📄️ Getting Started
First steps after signing up — navigate the dashboard, understand your organization, and find your way around the platform
📄️ Create a Data Plane
Register a data plane to host data clusters — primarily for on-premise enterprise deployments
📄️ Create a Data Cluster
Create an isolated data cluster to store and process your document collections
📄️ Create a Dataset
Create a dataset, choose a schema, and configure a processing pipeline
📄️ Upload Documents
Upload files, monitor processing status, and verify results
📄️ Configure a Pipeline
Pipeline presets, auto-trigger settings, and custom configuration options
📄️ Pipeline Presets & the General Purpose Pipeline
Apply, discover, and trigger dataset processing presets through the Data API
📄️ Search and Query
Expose your documents to AI agents and users through workflows, MCP, and direct search
📄️ AI Agent Integration
Connect AI agents to your data via the Model Context Protocol (MCP)
📄️ Manage Your Organization
Users, roles, invitations, API tokens, and billing
📄️ Install SDK
Install the data-api-client SDK for Python or TypeScript
📄️ Deploy MCP
Deploy an MCP server on your data cluster to connect AI agents to your documents
📄️ Organization User Management
Create service accounts for programmatic access and managed users who log in via the platform
📄️ Alien Marketplace
Extend Claude Code with research intelligence plugins from the Alien Marketplace
📄️ Attach Files to an Agent
Upload a docx / xlsx / pdf and pass it to a Responses API run so the agent can read it with docx_read / xlsx_read / pdf_read — using the OpenAI-compatible Files API.
📄️ Connector Examples
Working examples for each connector showing user prompts, tool calls, and expected output
📄️ Connect with Claude
Connect Alien Intelligence connectors to Claude Desktop, Claude Code, and claude.ai
📄️ Connect with ChatGPT
Connect Alien Intelligence connectors to ChatGPT
📄️ Connect with Le Chat
Connect Alien Intelligence connectors to Mistral Le Chat
📄️ Querying Metrics with GraphQL
Read dashboard, consumer, and dataset metrics and execution history through the platform's data-owner GraphQL endpoint