An agentic cursor increased participants' understanding and predictability of the AI agent's actions during collaborative writing¶
Claim · All claims
Evidence · 1 study · causalr?·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? The visible cursor helped participants know where the agent was working and align their own writing process accordingly. → Michael Yin 2026
Evidence¶
Michael Yin 2026¶
Michael Yin, Angela Chiang, Samuel Rhys Cox, and Robert Xiao. (2026). "It Felt a Bit Eerie": Exploring Humanlike Interactions During Collaborative Writing with an Artificial Agent. arXiv. https://arxiv.org/abs/2605.24729 doi:10.48550/arxiv.2605.24729
q2 · i? · causal · r?
In qualitative findings on visual humanlikeness (§5.2.2), participants reported the cursor made agent actions understandable; P46 said "having the cursor there makes it easier to know where the AI is reviewing stuff as opposed to not having it".
"having the cursor there makes it easier to know where the AI is reviewing stuff as opposed to not having it."
Discussion¶
Related Claims¶
- Humanlike AI co-writing (real-time suggestions and an agentic cursor) evoked feelings of surveillance, judgment and eeriness, and the moving cursor distracted writers — related
- Synchronous collaboration with an artificial agent amplifies contextual misalignment because the agent only sees ongoing output, not the writer's planning process — related
- Synchronous autonomous AI suggestions increased perceived writing efficiency but also caused distraction and mental overload during writing — related
- Synchronous AI suggestions shape subsequent writing, offering new ideas but risking influence over the writer's voice and argument — related
- Participants generally felt humanlikeness should not be a design goal for a writing-support agent used as a tool — related
- Agent perception followed a U-shape across variants: the mixed temporally-humanlike/visually-nonhumanlike Variant 2 was rated least positively on partnership and agent-perception measures — related
- Adding a second writing agent increased reported cognitive load, and writing confidence did not increase monotonically with support, with the Single condition reporting the lowest confidence — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
agentic-cursor-increases-agent-understandability |
title |
An agentic cursor increased participants' understanding and predictability of the AI agent's actions during collaborative writing |
description |
An agentic cursor increased participants' understanding and predictability of the AI agent's actions during collaborative writing |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2026 |
generated |
by process:wiki-ingest on 2026-10-11 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — michael-yin-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.