# PME workbench guide

Status: Proposed PME design — awaiting faculty trials and evidence from use.

Design practice in professional judgment, inherited inputs, risk, and accountable authority.

## Readiness and responsibility

Check understanding of the professional task, source limitations, authority, and causal inference. Seniority does not establish readiness. Model unfamiliar analysis before expecting independent critique.

Learners own recommendations and the decisions assigned in the exercise. Faculty own pedagogy and assessment; actual operational authority remains outside this fictional exercise.

## Worked teaching example

### Fictional outage brief

This is an authored, fictional design example, not a classroom result or a captured model response. Offer it as an optional starting point; the educator may supply a different task.

A fictional report records 12 outages: 8 followed equipment updates and 4 have unexplained causes. The proposed AI contribution attributes all 12 to updates and recommends a fleet-wide rollback. Timing alone does not establish cause, and the 4 unexplained cases do not support that attribution.

### Interactive sequence

1. Before showing the contribution, ask which conclusions the report supports and what additional evidence a rollback decision requires.
2. Ask one question at a time and wait. Show the constructed contribution after the initial judgment; let the educator accept, check, revise, or refuse with reasons. Provide assistance when requested and record it.
3. Replace the report with independent diagnostic evidence identifying a software defect in 10 outages; 2 remain unexplained. Ask what now warrants action, what uncertainty remains, and who has authority to act.
4. Save the initial judgment, inspected assumption, accepted or revised recommendation, residual risk, and response to the changed evidence.

## Reference matrix

These are proposed practices for this setting. Choose by learning objective and task readiness. The six phases are a design lens, not a validated developmental sequence; later phases are not automatically better.

| Practice | Learner | Educator | Institution |
| --- | --- | --- | --- |
| Ask | Ask a bounded question about the report; distinguish answering from taking action. | Model source checking and the limits of an operational analogy. | Provide approved public or synthetic materials and tool boundaries. |
| Understand | Explain association versus cause using the outage evidence. | Check the explanation without requiring new strategic vocabulary. | Make prerequisite primers and review time available. |
| Produce | Draft a limited recommendation from supplied evidence. | Specify what the officer must decide and what may be delegated. | Define disclosure, source handling, and exercise authority. |
| Judge | Accept, revise, or refuse the rollback proposal with reasons. | Probe uncertainty and the changed diagnostic evidence. | Support review of reasoning, not only finished briefs. |
| Codify | Save a reusable causal-check method with exceptions. | Test the method on a second professional case. | Retain reviewed versions, provenance, and unresolved disagreement. |
| Supervise | Direct bounded analysis with checkpoints and a stop rule. | Inspect whether the learner can interrupt unsupported recommendations. | Keep operational permissions and human approval outside classroom automation. |

## Evidence needed before broader use

Two faculty reviewers inspect the same fictional decision record. Compare causal reasoning, authority boundaries, and how the learner handles residual uncertainty. Record disagreements and actual review time. Later test transfer to another professional case; do not infer operational competence from this exercise.

Record the setting, subject, task, participants’ roles, support, observed evidence, reviewer disagreement, and limits. Evidence from one audience does not validate another. A software check or an educator rehearsal does not establish student learning.

Keep the essay, claims, and source spine as the original argument and evidence. These examples are teaching proposals derived from the shared method; they add no claim of demonstrated effectiveness. Jev remains a separate evaluation workstream.