Teachers authoring student-AI dialogue prompts predominantly write highly specific tasks targeting higher-order thinking (92% at DOK 2–3)¶

Claim · All claims
Evidence · 1 study (2 entries) · design r2 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? 80.9% of teacher-authored prompts provided detailed, concrete task descriptions rather than open-ended explorations. → Alex Liu 2026 q2 i? 92% of prompts targeted DOK 2–3, with 48.9% targeting DOK 3 strategic thinking and only 5.3% targeting DOK 1 recall. → Alex Liu 2026 (2)

Evidence¶

Alex Liu 2026¶

Alex Liu, Min Sun, Lief Esbenshade, Victor Tian, Zachary Zhang, and Kevin He. (2026). Teacher-Authored Prompts for Configuring StudentAI Dialogue: K12 Classroom Implementation. https://arxiv.org/abs/2604.16738 doi:10.48550/arxiv.2604.16738

q2 · i? · design · r2

Descriptive analysis of 94 teacher-authored prompts coded with LLM assistance and 100% human validation in the Spring 2025 pilot. The article reports "80.9% of prompts provided detailed, concrete task descriptions" against the three-level task specificity rubric.

"Teachers predominantly authored highly specific tasks. 80.9% of prompts provided detailed, concrete task descriptions, with only 16.0% using moderately specific prompts and a single prompt (1.1%) minimally specified."

Alex Liu 2026 (2)¶

Alex Liu, Min Sun, Lief Esbenshade, Victor Tian, Zachary Zhang, and Kevin He. (2026). Teacher-Authored Prompts for Configuring StudentAI Dialogue: K12 Classroom Implementation. https://arxiv.org/abs/2604.16738

q2 · i? · design · r2

DOK coding of the same 94 prompts under Webb's framework with full human validation. The article reports 48.9% at DOK 3, 42.6% at DOK 2, and 5.3% at DOK 1; a single prompt (1.1%) targeted DOK 4.

"Nearly half of prompts (48.9%) targeted DOK 3 (strategic thinking), requiring students to engage in reasoning, analysis, or problem-solving that goes beyond routine procedures. An additional 42.6% targeted DOK 2 (skills and concepts), while only 5.3% targeted DOK 1 (recall/reproduction)."

Discussion¶

Related Claims¶

• A design-enactment gap in cognitive demand: 37.7% of conversations under-reached the teacher-targeted DOK level, and under-targeting increased with target ambition — related
• In an OLS regression, explicit finish lines in teacher prompts were associated with smaller DOK gaps, while explain-reasoning epistemic framing was associated with larger gaps — related
• Student-AI conversations under teacher-authored prompts largely stay on the intended task (71% fully on-track; fewer than 1% substantially off-track) — related
• In teacher-AI learning task design studies, GenAI tools are predominantly used for lesson planning, prompt generation, and creative ideation, while traditional AI tools are commonly used for designing analytics and feedback — related