Scoring & Rubrics¶
Aimee.ai uses AI-powered scoring to evaluate learner performance against defined rubric criteria. This page explains how rubrics work and how scores are generated.
Rubric management: Trainers, Workspace Owners, Admins Score review: Reviewers, Workspace Owners, Admins
How scoring works¶
graph LR
A[Learner completes session] --> B[Transcript captured]
B --> C[AI evaluates against rubric]
C --> D[Score report generated]
D --> E[Reviewer validates]
- When a learner finishes a simulation, the conversation transcript is saved
- The AI scoring engine evaluates the transcript against each rubric criterion
- A score report is generated with per-criterion scores and overall results
- A reviewer can inspect and optionally override the scores
Rubrics¶
A rubric is a set of scoring criteria attached to a course version. Each criterion defines one aspect of performance to evaluate.
Creating a rubric¶
- Open a course in the Course Editor
- Scroll to the Rubric section
- Click Add Criterion
- Fill in the criterion details:
| Field | Description |
|---|---|
| Title | Name of the criterion (e.g., "Empathy") |
| Description | What this criterion measures |
| Weight | Relative importance (default: 1.0) |
| Guidance | Instructions for the AI scorer on how to evaluate this criterion |
Example rubric¶
A customer escalation course might use:
| Criterion | Weight | Description |
|---|---|---|
| Empathy | 1.5 | Did the learner acknowledge the customer's feelings? |
| De-escalation | 2.0 | Did the learner successfully calm the situation? |
| Policy Adherence | 1.0 | Did the learner follow company policy? |
| Resolution | 1.5 | Did the learner propose an appropriate resolution? |
Weight strategy
Higher weights make a criterion count more toward the overall score. In the example above, "De-escalation" has the highest weight (2.0) because it's the most important skill for an escalation course.
Score reports¶
A score report contains:
| Field | Description |
|---|---|
| Overall Score | Weighted average across all criteria (0–100) |
| Breakdown | Individual score per criterion |
| Feedback | AI-generated qualitative analysis |
| Recommendations | Suggested improvements for the learner |
| Status | pending, processing, completed, error |
Score calculation¶
The overall score is calculated as a weighted average:
Overall = Σ (criterion_score × weight) / Σ (max_possible × weight) × 100
Pass/fail¶
The trainer sets a pass threshold per course (default: 70%). If the overall score meets or exceeds the threshold, the learner passes.
Reviewing and overriding scores¶
Reviewers can:
- View the full score breakdown for any completed session
- Override individual criterion scores or the overall score
- Add notes explaining the override rationale
Override audit trail
All overrides are recorded. Include a clear justification when overriding an AI score.
Related¶
- Courses — creating courses with rubrics
- Assignments — assigning courses
- Reviewer role guide — review workflow