NDIS plan managers (Australia)

What is in the early-access pack

The NDIS pack is available to early-access customers. Document types cover provider invoices, quotes and credit notes, participant plans or statements of supports, service agreements, support worker timesheets, progress and shift notes, incident reports and restrictive practice records, and therapy and support coordination reports.

Starter schemas extract fields such as invoice number and dates, provider and provider ABN, participant, the last four digits of the participant number (the extraction instructions ask for only those digits; Droqify does not currently mask these numbers), service start and end dates, support type and category, line items, subtotal, GST and total, plan start and end dates, plan management type, budgets by support category as printed, and cancellation terms in a service agreement. Cross-document indexes cover invoice number, participant, participant number digits, provider, support type, plan management type, invoice kind, note kind and incident reference. Smart folders include invoices to check, quotes, plan-managed plans, core supports, incident reports and progress notes. Sample questions ask for invoice lines as printed, which invoices show no ABN, and which invoices have service dates outside the plan dates, for a person to review.

What is still being confirmed

Early-access packs are built from public form and agency guidance; some details are still being checked and may change. They have not been validated on production customer documents, and forms and fields will be confirmed with early-access customers. Reviewers compare documents using the extracted data and search; the pack does not check a file for completeness or compare documents automatically. Where your forms are not covered, your team can define additional schemas.

Where people stay in the loop

Each extracted field has a model-reported confidence score (not calibrated). When you turn on Human in the Loop for an upload, processing pauses at the steps you choose so a person can check the source document and correct the data before it continues. Documents that match no schema are flagged. The pack prepares document data for your team; it does not approve or pay invoices, or check them against a price guide. Key actions are written to an audit log.

Document text is processed by the AI service and stored in the search index, including progress notes and incident reports. The pack sets the default pipeline to one without the automatic summary step; a person can still choose another pipeline or generate a summary, and document text always goes to the AI service and the search index. We suggest starting with provider invoices: progress notes and incident reports carry sensitive information about participants, and we recommend that a person reviews every incident report; the pack does not route them automatically.

Join the waitlist

Australia is in early access: not yet validated on Australian documents with customers. If you want to try the pack on your own documents, join the waitlist and tell us about your document mix and volumes. We will follow up directly.