Configure the level of AI assistance per assignment according to learning objectives¶

Strategy · All strategies
Evidence · no claims cited

Description¶

The article recommends treating AI access as a configurable dial rather than a binary permission. As stated in its design goals, "Rather than treating AI access as allowed or forbidden, instructors can configure the level of AI assistance according to the assignment and learning objectives." In DRAFTTRACE, instructors can enable or disable the integrated assistant per assignment, and a system prompt instructs it to support understanding rather than write answers. This configurability also enables controlled studies of when assistance should be provided.

Design Implications¶

Context¶

Requirements¶

• A writing platform that supports per-assignment configuration of AI assistance and captures interaction traces

Constraints¶

Target Learners¶

• higher education students
• graduate students

Target Learning Goals¶

• aligning AI assistance with assignment learning objectives
• studying when and in what form assistance should be provided

Affordances¶

• Three Views Product Process Interaction Writing

Related Strategies¶

• Evaluate LLM-supported learning beyond binary access by measuring enacted interaction and preserving no-help assessments

Examples¶

-

Key Sources¶

• Divyansh Chandarana, Sandipan De, Vivek Gupta. (2026). DRAFTTRACE: A Multi-View Analytics Environment for AI-Integrated Writing. https://arxiv.org/abs/2609.36544