query/saved-views/): Save a SQL query as a view — a virtual dataset you can preview, chat with, dashboard, and serve over the API.
- [Your dataset's REST API](https://gopie.ai/docs/query/dataset-api/): Every dataset and view is an instant read-only REST API — explore it in the app, copy a snippet, and call it with an API key.
- [Downloads & exports](https://gopie.ai/docs/query/downloads/): Export datasets, views, and query results as CSV, JSON, or Parquet — generated server-side, with links that last 24 hours.

## Chat

- [How the SQL agent works](https://gopie.ai/docs/chat/how-the-agent-works/): The tool loop behind every chat answer — schema search, SQL generation with self-repair, fuzzy value matching, and what keeps answers grounded.
- [Starting chats & choosing context](https://gopie.ai/docs/chat/starting-chats/): Every way into a chat, and how the @ context picker scopes what the agent can see.
- [Reading results](https://gopie.ai/docs/chat/reading-results/): The steps timeline, the grounded answer with citations, and the results panel with SQL results and visualizations.
- [History, sharing & reliability](https://gopie.ai/docs/chat/history-and-sharing/): Where conversations live, how visibility and share links work, and what happens when a stream drops mid-answer.
- [Save & export results](https://gopie.ai/docs/chat/save-and-export/): Turn a chat result into a reusable saved view, or download the rows as CSV, JSON, or Parquet.
- [Tips for better questions](https://gopie.ai/docs/chat/better-questions/): How to phrase questions the SQL agent answers well — specificity, time windows, business terms, and productive follow-ups.

## Chat integrations

- [How chat integrations work](https://gopie.ai/docs/integrations/overview/): Connect a workspace once, then ask GoPie questions and get grounded answers inside Slack, Microsoft Teams and Google Chat.
- [Connect Slack](https://gopie.ai/docs/integrations/slack/): Connect your Slack workspace to GoPie, then ask questions and get answers in DMs, channels and the assistant pane.
- [Connect Microsoft Teams](https://gopie.ai/docs/integrations/microsoft-teams/): Connect your Microsoft Teams tenant to GoPie so your team can ask questions in personal chats and channels.
- [Connect Google Chat](https://gopie.ai/docs/integrations/google-chat/): Allowlist the GoPie app, connect your Google Workspace with a one-time code, and ask questions in Google Chat.
- [Deliver reports to channels](https://gopie.ai/docs/integrations/reports-to-channels/): Route scheduled and one-off report deliveries to a Slack channel, Teams channel or Google Chat space, alongside email.

## Dashboards

- [Dashboards in GoPie](https://gopie.ai/docs/dashboards/introduction/): The three dashboard kinds, the live canvas and its tiles, and the toolbar that filters everything at once.
- [AI dashboard generation](https://gopie.ai/docs/dashboards/ai-generation/): One-click generation from a dataset or view, and the multi-dataset project wizard — with every phase streamed as it happens.
- [Editing with dashboard chat](https://gopie.ai/docs/dashboards/dashboard-chat/): Ask questions about a dashboard or edit it in plain language — with Ask previews you apply deliberately and Edit changes that land directly.
- [Version history & restore](https://gopie.ai/docs/dashboards/version-history/): Every dashboard change is a restorable version — browse them, restore safely, and pin the ones that must never expire.

## Reports

- [Reports in GoPie](https://gopie.ai/docs/reports/introduction/): What a report is, how frozen snapshots differ from live dashboards, and who can create and run them.
- [Creating a report](https://gopie.ai/docs/reports/creating-a-report/): The four-step wizard — goal, sources, questions with AI suggestions and validation, and the pre-generation review.
- [Snapshots, editing & export](https://gopie.ai/docs/reports/runs-and-exports/): The run history, reading a generated document, editing a snapshot without losing the original, and exporting to PDF.

