PACE Claim-Exception Resolver | Real Minds AI
NDIS & DisabilityDecisioning

PACE Claim-Exception Resolver

Reconciles delivered shifts against claims, plan dates, and PACE rules before submission, flags likely duplicates, out-of-plan and missing-evidence exceptions, and drafts the correction note — but never adjusts a claimed amount itself.

How it would work

One agent, grounded in your library, with citations on every paragraph.

01 · input
Member question
02 · agent
Your agent
03 · output
Cited answer or escalation
The problem it solves

Under PACE, manual transposition between the rostering tool and the portal produces avoidable C38 and M02 rejections, and a scheme payment error rate around 5% turns into hours of reactive rework and cash-flow drag. This pattern cross-checks delivered shifts against submitted claims, plan dates, budget, and the claim rules, then flags the likely defects — duplicate dates or times, services outside plan dates, missing agreement evidence, line-item mismatches — before anything is lodged. It produces an exception queue with a suggested correction and the rule cited for each flag, so staff work exceptions instead of hunting errors. It adjusts no quantity or amount; the claim stays with a person. Illustrative of a published Australian plan-manager case that lifted straight-through processing from 25% to over 70%.

TA
Tracy Anthony · Co-Founder & CEO · wrote up this design
What it would take to build

Estimated build: 3–4 weeks. Most of it is template work we've already done.

Estimated build time
3–4weeks
Diagnostic · build · soft launch · review.
Reused from template
~70%
Agent shell · retrieval · audit · deployment.
Bespoke to this skin
~30%
PACE rule + error-code encoding, rostering/billing connectors.
stack · Power Platform/n8n · rostering + billing API · review UI
What it would cost for your org

Fixed scope, fixed price, fixed dates.

The cost band reflects the engagement shape, not a per-feature line item. We work on fixed scope, fixed price, fixed dates — see the services catalogue for what falls inside each band.

Engagement band
A bite-sized first piece → pilot build → embedded support. Start small, scale on proof — most builds land in the pilot band.

Considering this for your org?

The honest place to start is a bite-sized first piece — one contained change, low risk. Tell us where it hurts; we’ll play it back, scope it, and show you what’s possible.

Book a call →How we work →
Ask us anything