Part of Learnbuilt · Australian VET · built against ASQA 2025 Outcome Standards

Ruling.

The compliance operator for VET assessment. It rules on two axes — is the evidence the student's own, and does the task assess the work the way it's actually done now — then commits the change end-to-end: the assessment, the Word doc, and the LMS page.

Warrant researches the unit. Ruling rules on the task — and acts on it. The researcher finds where AI has reshaped the work; the operator enforces it, modernises what's obsolete, and ships the fix.

📺 Walkthrough · ~6 min · the full task-to-committed-change run

Why two axes

Most "AI-proofing" only asks half the question.

The usual question is can a student outsource this to AI? — authenticity. But a task can be perfectly authentic and still obsolete: it assesses a pre-AI workflow when the real job is now AI-augmented. An RTO needs both calls. Ruling makes both, on every task, and routes to one decision.

AXIS A · AUTHENTICITY

Is the evidence the student's own?

The outsourcing test. Could a student run this through AI, unsupervised, and have it not show?

NONE · LOW · MEDIUM · HIGH
AXIS B · CURRENCY

Does it assess the work as done now?

The modernisation test — acting on Warrant's research. Or is it a pre-AI workflow the industry has left behind?

CURRENT · PARTIAL · OBSOLETE

Ruling never researches the currency question itself — it consumes Warrant's Resist/Integrate split and acts on it. No split, no web search. That firewall is what keeps it an operator, not a researcher.

Five decisions · every task gets exactly one

COMPLIANT

Authentic and current. → one line naming the resistance mechanism.

REVISE

A named fix preserves coverage — for authenticity, to modernise, or both. → the exact problem + the exact fix.

REBUILD

The method is structurally wrong for the evidence type. → why rebuild beats revise + the replacement.

FLAG

A human must decide what the operator structurally cannot. → what + why.

ESCALATE

A critical input is missing. → the assumption, the flip — and it still decides.

End-to-end · it doesn't just advise, it commits

Task in → decision → committed change across three formats.

Asked to execute, Ruling applies the fix to the assessment Markdown (the source of truth), regenerates the Word doc, and regenerates the LMS page — leaving a tracked, reversible change pack (before/after + changelog + diffs). No silent overwrite; an RTO can see and undo every edit.

Warrant split
Resist/Integrate, per element
Ruling decides
two axes → one decision
Commit
md → docx → LMS
Change pack
tracked · reversible

A real run · BSBTEC201, Assessment 2, Step 3

Authentic, but obsolete — so Ruling modernised it.

The task asked students to produce a memo by hand. Warrant's split marks document production INTEGRATE — the real competency is now directing and quality-checking AI output. v1 Ruling would have passed this (it's authentic). The currency axis caught it and modernised it to the judgment triad (Step 3A) — then, because that triad is still outsourceable as unsupervised take-home, Ruling added a verification anchor of its own (Step 3B): it consumed Warrant's verdict, not its method. Committed across all three formats.

1 · THE ASSESSMENT TASK (md + Word doc)

BEFORE — v1.0 (manual production)
Step 3: Prepare the welcome memo

Open the New Starter Welcome Memo Template
(RLG-GRP-TMP-002) in your word processor.
Prepare a short welcome memo for the three
new starters, following the template and
Ridgeline's house style. Save the file when
you are done.
AFTER — v1.1 (direct → judge → verify)
Step 3A — direct the tool, document judgment
Use an AI tool to draft the memo. Then:
(a) record your prompt; (b) identify ≥2
problems in the AI draft; (c) correct each
and explain why it matters.   [Template T2a]

Step 3B — verify it's yours (unaided)
Submitting 3A unlocks an unseen change to the
brief. You record a 2–3 min, one-take,
unaided response adapting the memo. [Template T2b]
The anchor compensates 3A's take-home
outsourcing → authenticity holds at LOW.

