Generate Variants with AI

Writing a second version of an exercise by hand is the expensive part of exercise variants. For a programming exercise it means re-theming the problem statement, template, solution and tests consistently, keeping every task-to-test link intact, and making sure the solution still builds green while the template still fails.

Artemis can do that work for you. Create Variant takes an existing exercise, asks what should change, and produces a complete, verified Artemis exercise in the background.

ℹ️

Information:

Variant generation is part of Hyperion and is available only when your Artemis instance has the Hyperion module enabled. It requires at least the Editor role in the course.

Supported Exercise Types

Exercise type	Supported
Programming	Java with Gradle or Maven student and test projects on LocalVC + LocalCI, with whole-exercise generation enabled; no auxiliary repositories, sequential tests, or static code analysis
Quiz	Yes, unless the quiz contains drag-and-drop questions
Modeling, Text, File Upload	No

The action is hidden when the required module is disabled or you lack Editor access. For programming exercises, it is also hidden in exam management. On programming exercise details pages, unsupported configurations show a disabled action with an explanation. In exercise lists, the action is hidden when the list data identifies an unsupported configuration. If that data omits configuration details, the action can remain available; open the details page to see the configuration check and any explanation.

Starting a Generation

On an exercise's details page, the yellow Create Variant button appears with the editing actions. On the course's Exercises page in course management, the overflow menu (…) of an exercise row offers Create Variant. For quiz exercises in exams, the same action sits on the rows of an exercise group.

Create Variant alongside the editing actions on a quiz’s details page

A wizard collects the requested changes and placement. Programming variants then continue in the shared AI authoring run view; quiz variants use the wizard's progress and result steps below.

Select What Should Change

Pick one or more aspects. You can combine them freely.

Choose the aspects the AI should adapt

Aspect	Effect
Difficulty	Re-tunes how hard the exercise is. The variant keeps the core concept and the clear majority of its tests — it is never gutted, and a task never becomes easier by handing students working code
Application Domain	Moves the exercise to a different real-world theme. Algorithm, data-structure and design-pattern names stay as they are, because they are the learning content
Storytelling	Sets the narrative style, from a plain technical description to a fully told story
Custom	Free-text instructions of your own

Configure the Aspects

Fill in the details for the aspects you selected: the target difficulty, the new domain, the narrative style, and your custom instructions.

The narrative styles are:

Style	Description
Technical	No story — a plain, concise focus on the technical concepts
Realistic	A short real-world scenario introduces the task, the rest stays technical
Creative	A story carries the task: themed setting, named actors, story-driven examples

Choose the Placement

Decide where the finished variant goes.

Placement: create a group with the original, join an existing group, or stay standalone

Option	Result
Create new group with original	A new variant group holding the source exercise and the variant. You set the group title, points cap and timeline right here
Add to group "…"	The variant joins the group the source exercise already belongs to
Add as standalone exercise	No group — the variant appears on its own in the exercise list

Follow the Generation

The wizard shows the phases as they happen: the source exercise is analyzed, the change is planned, a real copy is provisioned, the changes are applied, and the result is verified and — if needed — repaired.

The live timeline of a running generation

A programming variant runs real template and solution builds, so a generation typically takes a few minutes. Quizzes are faster.

For a quiz variant, click Run in Background to close the wizard and let the job continue. The shared AI activity tray shows quiz variants alongside programming authoring. Open a row to inspect its progress and available cancellation controls; closing or dismissing the tray does not cancel the run.

The shared activity tray, illustrated with programming runs

For quiz variants, canceling ends the job and removes the half-finished copy, including its repositories and builds where applicable. Quiz job details remain available for 24 hours.

Programming variants use the same cancellation boundary as adaptation: they can be cancelled before persistence, but not during draft repository preparation or saving. Their destination remains a visible draft when generation fails or is cancelled, so you can inspect, retry, or delete it. No unverified generated candidate is saved. Owner-scoped run history and status links are temporary: the configured retention window defaults to four hours (artemis.hyperion.generation.terminal-replay-ttl). After the run records expire, the run is absent from history and its status link is unavailable. Ordinary exercise version snapshots remain available independently. Detailed progress and retained working files have their own retention limits.

