Data Connectors

Connect your knowledge sources to power your AI agents with up-to-date, relevant information from across your organization.

Overview

Data integrations allow you to sync content from various sources into your knowledge base. Your AI agents use this data to provide accurate, contextual responses grounded in your organization's information.

Why Data Integrations Matter

• Single Source of Truth: Centralize knowledge from multiple platforms
• Always Up-to-Date: Automatic syncing keeps your knowledge base current
• Secure Access: Maintain security boundaries and permissions
• Rich Context: Provide agents with comprehensive information for better responses

Available Integrations

File-Based Sources

• File Upload: Upload PDFs, documents, and other files directly
• CSV Data Import: Import structured data from spreadsheets
• QnA CSV: Bulk upload question-answer pairs

Web Content

• Website Crawling: Automatically crawl and index website content
• Sitemap Integration: Use sitemaps for efficient website indexing

Cloud Storage

• Google Drive: Sync documents, spreadsheets, and presentations
• Microsoft OneDrive: Connect personal and business OneDrive accounts
• Microsoft SharePoint: Access team sites and document libraries

Collaboration & Support Tools

• Confluence: Sync wiki pages and spaces
• Slack: Index conversations and shared knowledge
• Zendesk: Import support articles and tickets

Getting Started

1. Choose Your Sources: Identify which platforms contain your critical knowledge
2. Set Up Connections: Follow the integration-specific guides to authenticate and configure
3. Configure Sync Settings: Set sync frequency, filters, and permissions
4. Test & Validate: Verify data is flowing correctly and agents can access it
5. Monitor & Maintain: Keep integrations healthy with regular monitoring

Integration Features

Automatic Syncing

Most integrations support automatic incremental sync to keep your knowledge base updated without manual intervention.

Selective Import

Configure filters to sync only relevant content, reducing noise and improving agent accuracy.

Permission Mapping

Maintain source system permissions to ensure users only access data they're authorized to see.

Metadata Preservation

Important metadata like authors, dates, and tags are preserved for better context and filtering.

Best Practices

• Start Small: Begin with one or two critical sources before expanding
• Set Appropriate Sync Intervals: Balance freshness with API rate limits
• Use Filters Wisely: Exclude archived, draft, or irrelevant content
• Monitor Data Quality: Regularly review what's being synced
• Document Your Setup: Keep notes on filters, permissions, and configurations

Common Use Cases

Customer Support Teams

Sync Zendesk articles, Confluence docs, and Slack channels to provide agents with comprehensive support knowledge.

Engineering Teams

Connect GitHub wikis, Confluence spaces, and Google Drive folders containing technical documentation.

Sales & Marketing

Integrate product docs, marketing materials from Drive/SharePoint, and competitive intelligence.

HR & Operations

Sync policy documents, training materials, and internal wikis for employee self-service.

Troubleshooting

Having issues? Check our Data Integration Solutions section for common problems and fixes.

Need Help?

• Review the Overview Guide for general data source concepts
• Check integration-specific documentation for detailed setup instructions
• Contact support if you encounter authentication or sync issues

Next Steps

Choose an integration from the list above to get started, or read the Overview for more context on how data integrations work.

---

Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the ask query parameter:

GET /dev/product/data-integrations.md?ask=<question>

The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.