Part 1 · Post 1
What problem are we designing for?
180 sites, 9,000 caregivers, up to a third of every shift on paperwork, and four rules that can't be broken.
Tomás has finished his last round. Before he can go home, he has to write up the night: who slept, who didn’t, who needed help to the bathroom at 2 a.m.
Down the corridor, Priya is reading through an incident note. Was it a fall or a slip? Does it need reporting? The decision is hers.
Two hours away, Grace’s phone buzzes: “How was Mum’s night?” Nobody has had time to answer yet.
None of these three people needs an AI to decide anything for them. What they need is time. That’s the problem this series is about.
The brief, in three numbers
The case study describes a regional aged-care operator. I’ve called it Zava Care Group.
Caregivers are scarce, and every hour spent on paperwork comes out of hands-on care. Night incidents, family enquiries and rejected insurance claims add to the load.
The brief asks for agentic AI that hands that time back to care. It also sets firm limits on what the agents may do.
Five agents, five jobs
The operator asked for five agents. Each one gets a fixed autonomy level, which says how far it can go before a person steps in:
- L2 (recommend): the agent proposes, and a person approves before anything happens.
- L3 (act with oversight): the agent carries out the task within set rules, and a person confirms the result, handles exceptions and responds to escalations.
| Agent | Its job | Level | Who decides |
|---|---|---|---|
| Care Record | Turns spoken or typed notes into structured draft entries | L3 | The caregiver confirms; the RN handles incidents and care-plan changes |
| Billing | Prepares claims from confirmed care and flags exceptions | L3 | A billing administrator reviews exceptions; a person certifies |
| Shift Planning | Recommends rosters that respect skill mix, award rules and care-minute targets | L2 | The facility manager |
| Night Watch | Raises falls and wandering alerts from facility sensors | L3 | Night staff and the RN on duty |
| Family Communication | Answers family enquiries within a disclosure policy | L3 | Staff, for anything sensitive |
Notice that nothing goes above L3. The brief says “no automated care decisions”, and that caps every agent. Agents can draft, prepare, recommend and alert. Clinical judgement stays with qualified staff.
Shift Planning sits one step lower than the rest. A wrong roster affects staffing standards and labour rules and is hard to undo, so a manager signs it off before it takes effect.
Targets, not results
The brief comes with ambitious numbers. Here they are, labelled honestly:
| The brief’s target | Status |
|---|---|
| Documentation time cut by 60% | Target Not measured |
| About 1.3 million care-hours a year handed back | Target Derived from the 60% |
| Roughly 700 caregivers’ worth of time | Target Depends on an assumed hours-per-caregiver figure |
| USD 40 million in additional serviced revenue at current occupancy caps | Target Not an Australian forecast |
| Billing rejections cut by 70% | Target Not measured |
| 15% more residents served with the same staff | Target Needs restating for Australia |
The Australian twist
The brief describes an Asian operator, but I’ve framed the design around Australian regulation. A real regulatory setting turns vague requirements into concrete ones. It also changes how some of the targets read.
The growth targets need an Australian translation. The latest StewartBrown survey coverage reported residential occupancy near capacity (Inside Ageing, 21 July 2026). So “15% more residents” doesn’t translate directly. Capacity and agency hours avoided, or growth in home care, are better measures. The brief’s USD 40 million revenue target also needs a local value model; it isn’t an Australian forecast.
Care minutes are measured on paid hours. Each resident’s funding class comes with daily care-minute targets, set in the Aged Care Rules 2025 (compilation in force from 1 October 2026). These are counted against paid worked hours, so saving documentation time doesn’t raise a facility’s reported care minutes. What it does is put more of those paid minutes into direct care, which matters more.
Billing value is mostly about accuracy. For residential care, the money is in getting each resident’s funding classification right and on time (Department of Health, 24 July 2026). Fewer rejections matter more for home care and private fees.
Regulation shapes the design. For example, privacy-policy transparency rules for automated decision-making commence on 10 December 2026 (OAIC, 30 September 2026). Any agent that does something “substantially and directly related” to a significant decision needs to be disclosed.
The rules that can’t be broken
These are the non-negotiables. Every later post comes back to them.
- No automated care decisions. Agents draft, recommend or alert. People confirm, approve, certify or respond.
- Resident health records stay in Australia. Identifiable data never leaves the country.
- Only de-identified quality metrics go regional. A group-wide view of quality, without names.
- Night Watch alerting runs on-site and keeps working offline. A falls alert can’t depend on an internet connection.
The brief also requires these controls, which the design treats as equally firm:
- Consent before sensitive data is processed, with a non-AI fallback.
- Alert-accuracy thresholds that Night Watch must meet before it goes live.
- A family disclosure policy that is enforced in code, outside the language model.
- A billing audit trail, with a person certifying each claim.
What’s in scope, and what isn’t
| In scope | Out of scope |
|---|---|
| Five agents with human checkpoints at the levels above | Any automated clinical decision |
| A shared Azure platform in Australia East | Replacing the operator’s clinical, payroll, claims or nurse-call systems |
| A standard health-data (FHIR) layer over the clinical system, with synthetic data | Real resident, staff or family data |
| A design for on-site Night Watch that works offline | A production rollout |
| A simulated “Zava Care Group” to test against | Treating the simulation as part of the solution |
Still open
I’ll be honest about what’s not settled yet:
- The value model. The business case for an Australian operator isn’t written yet, so there are no baselines.
- How to restate “more residents served” for a market that’s already nearly full.
- The final success measures for a pilot. The candidates are documentation minutes per resident-day, billing exception rate, night alert-to-acknowledgement time, staff turnover and occupancy. None has a baseline yet.
Next: the whole system on one page, and the principle that holds it together: the model drafts, rules decide, people confirm.