Configure AI features

AI features are optional and configured separately for each course. Instructors can configure course AI agents and grading behavior, but they can choose only the providers and models enabled by their administrator. All controls described below are instructor controls.

AI settings

Open the course-name menu and select AI Settings. The page has three panels.

Course context

Course context is background used by applicable grading, rubric, solution, and class-performance features.

AI grading policy

Policy changes affect future launches only; they do not change work already running or completed.

• Grading mode selects non-deliberative independent assessments or deliberative rechecks.
• Number of independent agents selects one to three primary models in non-deliberative mode. One model cannot establish agreement or provisional approval.
• Maximum rechecks permits one or two peer-informed rounds in deliberative mode.
• Agreement tolerance defines the permitted score range for agreement.
• When agents agree, use selects model priority, highest score, or lowest score; model priority breaks ties.
• Provisionally approve assessments when agents agree makes eligible agreed results available for human bulk approval. It never creates a fully approved grade.

AI agents

An AI agent is a named provider-and-model choice available to the course. Agents are course-specific: adding or editing an agent does not change another course.

To add an agent:

1. Select + Add New Agent.
2. Enter a unique Agent name for the course.
3. Choose an LLM provider from the displayed list. If exactly one provider is available, it is selected automatically.
4. Choose a Model from the displayed list. If exactly one model is available, it is selected automatically.
5. Select Create Agent.

If the required provider or model is absent, an instructor cannot add it from AI Settings. Contact Gradebird support.

Use Edit on an agent row to change its name, provider, or model. If an agent already has candidate assessments, changing its provider, model, or generation settings moves the original under Show archived agents and creates an updated agent for future work. Other edits are applied directly. Deleting an unused agent removes it; deleting one with prior work moves it under Show archived agents.

Drag the handle at the beginning of an active agent row to change priority. The order saves automatically. Select Show archived agents to inspect archived entries, and use Restore to return an eligible archived agent to active use.

The grading policy uses the first required active agents as primary models. Later active agents are ordered backups. A completed workflow identifies when a backup was used. An archived agent is not selected for new work.

The initial AI configuration is copied when a course is created. Later organization-level changes do not change that course's saved policy or agent order. Review the active agents if an expected choice becomes unavailable.

Review AI-assisted results

AI output can propose a rubric, analyze a problem, recognize a marked choice, suggest a roster match, or propose an assessment. It does not publish an exam or rubric, choose the canonical packet, approve a free-response final, or release a student report. Review the visible source evidence and save the human decision required by that workflow.

AI agent prompt preview

This read-only page previews the provider-specific prompt structure for an AI agent using representative problem data. It helps an instructor understand how the saved agent configuration is translated for a provider; it does not launch AI work, expose a student response, or modify the agent.