Annex has published an example of turning disconnected documents into searchable website content. In that work, an AI-based digitisation pipeline enriched documents with metadata, which helped make them easier to find through search and the site’s information architecture. The pipeline was built in Azure and integrated with Drupal. A person checked the results before content was uploaded and published, so the example included human review as well as automation. Whether a similar approach suits another collection depends on its documents, systems and publishing needs.
Public Q&A
How could you make a large document collection easier for people to search and use?
Useful next steps
Use this answer as a practical starting point. Current scope, specifications, compatibility, availability, pricing, timing and next steps should be confirmed directly with Annex where they affect a decision.
Related visual examples
Information Architecture & Content DesignAn information architecture workshop with content cards being sorted into clear groups while a digit…
Visual exampleWebsite homepage for Australian Government veterans employment program
Content Audit & InventoryA content design team reviewing a content audit with page groupings, duplicated material and migrati…
IA Card Sorting SessionA collaborative card sorting activity with stakeholders grouping content topics into a clearer infor…
