Polish

• Improvement: updated the advanced-essay model to point to 2025-11-07, which included grader annotation support and minor tweaks to topic check.

Features

• Added support for the moderation evaluation option for use with short response rubrics.
• Added a new POST /utility/generate_transcript/{transcript_uuid} endpoint that generates a transcript from an uploaded video or audio file.
• Added support for AI-generated annotations that automatically highlight key elements in learner responses such as: the main idea or thesis statement, supporting evidence, and citations.
• Added annotations evaluation option to control which annotations to enable.
• Added modules.grader_annotations option in the createUI method to show annotations in the grader interface.
• Added a close button to the modal header and improved its accessibility. (Rubric Editor)

Polish

• Improvement: added more details to the structure check error messages.
• Improvement: existing feedback can now be rendered in the Feedback Aide UI if an evaluate endpoint call was previously used to generate feedback for the session.
• Improvement: all headings in the Feedback Aide interface are now constantly using bold styling.
• Improvement: updated the justification of score output to return more detailed information on how each score was determined.

Bug fixes

• Fixed a bug that prevented the server-side documentation from rendering.

Bug fixes

• Fixed a bug where certain characters in notification messages were being escaped.

Polish

• Improvement: added linebreak handling to the docx-to-html endpoint.
• Improvement: removed deprecated models from the Feedback Aide API for essay and short responses.
• Improvement: updated internal libraries to maintain security, stability, and performance.
• Improvement: updated the default model to match the rubric type if it was not provided as an argument to the generateFeedback() method.

Bug fixes

• Fixed a bug that caused the rubric editor to crash when adding a new level to a holistic rubric. (Rubric Editor)

Polish

• Improvement: enhanced the accessibility of the Feedback Aide UI in the review state.
• Improvement: renamed the createUI argument saveButton to save_button for consistency in casing with other arguments.
• Improvement: updated internal libraries to maintain security, stability, and performance.

Features

• Added support for rendering additional context within the Rubric UI component, enabled using the additional_context property in the modules.rubric argument of the createUI() method.
• Added support for including additional context in Rubrics within the Rubric Editor API. (Rubric Editor)
• Added support for rendering score justification through a new UI component, enabled using the justificationOfScoreView property of the modules argument in the createUI() method.
• Added the justification_of_score evaluation option, which provides a justification for the score given when enabled.
• Added language_check evaluation option to mark responses as non-scorable when they were not in the expected language.
• Added "failed_check" field to not_scorable response objects on evaluation endpoints to enable appropriate filtering and handling.

Polish

• Improvement: disabled add buttons when the maximum number of elements had been reached. (Rubric Editor)
• Improvement: warnings are now displayed in rich text fields when content exceeds the maximum length. (Rubric Editor)

Bug fixes

• Fixed a bug in the rubric editor where applying the source did not correctly update the rich text editor. (Rubric Editor)
• Fixed a bug related to switching between rubric types by replacing the source. (Rubric Editor)

Polish

• Improvement: evaluate endpoints now return HTTP 503 errors when upstream services had temporary availability issues or required backoff, and callers were expected to retry with exponential backoff.

Features

• Added rich-text editing for all short response rubrics. (Rubric Editor)

Bug fixes

• Fixed a bug that caused source credits to be undercounted in some cases.
• Fixed a bug where adding new criteria to the analytic or holistic rubrics would leave the new accordion entry collapsed by default. (Rubric Editor)
• Fixed a bug where holistic rubrics with empty criteria titles caused an extra "." character to appear in feedback.
• Fixed a bug where indentation styles that were applied in the rich text editor were not appearing in the rubrics. (Rubric Editor)
• Fixed a bug where rubric-editor point values were covered on Firefox. (Rubric Editor)
• Fixed a bug where X from Y was missing the Alternate responses field. (Rubric Editor)
• Fixed a bug in the display of Short Response General rubric possible responses so it's easier to distinguish between different responses when they contain rich text, such as paragraphs.

Polish

• Improvement: enabled HTML rendering in the short response rubrics. (Rubric Editor)
• Improvement: update the validation logic for the setFeedback() method.
• Improvement: removed the default text from Short Response X from Y template. (Rubric Editor)

Features

• Added support for MathML rendering when using the enable_math_rendering option in the createUI() method.

