Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note2 min read

Thinkink: 2D Spatial Ink-native Interaction with LLMs

Source

arXiv

arxiv.org/abs/2607.21468v1

Read the source

Source

Plain-Language Brief

Researchers propose Thinkink, a tool that allows users to interact with large language models (LLMs) using handwritten notes and sketches on a shared digital canvas. The tool was designed through a series of studies to understand current practices, identify challenges, and improve the usability of the system.

What the Document Says

  • The researchers propose Thinkink, a tool for interacting with LLMs using handwritten notes or sketches on a shared digital canvas.
  • Handwritten text and drawn sketches can trigger LLM-generated responses visualized as ink-like text and sketches on the canvas.
  • A semantic tree streamlines ink interpretation, and a lightweight UI provides explicit control using a state machine.
  • The tool was designed through a three-stage process: formative study (N=12), technical probe for diagnostic study (N=6), and final study (N=10).
  • The formative study examined current practices with conventional and digital inking methods, the diagnostic study identified usability and human-LLM interaction challenges, and the final study examined how people incorporate Thinkink into their ideation practices.
  • The researchers contribute design implications and a tool for ink-native LLM interaction.

Key Concepts Mentioned

  • Thinkink
  • large language models (LLMs)
  • handwritten notes
  • sketches
  • semantic tree
  • state machine
  • formative study
  • diagnostic study
  • final study

Claims Made by the Document

  • Thinkink allows users to interact with LLMs using handwritten notes and sketches on a shared digital canvas.
  • The tool was designed through a three-stage process.
  • The formative study, diagnostic study, and final study provided insights into current practices, challenges, and the incorporation of Thinkink into ideation practices.

Evidence Used

  • The text states that the researchers propose Thinkink and describe its features.
  • The text mentions a three-stage process for designing Thinkink, which includes formative, diagnostic, and final studies.
  • The text provides details about each study's purpose and findings.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

People often use handwritten notes and sketches to externalize ideas for ideation. To integrate large language models (LLMs) into this practice, we propose Thinkink. Prompts can be handwritten text or drawn sketches with LLM-generated responses visualized as ink-like text and sketches spatially integrated into a shared canvas. A semantic tree streamlines ink interpretation, and a lightweight UI provides explicit control using a state machine. The tool was designed using a three-stage process. A formative study (N=12) examined current practices with conventional and digital inking methods. The results informed a technical probe for a diagnostic study (N=6) identifying usability and human-LLM interaction challenges. This motivated the design of Thinkink, with a final study (N=10) examining how people incorporate it into their ideation practices. We contribute design implications and a tool for ink-native LLM interaction where the user and LLM write and draw in a shared 2D canvas.