AI services ready
DW
Panel assurance

Transparent evidence and governance

ExperienceCraftAI makes its pedagogical checks, design evidence and human decision points visible. This turns AI generation from a black box into an auditable co-design process.

Hard constraints passed4 of 4
100%
Safety, time, format and accessibility
Learning modes evidencedof 7
6
Each mapped to a concrete activity feature
Bloom progressionMiddle → High
3
Apply, analyse and evaluate
Human approvalsMandatory
3
Refine, select and improve

Alignment evidence matrix

Every claim is connected to a visible activity design feature

Fully evidenced
Framework / criterionTargetDesign evidenceConfidence
Learning outcomeClassify microorganism groups using characteristicsEvidence-based classification and defenceHigh · 96
Bloom: ApplyUse characteristics in a novel scenarioOutbreak clue analysisHigh · 95
Bloom: AnalyseDifferentiate plausible organismsCompare evidence and reject an alternativeHigh · 97
Bloom: EvaluateJustify a response planTeam presentation and cross-questioningHigh · 91
7 Modes: DoingLearn through purposeful actionHands-on sorting and investigationHigh · 94
7 Modes: Social belongingConstruct understanding with othersInterdependent team rolesHigh · 93
Seriously Fun: AgencyMeaningful learner choicesTeams choose evidence strategy and response planGood · 87
FeasibilityDeliverable in 120 minutesTimed run sheet and low-complexity materialsHigh · 96

Human oversight trail

Clear accountability

01
Lecturer refined the briefAdded rejected-alternative requirement
02
Lecturer selected the optionChose outbreak investigation
03
Lecturer approved version 2Pending after first implementation
Pending

AI is advisory, not autonomous

The system proposes, explains and checks. The lecturer owns the teaching decision and can edit every output.

Traceable design rationale

Why each element exists

The outbreak scenario directly answers the prior feedback that learning felt too theoretical. Team roles provide structured social interaction, while the response plan raises the task from classification to evaluation.

Constraint assurance

Before generation and after refinement

No live microorganisms are used. Materials are printable, instructions are multimodal and no success cue depends on colour alone.

Evidence-informed improvement

Post-implementation learning

Student outputs, rapid sentiment, timing data and lecturer notes are combined to propose specific, reviewable refinements for the next run.