Bug fixes

• Fixed a bug in the UI where at small container sizes, the rubric legend's total score would become truncated.
• Fixed a bug where the "Summary of Feedback" field would be immediately focused when initially loaded.
• Fixed a bug where the feedback:complete event was not emitted during subsequent generateFeedback() method calls.

Polish

• Improvement: allow detailed score range customization in analytic rubrics. (Rubric Editor)
• Improvement: updated the names for the English variants in the language evaluation options.

Features

• Added new enable_math_rendering option to the createUI method, allowing LaTeX rendering in the UI.
• Added support to include sources in requests with topic check enabled, improving topical-relevance accuracy.

Bug fixes

• Fixed a bug where the Feedback Aide UI failed to render when the sr-general rubric had empty alternate or incorrect criteria.
• Fixed a bug where sources with content under 20 characters prevented the Feedback Aide UI from rendering.
• Fixed a bug where disabling both stimulus and response introduced excessive whitespace above the rubric.

Polish

• Improvement: Removed the "X" button that indicates that the student got a criterion incorrect from the UI for the sr-xfromy rubric to improve readability and reduce visual noise.
• Improvement: Adjusted docx to html endpoint to generate HTML snippets instead of full HTML pages.
• Improvement: Updated HTML sanitizer to strip disallowed tags instead of encoding them.

Polish

• Improvement: enhanced the server-side performance when handling multiple requests.
• Improvement: enhanced HTML sanitization of all parameters to prevent XSS attacks, ensuring all user-generated content is secure.
• Improvement: moved the /docx-to-html utility to /utility/docx-to-html to group current and future utility endpoints; the original /docx-to-html route is now deprecated.
• Improvement: enhancements to the dedicated editor interface for rubrics.

Features

• Added a citation_check evaluation option to mark responses with insufficient in-text or bibliographic citations as non-scorable.
• Added a min_paragraph_words parameter to the structure_check evaluation option to define the minimum number of words required for a paragraph.
• Added support for the language and grading evaluation options in the latest Short Response evaluation model, enabling multilingual and context-aware feedback.
• Added support for additional options in createUI to provide more granular control over the UI.
• Added initial support for editing rubrics through a dedicated editor interface.

Bug fixes

• Fixed a bug where the language evaluation option was not correctly applied to Topic Check and Moderation.
• Fixed a bug where special characters in the title of a rubric criteria caused the evaluation to fail.
• Fixed a bug where the first HTML sub-element of some content rendered in a larger font size.
• Fixed a bug where malformed data URIs in stimulus and rubric content caused evaluation failures. The content is now sanitized in the frontend, and the backend rejects evaluation requests if data URIs are present.
• Fixed a bug that misaligned score bubbles vertically in the rubric-score bar.

Polish

• Improvement: updated evaluation option parameter names to consistently use snake_case. Parameters are now topic_check and structure_check instead of topiccheck and structurecheck.
• Improvement: updated the schema for sr-categorize to aid rubric authoring.
• Improvement: updated the schema for sr-general to align with sr-xfromy.
• Improvement: updated the schema for sr-xfromy to allow more than one correct answer.
• Improvement: reduced the minimum essay response length from 100 to 20 characters, allowing shorter formative answers.
• Improvement: enhanced the UI for Short Response rubrics.

Features

• Initial v1.x public release.
• Added support for shortresponse question scoring with 4 different rubrics to handle different question types.
  • sr-general: questions that require a short answer or explanation.
  • sr-keypoints: evaluate the correctness of the key points in the response.
  • sr-categorize: evaluate the learner's ability to categorize or classify information.
  • sr-xfromy: use when a student must provide 1 or more (X) correct answers from a longer list of (Y) correct answers.
• Added a new configuration in the createUI that allows switching the rubric layout in between auto,compact, and full
• Added 2025-03-14 models which add support for new model grading options:
  • grading.learnerlevel: allows specifiying the context of the learner for more accurate grading and feedback.
  • grading.markingstyle: allows specifiying the context of the grader to be more generous, balanced or harsh as required.
• Added preview support for additional languages: fi: Finnish, sv: Swedish, no: Norwegian, da: Danish, nl: Dutch, pl: Polish, en-us: English (US), en-gb: English (UK), pt-br: Portugese (Brazil)

Bug fixes

• Fixed a bug where the sources did not contribute correctly to the credits used calculation.

