Overview

Feedback Aide is an embeddable API for assessing a learner response against a rubric using Learnosity’s AI engine. Feedback Aide is a safe and efficient assistant for evaluating and providing quality feedback on essays and short responses.

Request a demo

Learnosity's AI engine generates an initial score for a learner response, given the Question stem and a grading rubric, as well as actionable, written feedback. Learnosity's FeedbackAide API then helps graders easily edit the generated scores and feedback.

Screenshot 1: Feedback Aide showing the rubric / assessment criteria

How it works

Feedback Aide takes an essay "stimulus", a scoring "rubric", and a user "response". It then evaluates the response to the stimulus against the rubric and identifies the appropriate rubric levels for the essay and provides constructive feedback based on the essay.

This can then be reviewed, and modified by a human grader prior to be saved.

Once the feedback has been finalized it can then be presented to the learner in a simple read-only interface.

Feedback Aide can also handle short response Questions, taking a short stimulus, a rubric of correct answers and a user response. It then evaluates the response against the rubric, scoring the student and providing them constructive feedback based on which parts of the correct answer they achieved.

Screenshot 2: Feedback Aide showing the automated grading decisions (in orange)

Screenshot 3: Feedback Aide showing the manual grading decisions (in blue)

Screenshot 4: Feedback Aide grading a short response question (teacher and student views)

What can Feedback Aide score?

Essays

Feedback Aide can score essays in many styles from persuasive to narrative to expository to research-based from grade school through to university level. 

We offer:

• AI enhanced feedback and grading of essays between 100 and 15,000 characters.
• Rubrics that cover different grading types:
  • analytic: assess learner work across multiple different criteria
  • holistic: assess learner work as a whole

Read more about our rubric types.

Short Responses

Feedback Aide can score constructed response Questions across many subjects from english to social studies to science to math.

We offer:

• AI enhanced feedback and grading of short response Questions up to 2,000 characters.
• Rubrics that cover different Question types:
  • sr-general: Questions that require a short answer or explanation.
  • sr-categorize: evaluate the learner's ability to categorize or classify information.
  • sr-keypoints: evaluate the correctness of the key points in the response (Screenshot 4).
  • sr-x from y: use when a student must provide 1 or more (X) correct answers from a longer list of (Y) correct answers.

Read more about our short response rubrics.

Modalities

Feedback Aide can score:

• HTML or plain text responses passed to us from your product platform or system.
• .docx files (through our docx-to-html endpoint).
• Video and audio transcripts (through our transcription endpoint).

What workflows are available?

• Grading state. This is meant for the first scoring of a learner’s response. It initializes with a blank rubric and a null score.  If this session has previously been initialized, it will restore any feedback that has previously been saved. In this mode, the grader can trigger the scoring of the response, review AI-generated scores and feedback, and override scores and feedback.

• Learner review state. This is a read-only view of the populated rubric, overall score, and written feedback aimed at learners and administrators/reviews. Before this state can be shown, a grader must accept the scores and feedback, and approve them as ready for review. This UI therefore doesn't distinguish between AI and human scores.

  

  Screenshot 5: Feedback Aide in learner review state

What options are available?

• Localise and internationalize Feedback Aide.
• Choose from 20 supported languages to have all system-generated feedback delivered in the language you select. See feedback language option.
• Customize grading to match the learner’s level and the desired marking style.
• Provide up to 10 sources for reference during grading.
• Detect essays not meeting minimum requirements with the Content & Structure Agent.
• Identify responses with sensitive or concerning content with the Moderation Agent.
• Assist graders through justification and annotations with the Explainability Agent.

Troubleshooting

• Manual grading: If AI grading isn't enabled or is unavailable, a human grader can manually score the response using the rubric.
• Unsupported essay: If the response is less than 100 characters or over 15,000, Feedback Aide will not grade the essay. Graders will be shown a warning message and can manually grade the response.
• Unsupported short response: If the response is over 2,000, Feedback Aide will not grade the response. Graders will be shown a warning message and can manually grade the response.
• Disruption: If there is an interruption in service from the AI engine, the grader will see an error message informing them of the disruption. They have the option to regenerate, resend the information to the engine, without using additional credits, or to manually grade.

Release Notes

The detailed release notes are available on Feedback Aide Release Notes.