Enterprise Generative Search — Azure and Open Source  ·  View 01 of 41  ·  Context and scope

System Context

Who asks, what the platform reads, and what it deliberately never writes to.

Editable source SVG draw.io All views
Unstructured content sources Confluence and Jira engineering knowledge Microsoft 365 SharePoint, Teams, OneDrive ServiceNow Knowledge support articles Document Archive 12 TB scanned PDF People it serves Knowledge Worker 9,000 daily active Research Analyst 400 seats Field Engineer 1,200 mobile Knowledge Steward 85 content owners Structured, external and downstream Databricks Lakehouse governed Delta tables Downstream Applications CRM and intranet assistants Regulator and Standards Feeds public web Generative Search Platform grounded answers over 40 M documents Platform services it depends on Microsoft Entra ID identity and groups Azure AI Foundry Azure OpenAI models Azure AI Content Safety Prompt Shields Azure Monitor and Langfuse traces and telemetry asks multi-hop photo, voice curates REST delta KB API nightly SQL API crawl OIDC, OBO inference screening OTLP Enterprise Generative Search — System Context External / third party Person or role Security / platform synchronous batch event / async Read-only against every source. The platform indexes and cites content; it never edits or republishes it. v 1.0 · owner Data and AI Global Practice · date 2026-09

Decisions

  • Read-only against every source. The platform indexes and cites; corrections are routed back to the owning system as a task, never written by the search stack.
  • Databricks governed tables are queried live and never indexed. A figure that can be computed correctly on demand should not be embedded and allowed to go stale.
  • Downstream applications consume the same Answer API a person uses, carrying the caller's identity. There is no second, more permissive path for machines.

Assumptions

  • Microsoft Entra ID is the single identity provider; every source system's permissions can be expressed as Entra object ids.
  • 62,000 queries a day, peak 34 per second, 9,000 daily active users across 45,000 employees; 40 M documents and about 320 M chunks.
  • SAP and other systems of record reach the platform through governed Databricks tables rather than by direct connection, which is why they are not on this page.

Out of scope

  • Authoring, workflow and records management — the platform reads what those systems publish.
  • Customer-facing external search; every consumer here is inside the tenant.
  • Replacing the source systems' own search. This platform answers across them; it does not remove them.
All views High-Level Architecture  ▶
Solution Architecture v1.0 · Data & AI Global Practice · 2026-09 · 41 views · Microsoft Azure and open source01-system-context