## Context & knowledge

- [What makes answers smarter](https://gopie.ai/docs/context/overview/): The four kinds of context GoPie's AI draws on — descriptions, documents, custom prompts, and dictionaries — and which features use which.
- [Context documents](https://gopie.ai/docs/context/documents/): Upload reference documents — data dictionaries, codebooks, methodology notes — that the AI searches and reports cite.
- [Dictionaries](https://gopie.ai/docs/context/dictionaries/): CSV lookup tables that map coded values to human-readable labels, used by data cleaning during ingestion.
- [Custom AI prompts](https://gopie.ai/docs/context/custom-prompts/): Standing instructions on a project, dataset, or view that the AI receives every time it works with that data.

## Collaboration & admin

- [Organisations & members](https://gopie.ai/docs/collaboration/organisations-and-members/): Creating and switching organisations, inviting teammates, changing roles, transferring ownership, and leaving or deleting an organisation.
- [Roles & permissions](https://gopie.ai/docs/collaboration/roles-and-permissions/): The two independent role axes, the owner/admin/member matrix, the creator override, and how members see only what they're granted.
- [Sharing & access](https://gopie.ai/docs/collaboration/sharing-and-access/): Granting members access to projects and datasets, what a grant actually unlocks, and how chats and dashboards differ.
- [The admin console](https://gopie.ai/docs/collaboration/admin-console/): Platform-wide user and organisation management for System Admins — creating users, banning, impersonation, and org membership repair.

## Account & settings

- [Profile & security](https://gopie.ai/docs/account/profile-and-security/): Your name and password, two-factor authentication with backup codes, linked sign-in providers, and active sessions.
- [Applications & API keys](https://gopie.ai/docs/account/applications-and-api-keys/): Grouping API keys into applications, granting them exactly the projects and datasets they need, and creating keys safely.
- [Global search & shortcuts](https://gopie.ai/docs/account/search-and-shortcuts/): The ⌘K palette that jumps to any project, dataset or dashboard, and the keyboard shortcuts worth knowing.

## API & MCP

- [API overview & authentication](https://gopie.ai/docs/api/overview/): The base URL, the two kinds of API key, how requests authenticate, the identifiers you'll juggle, the error envelope, and rate limits.
- [Querying data](https://gopie.ai/docs/api/querying-data/): The endpoints that read your data over HTTP — the /tables REST facade, arbitrary read-only SQL, natural-language SQL, schemas, summaries and dialect discovery.
- [Datasets API](https://gopie.ai/docs/api/datasets-api/): List and inspect datasets, read and edit column descriptions, share a dataset with a teammate, and reindex it for chat — all over HTTP.
- [Downloads API](https://gopie.ai/docs/api/downloads-api/): Export a query result to a file — a streamed create endpoint that runs your SQL, writes it to storage, and hands back a time-limited download link.
- [Chat API & streaming](https://gopie.ai/docs/api/chat-api/): Drive the SQL agent over HTTP — create chats, stream a grounded answer as it's generated, resume an interrupted stream, and read a chat's history.
- [Dashboards API](https://gopie.ai/docs/api/dashboards-api/): Generate dashboards for a dataset, view or project, manage them with optimistic concurrency, and browse their version history — over HTTP.
- [MCP server overview](https://gopie.ai/docs/api/mcp-overview/): What GoPie's MCP server is, the organisation-wide key it requires, and how to get one — so an AI client like Claude or Cursor can query your data directly.
- [Connect an MCP client](https://gopie.ai/docs/api/mcp-setup/): Wire GoPie's MCP server into Claude Code, Claude Desktop, Cursor, or any streamable-HTTP client — plus the local stdio binary.
- [MCP tools & resources](https://gopie.ai/docs/api/mcp-tools/): The 9 tools and 3 resources a connected MCP client can use — what each does, its limits, and the upload-then-create recipe for ingesting a file.

## Trust & security

- [AI data privacy](https://gopie.ai/docs/trust/ai-data-privacy/): What the AI model actually sees, where your data stays, how to bring your own LLM provider, and the things GoPie deliberately does not do with your data.
- [Security overview](https://gopie.ai/docs/trust/security-overview/): How GoPie authenticates people and programs, isolates organisations, protects secrets at rest and in transit — and what it deliberately leaves to your own infrastructure.

## Optional

- [Full documentation](https://gopie.ai/llms-full.txt): all 68 pages concatenated as raw markdown