Aged Care /Decisioning live field guide · 9 min

SIRS Incident Triage Assistant

Reads each incident note against the eight reportable-incident categories, surfaces the likely category, priority and notification deadline, and drafts the notice for a clinician to approve — so a night-shift under-call doesn't quietly blow the 24-hour window.

Open the live demo

theater/demos/aged-care_sirs-incident-triage-assistant.html · sandbox · read-only

Open

FIG. 1

The live demo, running on fabricated data. Open it to step through the full flow — every output is shown for a person to approve before anything happens.

How it would work

Reads each incident report against the eight SIRS reportable-incident categories, surfaces the likely category, priority and hours-left-to-notify, and drafts the Commission notice for your Quality Manager to approve before anything is lodged.

Input 01

The incident report

One report per resident incident — a handwritten night-shift scan or a digital form: resident and room, time, what happened, injury, action taken, and any medication given with dose and time.

Agent 02

Tests against SIRS criteria

Extracts the facts, tests them row-by-row against the eight reportable-incident categories and the restrictive-practice and injury thresholds, and drafts the notice to the Aged Care Quality and Safety Commission.

Output 03

A draft, with its working shown

A reportability call — category, priority, hours-left-to-notify and a drafted Commission notice — held for your Quality Manager to approve, edit, or send back to the RN before anything is lodged.

Where it works well

It reads every incident note the moment it lands, so the reportable ones rise to the top instead of waiting their turn.

Best for the clinical governance lead or Quality Manager accountable for the 24-hour and 30-day SIRS windows who can't personally read every note as it's written.
Earns its keep where incident volume banks up overnight and over weekends, and reporting depends on whichever RN next reaches the pile.
The recaptured hours go back into the reportability judgement and the resident, not into hunting through a queue of free-text.

The slow, invisible problem is the under-call: a 2am note logged as "both settled, review with RN in the morning" that is in fact an unreasonable use of force with an unauthorised chemical restraint — a Priority 1 with a 24-hour clock already running while the report sits in a queue.

Where it works badly

It is only as good as what made it into the report — and it is confidently wrong at the edges of legibility.

Wrong at the edges of handwriting — a smudged drug name, an unusual local shorthand, a dose written ambiguously. It flags an unreadable field as missing, not invented.
It cannot adjudicate the genuinely borderline call — whether a bruise crossed the "injury requiring treatment" line, whether a raised voice was psychological abuse. Those are clinical judgements; it hands them up with the evidence, never resolves them.

The honest test

If your incident reports already capture what happened clearly and consistently — mechanism, injury, treatment, medication — this saves you real time. If they don't, fix the reports first; the triage layer is premature.

If the night note says "resident had a fall" and omits that another resident pushed them, it triages a fall, not a use-of-force incident, because the use-of-force fact was never written down. It surfaces under-documentation; it can't recover a fact nobody recorded.

What it doesn't do — and shouldn't

It drafts. Your Quality Manager decides and lodges. That boundary is deliberate.

WHAT IT DOES

Surfaces the category, the SIRS criteria it triggered, and the report wording that triggered them

Shows the priority and the hours left against the 24-hour or 30-day window

Drafts the Commission notice and flags a consent or authorisation gap for a human to confirm

WHAT IT WON’T

Lodge anything with the Aged Care Quality and Safety Commission

Decide reportability or settle a borderline clinical call

Treat a flagged consent gap as resolved on its own say-so

Under the Serious Incident Response Scheme the provider is accountable for the notification, and that accountability cannot sit with a model. A drafted notice that goes out unread is worse than no tool at all — it launders an unchecked judgement into an official notification to the Commission. The decision to lodge stays a human act, on the record, with a name against it.

What your data has to look like

The incident free-text has to describe what actually happened — mechanism, injury, treatment, medication — and the plan and consent records have to be readable at triage time.

Typical readiness

across orgs we see, before the first job

Incident free-text that names the mechanism

Needs shaping

Medication administered, with drug, dose and time

Usual weak point

Current behaviour support plan, readable at triage

Needs shaping

Restrictive-practice authorisation linked to the resident

Needs shaping

Provider and facility identifiers for the notice

Usually ready

The real first job

Getting incident notes to reliably distinguish a mechanism from an outcome, and getting plan and consent records into a form the triage step can actually read, is usually the bigger and more valuable piece of work — and it's mostly about how information is captured at the point of care, not about buying a tool. That's the part we help with first.

Right fit if…

You are accountable for the 24-hour and 30-day SIRS windows but can't read every note as it's written

Incident volume banks up overnight and over weekends across multiple wings

Your incident notes already name the mechanism, the injury and any medication given

Behaviour support plans and restrictive-practice authorisations are linked to the resident and readable

Walk away if…

Staff aren't reliably writing down what actually happened — fix the documentation first

Most of your reportable calls are genuinely borderline judgements, not under-calls

Plan and consent records live in paper folders the triage step can't read

You want a tool that decides reportability and lodges the notice for you

Open questions

The worried-buyer questions, answered straight

It never lodges anything. Every assessment lands in front of your Quality Manager with the SIRS category, the criteria it triggered, and the wording from the report that triggered them, so you can see why it made the call before you approve, edit, or send it back to the RN. A wrong flag costs a few minutes of review; a missed Priority 1 costs you a breach of your 24-hour obligation to the Aged Care Quality and Safety Commission, which is the failure mode it’s built to catch.

Handwritten scans are the main thing it’s built for — the demo runs on a handwritten night-shift note. It will still misread a smudged word or an unusual abbreviation, which is why the extracted facts are shown back against the original report for the reviewer to check. If a report is so illegible that key facts can’t be read, it surfaces an unreadable field as missing, not invented.

No. The reportability decision under the Serious Incident Response Scheme stays with your Quality Manager — the provider is the accountable party, not a model. The tool does the reading and the first-pass triage so that decision is made on a complete, deadline-aware draft instead of a 2am note logged as routine. The time it recaptures redirects to the judgement call that has to stay human.

It is only as current as the records it can read at the moment of triage. If it checks a resident’s behaviour support plan or restrictive-practice authorisation, it reads whatever your clinical system holds then; a consent form signed an hour ago but not yet in the system won’t be seen. That’s why a flagged consent gap is raised for the reviewer to confirm against the live record, not treated as settled.

That’s a deployment decision made with you, not a default. Incident reports contain identifiable resident health information, so the build is scoped around where that data is allowed to sit — what stays in your environment, what (if anything) calls an external model, and what’s logged. The demo runs on fabricated data; R. Perkins of Northern Gardens is not a real resident.

A logging system records that an incident happened; it doesn’t read the free-text and tell you the note that says “both settled, review in the morning” is actually a Priority 1 use of force with an unauthorised chemical restraint. That gap — between what was written and what’s reportable — is where under-reporting lives, and it’s the gap this closes before the 24-hour clock runs out.

What it takes to build

3–4 weeks · 4 phases

Reused from template~65%

Bespoke to this skin~35%

stack · Claude · criteria engine · review UI

What it would cost

Fixed scope, fixed price, fixed dates.

Bite-sized first piece

One contained change, low risk

Pilot build

Most builds land here

Embedded support

Scale on proof

Considering this for your facility?

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

Book a call How we work