Knowledge Graph and Vector Database Integration

7/16/2026

This post details the integration of Databricks as a native data source within Glean Assistant, enabling users to query Databricks data using natural language or read-only SQL. Glean translates natural language queries into SQL via Databricks Genie and combines these insights with broader enterprise context from documents, tickets, and other sources. The system also supports building polished artifacts like charts and slides from the analyzed data. Further integrations include indexing Databricks AI/BI dashboards and Genie Spaces, direct SQL querying within Glean Assistant and Agents, and bringing Glean's enterprise context into Databricks workflows via the MCP.

7/7/2026

This post elaborates on the enterprise AI stack, positioning Glean as the foundational context and agent layer. It details how Glean's continuous indexing and AI-powered knowledge graph provide permission-aware, grounded context for AI models, contrasting this with less robust retrieval methods. It also discusses the integration of reasoning models and specialized AI agents, emphasizing the importance of a layered architecture for enterprise AI.

6/2/2026

This post introduces and elaborates on the 'two-layer model' for generative AI in software engineering, emphasizing the critical role of a 'context layer' beneath coding surfaces. It details how this context layer, powered by Glean's knowledge graph and enterprise graph capabilities, connects disparate engineering systems (code repositories, Jira, Slack, observability tools, design docs, wikis) to provide AI tools with comprehensive, permission-aware context. This enables AI to move beyond code completion to assist with finding context, navigating incidents, and shipping safely. The post explains how this architecture addresses the 'AI productivity paradox' by solving the bottleneck of context assembly, which slows down developers and impacts onboarding, daily coding, and incident response. It highlights Glean's role in indexing code and documents with hybrid search, building an enterprise graph linking services, APIs, incidents, tickets, and owners, and respecting security and governance boundaries.

6/2/2026

This post introduces the Glean MCP Gateway, which enhances the Model Context Protocol (MCP) by providing a dedicated context layer for AI. It addresses the limitations of off-the-shelf MCP tools by leveraging Glean's precomputed index and knowledge graph for more efficient and accurate context delivery. The Gateway offers secure access to data and tools with granular access controls, prompt injection protection, and centralized administration. It also enables centralized rollout via MDM and provides detailed usage insights through a centralized dashboard.

6/1/2026

This post announces the general availability of Snowflake data as a native data source within Glean Assistant. It details how Glean Assistant leverages Snowflake Cortex Analyst and Cortex Agent for text-to-SQL translation, combining structured Snowflake data with unstructured enterprise context. It also highlights the integration's adherence to enterprise-grade trust, respecting existing permissions and governance, and outlines different user experiences for business users, data users, and builders.

3/19/2026

This post defines knowledge graphs and vector databases, comparing their strengths and weaknesses for AI applications. It explains how knowledge graphs excel at structure, relationships, explainability, and governance, while vector databases are strong in semantic search across unstructured content and fast prototyping. The post advocates for a hybrid approach, suggesting that combining both provides a more comprehensive foundation for enterprise AI by leveraging the explicit structure of graphs with the semantic understanding of vectors. It outlines specific workflow scenarios where each approach is beneficial and how they can work together.

1/6/2026

This post elaborates on Glean's context graph capabilities, framing it as the next data platform for agentic automation. It details the technical challenges and solutions in capturing 'how' work gets done by focusing on observability through connectors, understanding low-level activity data (discrete, timestamped actions), and deriving higher-level constructs (tasks, projects) from these signals. It emphasizes the algorithmic inference required due to privacy constraints and the integration of context graphs with indexes, connectors, and enterprise memory to form a complete agentic automation backbone.

12/21/2025

This post details the integration of Glean's enterprise context into v0 by Vercel through the Model Context Protocol (MCP). It highlights how Glean's remote MCP server allows v0 to query Glean's unified company knowledge, which is organized into an Enterprise Graph. The integration ensures that AI-generated apps are grounded in live company data, respecting existing permissions and governance. Specific use cases include generating auth logic flows from documentation, updating website copy based on product updates, and prototyping UIs from Product Requirements Documents (PRDs). The post also outlines the process for joint customers to enable this integration.