Integrations

Captain connects to your data wherever it lives. There are two ways Captain searches your data — Indexed Search and Live Search — and some integrations support both.

Search Types

Files are uploaded to cloud storage (S3, GCS, Azure), then processed by Captain’s RAG engine. Documents are chunked, embedded, and stored for fast semantic search across large volumes of unstructured data.

Best for: Documents, knowledge bases, archival data, spreadsheets, presentations, and any files you want to search semantically.

How it works:

  1. Upload files to S3, GCS, or Azure — or use the Captain Studio to connect Google Drive, SharePoint, Notion, Dropbox, or OneDrive
  2. Call the indexing API (or let the Studio handle it) to process files into searchable chunks
  3. Query the collection — Captain retrieves relevant chunks and optionally generates an AI response

Real-time queries against connected services. No indexing step — results come directly from the source API at query time, always reflecting the current state of the data.

Best for: Messages, issues, tasks, emails, calendar events, and live database queries where freshness matters.

How it works:

  1. Connect the integration via Captain Studio (credentials or OAuth)
  2. Ask questions in the chat interface — Captain’s agent calls the service API in real-time
  3. Results are always up-to-date

Indexed Search Integrations

Index files from cloud storage providers via the API, or connect SaaS platforms through the Captain Studio.

Cloud Storage (API)

Amazon S3
Amazon S3
Google Cloud Storage
Google Cloud Storage
Azure Blob Storage
Azure Blob Storage

SaaS Platforms (Studio)

Google Drive
Google Drive
SharePoint
SharePoint
OneDrive
OneDrive
Dropbox
Dropbox
Notion
Notion
Snowflake (Stage Files)
Snowflake (Stage Files)

Live Search Integrations

Real-time queries against connected services. Connect via Captain Studio — no indexing required.

Snowflake (SQL Search)
Snowflake (SQL Search)
Slack
Slack
Linear
Linear
Jira
Jira
Confluence
Confluence
Asana
Asana
Gmail
Gmail
Google Calendar
Google Calendar

Quick Reference

IntegrationLive SearchIndexed SearchAuthNotes
Amazon S3—YesAccess Key + SecretAPI: Full bucket, single file, or directory
Google Cloud Storage—YesService Account JSONAPI: Full bucket, single file, or directory
Azure Blob Storage—YesAccount Name + KeyAPI: Full container, single blob, or directory
Google Drive—YesOAuth (per-user)Studio: File picker UI
SharePoint—YesOAuth (per-user)Studio: File picker UI
OneDrive—YesMSAL (per-user)Studio: File picker UI
Dropbox—YesOAuth (per-user)Studio: File picker UI
Notion—YesOAuth (per-user)Studio: Page picker, markdown conversion
SnowflakeYes (SQL search)Yes (stage files)Credentials (org-wide)Live: Real-time SQL queries against your warehouse. Indexed: Index files from Snowflake stages for semantic search.
SlackYes—OAuth (per-user)Message search with channel/user/date filters
LinearYes—API Key (org-wide)Issue search, cycle tracking, status updates
JiraYes—API Token (org-wide)Issue search via JQL filters
ConfluenceYes—API Token (org-wide)Page search via CQL
AsanaYes—OAuth (per-user)Task search with project filtering
GmailYes—OAuth (per-user)Email search
Google CalendarYes—OAuth (per-user)Event listing with date range filters

Getting Data into Collections

Use the indexing endpoints to process files directly from cloud storage:

  • POST /v2/collections/{name}/index/s3 — Index from AWS S3
  • POST /v2/collections/{name}/index/gcs — Index from Google Cloud Storage
  • POST /v2/collections/{name}/index/azure — Index from Azure Blob Storage

Each endpoint supports full bucket/container indexing, single file indexing, and directory-scoped indexing. See the Quickstart for step-by-step examples.

Use the web UI at runcaptain.com/studio to connect cloud and SaaS sources:

  • Google Drive — Browse and select files or folders
  • SharePoint / OneDrive — Browse and select documents from sites and libraries
  • Dropbox — Browse and select files
  • Notion — Select pages and databases (automatically converted to markdown)
  • Snowflake — Index files from Snowflake stages

Files are automatically uploaded to cloud storage and indexed by Captain.

Connect credentials in the Studio for real-time search — no indexing required:

  • Snowflake — Account, username, password, warehouse, role
  • Linear — Personal API key (does not expire)
  • Jira / Confluence — API token + user email + Atlassian cloud ID
  • Slack — OAuth authorization per user
  • Asana — OAuth authorization per user
  • Gmail / Google Calendar — OAuth authorization per user

Environment Scoping

All collections and API keys are scoped to an environment:

  • Development (cap_dev_*) — For testing and development
  • Staging (cap_stage_*) — For pre-production testing
  • Production (cap_prod_*) — For production use

Collections created with a development key can only be accessed with development keys from the same organization. Use the Change Collection Environment endpoint to promote a collection from development to production without reindexing.