> ## Documentation Index > Fetch the complete documentation index at: https://docs.narrative.io/llms.txt > Use this file to discover all available pages before exploring further. # Concepts > Understand how Narrative I/O works—the architecture, primitives, and design decisions behind the platform The Concepts section explains the *why* behind Narrative I/O. Rather than step-by-step instructions, you'll find explanations of how the platform works, why it's designed the way it is, and how different pieces fit together. ## Core Primitives The fundamental building blocks of the platform. Where your data lives and is processed How Narrative orchestrates data collaboration How data plane, compute pool, database, and schema determine where operations run How compute resources are allocated for query execution Column-level metrics that describe your data ## Rosetta Stone Narrative's approach to schema normalization and data mapping. What Rosetta Stone is and why it matters The mechanics of automatic schema mapping How data gets normalized across sources How Rosetta Stone differs from the Open Semantic Interchange spec ## NQL The design and philosophy behind Narrative Query Language. Why NQL exists and how it differs from traditional approaches How NQL relates to SQL and when to use each How NQL handles data types and type safety Why certain JOIN patterns cause performance problems Pre-computed query results for performance and caching How NQL optimizes materialized view refreshes ## Identifiers How identifiers connect records across organizations and systems. How connected components unify identifiers into person-level profiles Strengthening graph structure with third-party linkage data Improving activation reach by appending additional identifiers ## Data Activation Delivering audience data from Narrative to external platforms. How connectors deliver audience data to advertising and marketing platforms What a dataset connects to, and how schema compatibility is decided Build, filter, and deliver audiences with a guided visual builder Expand reach by modeling audiences that resemble a seed ## Architecture How the platform is built and why. How queries are compiled, optimized, and executed How data moves through the platform How samples cross to the control plane How Narrative protects your data ## Workflows Automating multi-step data pipelines. How workflows automate sequential data operations and relate to the jobs system ## Webhooks Push-based notifications for job state changes. How webhooks deliver notifications when jobs change state ## MCP Server for Agents Connect AI agents to Narrative. How the Narrative MCP server lets AI agents interact with your data Pre-built, harness-agnostic workflows that orchestrate the MCP server ## Model Inference AI-powered operations within your data plane. How AI inference works within your infrastructure How inference keeps data secure in your data plane How JSON Schema ensures predictable responses ## Apps Third-party onboarding and account connection. How invite links enable third parties to connect accounts without Narrative authentication ## Security Enterprise security and access management. How SSO works with Narrative and why it matters for enterprise security How scoped permissions protect your resources and enforce least privilege ## Compliance Privacy regulations and data protection requirements. The EU's General Data Protection Regulation and its requirements California's privacy law and consumer rights framework