Knowledge Tree
Atlan
Facts (19)
Sources
Knowledge Graphs vs RAG: When to Use Each for AI in 2026 - Atlan atlan.com Feb 12, 2026 10 facts
claimAtlan’s context graph infrastructure supports both knowledge graph and RAG capabilities through unified metadata management.
referenceAtlan's context graph platform features active metadata captured from usage patterns, temporal awareness for time-travel queries, governance nodes that treat policies as queryable elements, and lineage integration for traceability from business concepts to technical implementations.
accountWorkday uses Atlan's unified context layer to build AI-ready semantic layers, allowing AI to leverage the shared language established by employees.
accountMastercard's Chief Data Officer describes Atlan as a "context operating system" that allows AI agents to access lineage context through the Model Context Protocol.
claimAtlan uses active metadata to automatically map relationships across data assets, connecting business concepts to technical implementations.
claimAtlan defines context graphs as knowledge graphs enhanced with operational metadata, governance rules, and decision traces.
referenceAtlan's platform provides GraphRAG systems for multi-hop reasoning, automated knowledge graph construction using LLMs to extract entities and relationships, Model Context Protocol (MCP) servers for programmatic AI agent access, and real-time metadata freshness.
measurementOrganizations using Atlan's approach report 5x improvements in AI analyst response accuracy when systems have access to rich metadata including definitions, relationships, and operational context compared to raw database schemas.
claimAtlan's unified context layer combines semantic definitions with active metadata to eliminate silos between glossaries, lineage, quality metrics, and governance, supporting both human search and AI-ready retrieval.
quoteThe VP of Enterprise Data & Analytics at Workday stated: “All of the work that we did to get to a shared language amongst people at Workday can be leveraged by AI via Atlan’s MCP server.”
Combining Knowledge Graphs With LLMs | Complete Guide - Atlan atlan.com Jan 28, 2026 5 facts
claimAtlan’s knowledge graph architecture automatically maps relationships across data assets, connecting business concepts to technical implementations.
quoteJoe DosSantos, VP of Enterprise Data and Analytics at Workday, stated: "Atlan enabled us to easily activate metadata for everything from discovery in the marketplace to AI governance to data quality to an MCP server delivering context to AI models. All of the work that we did to get to a shared language amongst people at Workday can be leveraged by AI via Atlan's MCP server."
claimAtlan uses active metadata approaches where LLMs enrich knowledge graphs with usage patterns, quality signals, and ownership information captured from system activity.
measurementWorkday achieved a 5x improvement in AI analyst response accuracy by using Atlan's platform.
quoteAndrew Reiskind, Chief Data Officer at Mastercard, stated: "Atlan is much more than a catalog of catalogs. It's more of a context operating system. The metadata lakehouse is configurable across all our tool sets and flexible enough to get us to a future state where AI agents can access lineage context through the Model Context Protocol."
Context Graph vs Knowledge Graph: Key Differences for AI - Atlan atlan.com Jan 27, 2026 4 facts
measurementAtlan's internal testing found that structured context improved accuracy by up to 5x compared to schema-only setups.
referenceExample platforms for knowledge graphs include Neo4j, Stardog, GraphDB, and Amazon Neptune, while example platforms for context graphs include Atlan (context layer), Glean (enterprise context), and context-aware data catalogs.
quoteMichael Weiss, Product Manager at Nasdaq, stated: "The implementation of Atlan has also led to a common understanding of data across Nasdaq... This is like having Google for our data."
claimNasdaq implemented Atlan to create a common understanding of data across the organization, which Michael Weiss, Product Manager at Nasdaq, described as being like "having Google for our data."