NDIS & Disability /Document Generation live field guide · 7 min

NDIS Service Agreement Generator

Draft a participant service agreement from the plan and the current price limits in minutes — every rate, support item and cancellation term in place before a coordinator signs off.

Open the live demo

theater/demos/ndis_service-agreement.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 the plan and the current NDIS price limits, drafts the full agreement, and surfaces every rate and term for a person to approve before it reaches the participant.

Input 01

The plan + the price file

Participant plan summary — goals, funded support categories and budgets — provider details, and the current NDIS Pricing Arrangements and Price Limits.

Agent 02

Maps, prices, drafts

Maps each funded support to a support item, applies current price limits, and drafts the six agreement sections — overview, services schedule, price-limit checks, cancellation, participant rights, signature block.

Output 03

A draft, with its working shown

A complete draft with every rate, item and term laid out for a coordinator or plan manager to review, correct and approve before it goes to the participant for signature.

Where it works well

It does the rate-by-rate cross-check every time, in full, and shows its working.

Done by hand it is an hour or two per agreement — and the rate check is the first thing skipped under time pressure.
Best for a coordinator or plan manager drafting regularly: plan start, plan review, new-participant onboarding.
At ten or twenty agreements a month, the recaptured hours go back into the participant conversation, not the paperwork.

The slow, invisible cost of a service agreement is the cross-checking — tracing every line from a funded support category, to a support item, to a price limit in a document that gets reissued mid-year.

Where it works badly

It is confidently wrong when the inputs are stale — and the output looks more trustworthy than the data behind it.

Weak where a support doesn't map cleanly to one item — bespoke or quotable supports that need a judgement call. It should flag, not guess.
If most of your agreements are non-standard one-offs, the template gives you less than your own manual judgement already does.

The honest test

If you cannot say, right now, which version of the price limits and which plan period this is drafted against — this tool makes your wrong answer faster, not safer.

Point it at last year's Pricing Arrangements, or a plan that has since been reviewed, and it drafts a clean, professional agreement full of rates that no longer hold. That is the trap.

What it doesn't do — and shouldn't

It drafts. A person approves. That boundary is deliberate.

WHAT IT DOES

Surfaces the rate it used and the support item it matched

Shows the price limit it checked against

Flags every support it could not match cleanly

WHAT IT WON’T

Send the agreement to the participant

Certify it as NDIS-compliant

Decide whether the service mix is right

A service agreement carries obligations under the NDIS Practice Standards and the participant's plan. A wrong rate or term has consequences for the participant's budget and the provider's standing with the NDIS Quality and Safeguards Commission. The accountable person stays on the decision because the consequence lands on them — not the tool.

What your data has to look like

Funded supports as structured fields, and the price limits that are in force today.

Typical readiness

across orgs we see, before the first job

Funded supports as structured fields

Needs shaping

Current NDIS price limits, machine-readable

Usual weak point

The support item catalogue to map against

Usually ready

Provider registration & ABN details

Usually ready

A clear plan period and review date

Needs shaping

The real first job

The price limits are usually the weak point — held as last year's PDF, or a spreadsheet updated by hand and forgotten. Fixing how plan and price data is captured and kept current is usually the real first job — larger and more valuable than the drafting layer on top. Once the inputs are clean, every agreement after that is faster and right by default.

Right fit if…

You draft service agreements regularly — plan start, review, onboarding

Ten or twenty-plus agreements a month, mostly recurring service schedules

You can point to the current, in-force price file today

Your plan summaries expose funded supports as structured fields

Walk away if…

Most agreements are non-standard, bespoke one-offs

Your price limits live as last year's PDF nobody owns

Plan data only exists inside PDFs a coordinator retypes

You need a tool that signs off compliance for you

Open questions

The worried-buyer questions, answered straight

It can draft a wrong rate — which is exactly why nothing is sent on its say-so. It maps each funded support to a support item, applies the current price limits, and shows its working: the rate used, the limit checked, and a flag where it could not match cleanly. A coordinator checks those before approving. The tool surfaces the numbers; the person stands behind them.

It works from structured fields — funded support categories, budgets, the item catalogue, the published price limits. If plan data lives in a PDF a coordinator retypes, the draft is only as good as that retyping, and the tool can’t tell a typo from a real figure. Getting that data into clean, current, structured form is usually the first piece of work — and the piece that pays off across every agreement after.

No. It removes the typing and the cross-checking — the two hours of clerical work — so the coordinator spends their time on the judgement: whether the service mix serves the participant’s goals, whether the frequency is right, whether the participant understands what they’re signing. The agreement is still theirs. The capacity it frees goes back into participant-facing work.

Current to the active arrangements. NDIS price limits are reissued — the 2025-26 arrangements have already been updated mid-year — and a plan can be reviewed at any time. Point it at last year’s file and it drafts confidently wrong rates. The honest test: do you know, today, which version of the price limits and which plan period this is drafted against?

A participant’s NDIS number, plan and funded supports are sensitive personal information under the Privacy Act and the NDIS Code of Conduct. Any deployment runs against your own systems and data handling, not a shared pool — we scope where the data sits and who can see it as part of the build. The demo here runs entirely on fabricated data; Emma Nguyen is not a real participant.

It drafts to the rules it’s given and flags where a rate sits outside a price limit, but it does not certify compliance. Incident-management obligations, complaints pathways and participant-rights wording come from the NDIS Practice Standards and your registered-provider obligations — a person confirms those are current for this participant. The tool gets the draft 90% of the way; the accountable person closes the last 10%.

What it takes to build

3–4 weeks · 4 phases

Reused from template~70%

Bespoke to this skin~30%

stack · Claude · template 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 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