Polish

• Improvement: increase maximum size of response from 10k to 15k characters.
• Improvement: increase size of allowed sources from 15k characters to 30k characters to allow for larger sources.
• Improvement: improved the layout of the compact accordion view to make it more compact and usable by moving score buttons to top right corner of header.
• Improvement: added a border to Essay to increase usability.
• Improvement: removed the older no longer used essay models 2024-06-30.

Polish

• Unreleased internal version.

Polish

• Unreleased internal version.

Bug fixes

• Fixed a bug where the response changed the case of the rubric title and caused an error.

Features

• Added 2025-02-24 model which adds support for sources and allows up 5 sources to be added to the evaluation of essays.
• Added responsive design accordion layout for the rubric when the available display container is narrow.

Bug fixes

• Fixed a bug where empty JSON parsing failed due to LaTeX formatting in AI responses.

Polish

• Change: Reduced the maximum size of the stimulus from 10,000 to 5,000 characters now that sources are available.

Features

• Added new models: standard-essay-ISCED1-2025-02-05, advanced-essay-ISCED1-2025-02-05, standard-essay-ISCED3-2025-02-05, and advanced-essay-ISCED3-2025-02-05. The ISCED1 variants are optimised for elementary school student levels and the ISCED3 variants for high school students.
• Added feedback in 10 languages other than English via evaluation options for 2025-02-05 and newer models.

Polish

• Improvement: improved the reliability of model responses with adversarial content.
• Improvement: improved error handling for docx_to_html endpoint. It now consistently returns 415 Unsupported Media Type errors when non-DOCX files are sent.

Features

• Added the isReadyForReview method, which determines whether a feedback session has been marked as ready for review.

Bug fixes

• Fixed a bug where a feedback session marked as insufficient_to_grade (i.e. not scorable) incorrectly returned a score when the method getFeedback was called.
• Fixed a bug in the holistic rubric feedback that would show "n" characters instead of newlines.

Polish

• Improvement: enhanced the "Submit to student" flow by disabling the save button with a clear explanation once feedback is marked as ready for review, instead of removing the button.

Features

• Added support for evaluation options in the frontend code that was released in v0.17.0.

Bug fixes

• Fixed a bug where empty paragraphs were counted in the structurecheck. They are now correctly ignored.
• Fixed a bug where moderation was not running on older models.

Features

• Added support for evaluation options to be passed to essay models to control behavior.
• Added support for structure check via the options check for a minimum number of paragraphs in an essay.
• Added support for moderation check via the options.
• Added support for topic check configuration via the options and the ability to tune the relatedness from Slightly related through to Completely related.
• Added models preview-standard-essay-ISCED3-2024-12-16 and preview-advanced-essay-ISCED3-2024-12-16 which work with ISCED level 3 (high school learners).

Polish

• Improvement: updated RESTful API documentation for the Essay Evaluate payload.

Bug fixes

• Internal logging improvements.

Bug fixes

• Added models preview-standard-essay-ISCED1-2024-12-16 and preview-advanced-essay-ISCED1-2024-12-16 which work with ISCED level 1 (elementary/primary learners).

Features

• Added a new method getEvaluateResponse, to retrieve server-generated feedback data.
• Introduced request rate-limiting support to enhance API performance and prevent misuse.

Bug fixes

• Fixed an issue where Docx-to-HTML conversion would fail if no style was applied to a paragraph.

Polish

• Improvement: internal tooling upgrades to improve the stability of the API.

Bug fixes

• Fixed a bug in the topic detection that was causing false positives.

Features

• Added preview models for structured essay formats: preview-standard-structured-2024-11-28 and preview-advanced-structured-2024-11-28
• Added a notification if an essay is not scorable including if it is too short, too long, or off topic.

Bug fixes

• Fixed a bug to validate the session_uuid at the request parameter parsing stage.

