Enterprise Generative Search — Azure and Open Source  ·  View 08 of 41  ·  People and journeys

Journey — Why Is My Document Not Found

The journey that decides whether content owners trust the platform or blame it.

Editable source SVG draw.io All views
Knowledge Steward owns a domain, not the platform Goal — Make my domain answerable, and know when it is not Trigger — A colleague says the platform never finds our standard Done when — The document is retrievable, and the steward knows why it was not 1 · Publish 2 · Assume it works 3 · Hear a complaint ◆ moment of truth 4 · Diagnose ◆ moment of truth 5 · Fix 6 · Verify What they do Publishes to SharePoint Moves on Tries the query themselves Opens the document report Fixes title and metadata Supersedes the old version Re-runs the probe query Where SharePoint library Nowhere The search box Steward console Source system Coverage report Behind the glass Graph delta notices it Parse, chunk, embed, index Retrieval returns rivals Per-document diagnostics Retrieval explain probe Incremental re-index Coverage metric recomputed How it feels Trusted Neutral Powerless Where it hurts No signal it was indexed Blamed for a platform fault Scanned PDF, no text layer Nothing tells them that What answers it Indexed receipt per document Self-service probe query Parse, chunk, ACL and OCR state Named cause, not a ticket OCR path re-queued on demand Domain coverage trend Journey — Finding Out Why a Document Never Surfaces A steward with no diagnostics blames the platform, and the platform blames the content. The diagnostics in view 34 exist to end that argument. v 1.0 · owner Data and AI Global Practice

The trough, and what it demands

  • The low point is Diagnose: the document is a scanned PDF with no text layer, and nothing in the platform tells the steward that. They experience an unaccountable black box and stop maintaining their domain.
  • The answer is the per-document receipt in view 16 and the steward console: parse state, chunk count, ACL as indexed, embedding version, last indexed time, and a retrieval probe they can run themselves.
  • This is why every ingestion stage writes a receipt even when nothing changed — an absent document and an unchanged one must never look the same.

Why this journey is in the set

  • Corpus quality is the largest lever on answer quality, and it is owned by people who do not work on the platform. A steward with no diagnostics is an unmaintained domain within two quarters.
  • Coverage per domain is reported to stewards as a trend, which turns an invisible platform property into something a content owner can act on.

Assumptions

  • 85 stewards across 22 domains, each owning between 400 and 90,000 documents.
  • Stewards will act on a named cause and will not raise a ticket to find one. The console is therefore self-service or it is unused.
◀  Journey — Multi-Hop Under Review All views Layered Architecture  ▶
Solution Architecture v1.0 · Data & AI Global Practice · 2026-09 · 41 views · Microsoft Azure and open source08-journey-knowledge-steward