Review the Result

A finished variant with every check green

The result step summarizes what the AI did per phase, how many tokens the run used, and offers Open in Editor to review the variant.

What Artemis Checks

Programming variants pass the same isolated verification as programming exercise authoring: the solution must pass, the template must fail the intended graded tests, and repository integrity and task bindings must hold. Quality findings remain visible for instructor review. Failed verification never saves an unverified candidate.

Quiz variants check question validity, answer options, and points. A best-effort quiz critique reviews wording and answer quality. If this AI-backed check cannot run, it contributes no finding; a completed quiz still needs instructor review.

Outcomes

Programming variants report Saved, Needs review, Failed, Cancelled, or Partially saved in the shared run view. Verified output is applied without a separate acceptance screen. A placement conflict is reported rather than overwriting concurrent edits. A partial save requires reconciliation. See cancel, adapt, and undo for guarded version restoration.

The following result labels and cleanup behavior apply to quiz variants:

Outcome	Meaning
Completed	Every hard gate passed, and every best-effort check that ran reported nothing. The variant is placed as configured and ready for review. A best-effort check that could not run is skipped silently, so review the variant yourself rather than reading Completed as a full semantic sign-off
Draft with warnings	Some check did not pass within the attempt budget, or the placement failed. The exercise is created all the same, with a short note on what is wrong — open it in the editor and fix that. A warning about the placement means the variant is not in the group you chose, so move it there yourself
Failed	The run could not produce a variant. The result step explains the phase it failed in and how to continue, and the half-provisioned exercise is deleted
Canceled	You stopped the run, and the half-provisioned exercise is deleted

⚠️

Warning:

A generated quiz variant is not held back from students. A course quiz variant is a real exercise and copies the dates of the exercise it was generated from, whatever the outcome — Completed as much as Draft with warnings. Generate a variant of an exercise that is already released and the variant is released too, before you have reviewed it. Generate variants before releasing the original, or postpone the variant's Release Date as soon as the run finishes; for a variant placed in a group, that date belongs to the group.

ℹ️

Information:

Deleting the half-finished copy of a failed or canceled run can itself fail — if the repository or the build cannot be removed, the exercise survives. Artemis says so on the result step and links the copy with Open in Editor, so that a run reporting a cleanup problem is one to follow up on: delete that exercise by hand.

⚠️

Warning:

AI-generated content may contain errors. Review a variant carefully before releasing it to students — the gates verify that the exercise builds and hangs together, not that it teaches what you intended.

Programming course destinations start unreleased. After verification, placing a destination in a variant group applies that group's timeline, which can already be released. Choose placement dates deliberately; automatic verification does not replace your teaching review.

Exam Exercises

Whole-exercise programming generation, adaptation, and variants are not available for exam exercises. Existing legacy repository generation is unchanged.

Quiz variant generation remains available for exam exercises. It has two deliberate differences:

• There is no placement step. The variant always joins the exercise group of its source, which is what makes it usable as a per-student variant, and it inherits the exam's timing.
• There is no difficulty option. Exam difficulty is reviewed in advance, and handing students variants of differing difficulty would be unfair.

For exam exercises the wizard has no placement step and no difficulty card

Troubleshooting

The Action Is Not Visible

Check that the Hyperion module is enabled on your instance, that you have at least the Editor role in the course, and that the exercise is a programming exercise or a quiz without drag-and-drop questions.

The Run Ended as a Draft with Warnings

Open Show technical details on the result step. It names the gate that did not pass — most often a build that stayed red or a task reference that no longer resolves to a test. Fixing that in the editor is usually a small edit.

The summary above it is written by the model, so read it as a description of what went wrong, not as instructions: the exercise already exists by then, and there is no later publish step to reach. If one of the warnings is about the placement, the variant is not in the group you chose and you have to move it there yourself.

Generation Is Slow

Programming variants run template and solution builds in the isolated generation worker, not the ordinary LocalCI build queue. They require an available worker slot. An admitted run can take many minutes; the shared header shows actual stages rather than a percentage estimate.