Announcing StackOne Documents API - a unified API and File Picker for your customers' knowledge

Integrate once to access every customer document — across cloud storage and knowledge bases — with a native picker and real-time, privacy-first architecture.

StackOne launched the Unified Documents API and File Picker, designed for AI agents, RAG pipelines, and enterprise SaaS applications requiring secure document access. The platform addresses customer pain points around connecting to file storage and knowledge bases — different auth models, inconsistent hierarchies, and weeks of engineering work for each provider.

With one API, you can search, retrieve, and interact with files from SharePoint, OneDrive, Google Drive, Confluence, and Notion.

Build AI and Knowledge Products That Are Context-Aware

Connecting to your customers’ file storage and knowledge bases has always been painful. Every provider comes with:

• No standard way to select files across providers
• Clunky or non-existent SDKs
• Sparse, inconsistent documentation and functionality gaps

The Documents API enables:

• Power AI assistants that fetch documents, metadata, and content instantly
• Enable users to attach files to CRM records, tickets, or training modules from their storage
• Allow dropping files from corporate drives into live chat conversations in one click
• Keep customers’ policies and compliance documents synced from approved locations

What’s Available Today

Currently supported providers:

• Notion
• Confluence
• Google Drive
• OneDrive
• SharePoint
• Dropbox, Workday, and Box coming soon

One API for Every Provider

List, upload, and manage files, folders, and drives through a single interface. Standardized fields — id, name, size, created_at, url, and more — work across all platforms without platform-specific code modifications.

Embeddable File Picker

A TypeScript/React file picker provides a native-feeling file browsing experience. It works across all connected providers, offering secure file and folder selection.

Enterprise-Ready Authentication

Connections run through StackOne Hub, managing a single flow, token lifecycle, and permission model. The system supports both:

• Admin-level connections for org-wide sources
• User-level connections for personal drives

Both can be used together.

Built for AI-Driven Products

The Documents API and File Picker support real-time document fetching, metadata extraction, and webhook subscriptions for keeping agents and knowledge systems current.

Why You’ll Love It

• Build once, connect to many. No one-off integrations, no separate SDKs per provider.
• A file-browsing experience that feels native — without designing it from scratch.
• Skip the headaches. No pagination quirks, permissions inconsistencies, or platform-specific edge cases.

Get Started

Book a demo or dive into the documentation to start building today.

FAQs

Do you store customer documents?

No. StackOne retrieves files in real time from source systems without persisting them. Metadata may be cached temporarily for performance, but file contents are not stored.

How do admin-level and user-level connections work?

Admin-level connections provide org-wide access (scoped to approved folders/sites) for shared knowledge. User-level connections allow individuals to connect personal storage. Both can be used together.

What’s supported per provider today?

Each provider supports read/write, picker UI, and webhooks where its API allows. Dropbox and Workday are coming soon.

How do you handle permissions?

StackOne honors the source system’s ACLs. If a user doesn’t have access to a SharePoint folder, it won’t appear in the picker or API results.

What about rate limits?

Provider-imposed limits are respected with guidance for batching, incremental syncs (via nested_items or delta tokens), and backoff strategies.

Can this run in a headless AI agent context?

Yes. The Unified Documents API can be used without the File Picker. Set up service accounts or admin connections, then invoke the API from your agent’s tool set.