Glean Connector for AI agents.

Yes, it connects directly to your current Glean instance using your API token. This means your agent gets access to the exact same data and permissions you already have.

Yes, the Connector allows your agent to pull data from multiple SaaS apps simultaneously. You can ask a single question and get results from across your entire workspace.

You can use the indexing capabilities to route new text directly into your corporate search logic. This ensures your AI agent is always working with the most recent information.

Yes, it can fire RAG mechanisms to return summarized AI blocks based on your data. It will read the documents for you and provide a direct answer in the chat.

The Connector uses your existing Glean permissions, so the AI only sees what you are already allowed to access. It follows your company's established security boundaries.

You can use the deletion capabilities to permanently remove an indexed file. This is helpful for removing outdated documents that might confuse your AI's answers.

Yes. Use the 'get_answer' capability. It fires Glean's internal RAG mechanisms to retrieve a pure AI-generated response distilled from your indexed company knowledge flawlessly.

Use the 'search_people' capability. The agent will retrieve information from your corporate active directory, matching user profiles, skills, and names to help you find the right colleague natively.

Absolutely. Use the 'index_document' capability. Provide a JSON object defining the ID, Title, and text content. The agent will route the payload into Glean's search logic synchronously.

Yes! The search capability queries all connected data sources in a single request. If you want to narrow results to a specific platform, use search_by_datasource with the datasource name (e.g., 'Confluence', 'Slack', 'Google Drive'). Use autocomplete to get intelligent suggestions as you refine your query.

Yes. The chat capability sends a natural language question to Glean's AI assistant, which generates an answer grounded in your organization's indexed knowledge. including documents, wikis, Slack conversations, and Jira tickets. This is ideal for getting synthesized answers rather than just search results.

Yes. Use index_document to add a single document with a JSON payload containing title, body, URL, and metadata. For large batches, use bulk_index_documents to index multiple documents in one request. Use delete_document to remove outdated content and get_document to verify indexing status.