Students use the integrated AI assistant differently across writing stages: clarification early, verification late¶
Claim · All claims
Evidence · 1 study · designr2·q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q2 i? Students whose first prompt came in the first quarter sought clarification or direct help, while students who first used the assistant in the last quarter almost always sought verification of their answers. → Divyansh Chandarana 2026
Evidence¶
Divyansh Chandarana 2026¶
Divyansh Chandarana, Sandipan De, Vivek Gupta. (2026). DRAFTTRACE: A Multi-View Analytics Environment for AI-Integrated Writing. https://arxiv.org/abs/2609.36544 doi:10.48550/arxiv.2609.36544
q2 · i? · design · r2
Interaction-view analysis of the classroom setting, in which 32 of 81 students used the integrated assistant, issuing 75 prompts (median 2 per student). Sessions were divided into four equal quarters and prompts categorized as clarification, verification, direct help, or collaboration. Descriptive counts only.
"Students whose first prompt came in the first quarter sought clarification (6 of 10) or direct help (4 of 10). Students who first used the assistant in the last quarter almost always sought verification of their answers (9 of 10)."
Discussion¶
Related Claims¶
- Students' LLM use in CS2 fell into three themes: understanding, assisting code writing, and writing code, with only a few using LLMs to write code — related
- Engineering students most often use LLMs for academic writing (27%), conceptual clarification (20%), programming help (17%) and brainstorming (13%) — related
- How genAI is used, not who uses it, predicts whether independent performance declines or improves — related
- Within a single LLM session, students' help-seeking shifts toward answer- and verification-seeking while explicit self-regulation modestly increases — related
- The majority of AI-assisted participants self-report using the AI primarily to get answers directly, a pattern validated against chatlogs — related
- High-achieving students describe selective AI use for clarification, summarisation, and workflow support while verifying outputs and keeping them subordinate to their own judgment — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
assistant-use-varies-by-writing-stage |
title |
Students use the integrated AI assistant differently across writing stages: clarification early, verification late |
description |
Students use the integrated AI assistant differently across writing stages: clarification early, verification late |
status |
review |
evidence_strength |
weak |
newest_evidence |
2026 |
generated |
by process:wiki-ingest on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — divyansh-chandarana-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.