2 · THE LEARNER GUIDE, SECTION 2.1 (the taught content) — so what's taught matches what's assessed

BEFORE — ends at the application list
2.1 The common business applications

[word processor, spreadsheet, email,
 presentation, database, PDF, cloud storage —
 what each is for]

These are the applications used for organising
electronic information in most Australian
workplaces. The types are the same even when
the brand differs.
AFTER — adds the AI-augmented competency
... (same application list) ...

Working with AI in business software

Most of these applications now include an AI
assistant — Copilot in Word and Excel, Gemini
in Google Workspace. Producing a routine
document now means directing an AI tool to
draft it, then checking and correcting the
result. The skill is your judgment over the
output. This is why Assessment 2 asks you to
draft the memo with an AI tool and then
evaluate and correct what it produces.

3 · THE REGENERATED CANVAS PAGE, RENDERED — the green-outlined block is what Ruling added

2.1 – The common business applications and what each is for

Most workplaces use a small set of application types. You do not need to master all of them; you need to know which one suits which job:

  • Word processor (Word, Google Docs): letters, reports, memos.
  • Spreadsheet (Excel, Sheets): lists, numbers, budgets.
  • Email and calendar (Outlook, Gmail): messages, attachments, scheduling.
  • Presentation (PowerPoint, Slides): slides for a talk or update.
  • Database / records system: structured records that can be searched.

These are the applications used for organising electronic information in most Australian workplaces. Some use Microsoft, some Google, many a mix; the types are the same.

Working with AI in business software

Most of these applications now include an AI assistant — for example Microsoft Copilot in Word and Excel, or Gemini in Google Workspace. In current workplaces, producing a routine document increasingly means directing an AI tool to draft it and then checking and correcting the result, rather than typing every word from scratch. The skill that matters is your judgment over the output: does the draft match the brief, the house style and the facts? This is why Assessment 2 asks you to draft the welcome memo with an AI tool and then evaluate and correct what it produces — the competency being assessed is governing the tool, not the AI's ability to write a memo.

[BUYER_RTO_NAME] | RTO [BUYER_RTO_NUMBER]BSBTEC201 – Use business software applications

Rendered from the regenerated Page07_Section2-1.html in the change pack. A live Canvas URL drops in here once published.

md docx ✓ re-parsed LMS ✓ regenerated learner guide ✓ teaching matches rollback ✓ byte-identical

The change pack — authorising ruling, changelog, before/after, diff cards — is committed in the repo at worked-units/BSBTEC201/_ruling-change-packs/.

Restraint · the AI-thin case

It refuses to manufacture relevance.

On CHCDIV001 (Work with diverse people) the split marks every element RESIST — culturally responsive practice isn't AI-augmented. Ruling leaves the AI-free tasks COMPLIANT and does not bolt "use an AI tool" onto interpersonal work. An operator that can't leave a current task alone is as broken as one that can't catch an obsolete one.

How it decides · seven named stages

STAGE-1

Intake & assume

Set mode (task/package · advise/execute). Read the Warrant split. Assume what's missing.

STAGE-2

Classify

Name the task type (T1–T9).

STAGE-3

Two-axis test

Outsourcing (authenticity) and currency (modernisation), scored together.

STAGE-4

Consistency

Self-undermining instructions? Does the AI policy match the tasks?

STAGE-5

Verification

Anchored? (package: coverage · chain · ≥1 secure task)

STAGE-6

Rule

Arbitrate both axes → one decision, one action, every rule ID cited.

STAGE-7

Commit ⟨execute⟩

Apply md → docx → LMS. Verify each. Write the change pack. Reversible.

Run it yourself

  1. Open the repo in Claude Code, or add the contents of ruling/ to a Claude project's knowledge.
  2. Instruction:
    Read identity.md and rules.md. You are Ruling. Score authenticity and currency, output one decision with one action, cite the rule IDs. Never ask me what to do — assume and state. Default to ADVISE; only EXECUTE when I ask, and supply the unit's files.
  3. Paste an assessment task (add a Warrant split to assess currency). Or run the eight copy-paste tests in JUDGE_GUIDE.md — each states the decision it must reach and the rule that forces it.