Polish

• Improvement: simplified oAuth authentication.
• Improvement: updated models for standard-essay and advanced-essay to point to 2024-11-22 which include topic detection and improved accuracy.
• Improvement: updated the documentation of the REST endpoints and RESTful mode documentation.

Polish

• Improvement: enhanced overall system stability.

Features

• Added a description for each rubric criterion, improving clarity and usability.
• Added a new endpoint to expose all internationalization labels used within the API for easier localization.

Bug fixes

• Fixed a bug where the API would use a different AI model when feedback was re-generated after an error during the previous feedback generation.

Polish

• Improvement: updated internal tooling to enhance the accuracy of our AI models.
• Improvement: sanitized rubric title and description fields to improve API security.
• Improvement: removed vague, low-use internalization labels to streamline localization.

Features

• [BETA] Added a new endpoint to convert .docx files into .html files.

Bug fixes

• Fixed a bug that caused the generateFeedback() progress bar to remain on the screen after grading complex essays.

Polish

• Improvement: improve the feedback accuracy for holistic rubric.
• Improvement: increase the maximum size of the comment box.
• Improvement: various internal tooling upgrades to improve the stability of the API.
• Improvement: various UI/UX clean up to remove unnecessary spacing.
• Improvement: show an error message when an unauthorized or invalid access_token is being used to generate feedback.

Features

• Added support for holistic rubric.

Bug fixes

• Fixed a bug that prevented feedback sessions with a short response from being initialized.

Polish

• Improvement: various internal tooling upgrades to improve the stability of the API.
• Improvement: update the moderation messages to be more informative.

Bug fixes

• Fixed a bug where -moderation models were not working.

Bug fixes

• Fixed a bug where feedback comments would not render after resuming an unsaved session in grading mode and calling generateFeedback.

Features

• Added models for standard-essay-2024-08-05 and advanced-essay-2024-08-05
• Added preview versions of standard-essay-moderation and advanced-essay-moderation, including AI moderation flagging for violence, sexual, and hate content in essays.
• Added a confirmation dialog if AI moderation flags a potential issue.
• Added a progress bar to show grading progress.
• Added input sanitization for untrusted content.
• Added a new setFeedback method.

Bug fixes

• Fixed a bug with rubric levels without titles.
• Fixed a bug with rendering zero-score rubrics.

Polish

• Improvement: deprecated the standard-essay-2024-06-30 and advanced-essay-2024-06-30 models, which have been superseded.
• Improvement: tightened rubric table styles to reduce space used by larger rubrics.

Features

• Added skipped score functionality to currently supported rubrics.

Polish

• Improvement: display unreviewed state instead of rejecting the promise when we create a new feedback session in the review state of a not_ready_for_review / non-existent session.
• Improvement: changed spacing around the stimulus and response areas.

Features

• Added support for rubrics with different score ranges.
• Added ready_for_review support for the feedback session.

Bug fixes

• Fixed a bug causing score and max_score to be intermittently calculated incorrectly during the generateFeedback process.

Features

• Added a new /essays/models endpoint to return a list of available models for essay evaluation.
• Added a new getter method session_uuid to the FeedbackSession instances.

Bug fixes

• Fixed a bug to increase the timeout limit to allow for longer model requests.
• Fixed a bug where an error in customer callbacks could stop all processing on the page.

Polish

• Improvement: increased the scalability and the reliability of the system.
• Improvement: updated the CSS build process for all styles.

Features

• Added credits and tag the models used for metrics.
• Added standard-essay-2024-08-05 and advanced-essay-2024-08-05 models

Bug fixes

• Fixed a bug where the initial auto generated comment was not being saved.
• Fixed a bug to make the feedbackSession request gracefully fail when it is not a 404.

Polish

• Improvement: updated error messages and handling to be consistent.
• Improvement: internal AI engine improvements.

Bug fixes

• Fixed a bug where we calculate the max score based on the highest level rather than the last index.

Polish

• Improvement: removed unused level property.

Bug fixes

• Fixed a bug and added a missing insufficient_to_grade option when resuming.
• Fixed a bug where the wrong validation was applied to a new feedback session.
• Fixed a bug where the comments were not showing when resuming in grade or student mode.

Polish

• Improvement: fix layout alignment with the rubric table.

Polish

• Improvement: updated styling for various elements.