Priyan Vaithilingam
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Priyan Vaithilingam has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Elena Leah Glassman
SEAS, Harvard University, Cambridge, Massachusetts, USA
5 shared publications - Ian Arawjo
Montréal HCI, Université de Montréal, Montréal, Quebec, Canada
4 shared publications - Martin Wattenberg
Insight and Interaction Lab, Harvard, United States
2 shared publications - Alan Leung
Apple, Seattle, Washington, USA
1 shared publication - Amine Mhedhbi
Polytechnique Montreal, Montreal, Canada
1 shared publication - Chelse Swoopes
SEAS, Harvard University, Cambridge, Massachusetts, USA
1 shared publication
Latest Publications
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-18
The Way We Notice, That’s What Really Matters: Instantiating UI Components with Distinguishing Variations
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Open AccessThe Way We Notice, That’s What Really Matters: Instantiating UI Components with Distinguishing Variations
- Open Access
- 27 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Semantic Commit: Helping Users Update Intent Specifications for AI Memory at Scale
- 27 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Open AccessSemantic Commit: Helping Users Update Intent Specifications for AI Memory at Scale
- Open Access
- 1 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 289-300
Imagining a Future of Designing with AI: Dynamic Grounding, Constructive Negotiation, and Sustainable Motivation
We ideate a future design workflow that involves AI technology. Drawing from activity and communication theory, we attempt to isolate the new value that large AI models can provide design compared to past technologies. We arrive at three affordances—dynamic grounding, constructive negotiation, and sustainable motivation—that summarize latent qualities of natural language-enabled foundation models that, if explicitly designed for, can support the process of design. Through design fiction, we then imagine a future interface as a diegetic prototype, the story of Squirrel Game, that demonstrates each of our three affordances in a realistic usage scenario. Our design process, terminology, and diagrams aim to contribute to future discussions about the relative affordances of AI technology with regard to collaborating with human designers.
- 1 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 289-300
Open AccessImagining a Future of Designing with AI: Dynamic Grounding, Constructive Negotiation, and Sustainable Motivation
We ideate a future design workflow that involves AI technology. Drawing from activity and communication theory, we attempt to isolate the new value that large AI models can provide design compared to past technologies. We arrive at three affordances—dynamic grounding, constructive negotiation, and sustainable motivation—that summarize latent qualities of natural language-enabled foundation models that, if explicitly designed for, can support the process of design. Through design fiction, we then imagine a future interface as a diegetic prototype, the story of Squirrel Game, that demonstrates each of our three affordances in a realistic usage scenario. Our design process, terminology, and diagrams aim to contribute to future discussions about the relative affordances of AI technology with regard to collaborating with human designers.
- Top Cited PapersOpen Access
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-17
DynaVis: Dynamically Synthesized UI Widgets for Visualization Editing
Users often rely on GUIs to edit and interact with visualizations — a daunting task due to the large space of editing options. As a result, users are either overwhelmed by a complex UI or constrained by a custom UI with a tailored, fixed subset of options with limited editing flexibility. Natural Language Interfaces (NLIs) are emerging as a feasible alternative for users to specify edits. However, NLIs forgo the advantages of traditional GUI: the ability to explore and repeat edits and see instant visual feedback. We introduce DynaVis, which blends natural language and dynamically synthesized UI widgets. As the user describes an editing task in natural language, DynaVis performs the edit and synthesizes a persistent widget that the user can interact with to make further modifications. Study participants (n=24) preferred DynaVis over the NLI-only interface citing ease of further edits and editing confidence due to immediate visual feedback.
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Top Cited PapersOpen AccessDynaVis: Dynamically Synthesized UI Widgets for Visualization Editing
Users often rely on GUIs to edit and interact with visualizations — a daunting task due to the large space of editing options. As a result, users are either overwhelmed by a complex UI or constrained by a custom UI with a tailored, fixed subset of options with limited editing flexibility. Natural Language Interfaces (NLIs) are emerging as a feasible alternative for users to specify edits. However, NLIs forgo the advantages of traditional GUI: the ability to explore and repeat edits and see instant visual feedback. We introduce DynaVis, which blends natural language and dynamically synthesized UI widgets. As the user describes an editing task in natural language, DynaVis performs the edit and synthesizes a persistent widget that the user can interact with to make further modifications. Study participants (n=24) preferred DynaVis over the NLI-only interface citing ease of further edits and editing confidence due to immediate visual feedback.
- Top Cited PapersOpen Access
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-18
ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing
Evaluating outputs of large language models (LLMs) is challenging, requiring making—and making sense of—many responses. Yet tools that go beyond basic prompting tend to require knowledge of programming APIs, focus on narrow domains, or are closed-source. We present ChainForge, an open-source visual toolkit for prompt engineering and on-demand hypothesis testing of text generation LLMs. ChainForge provides a graphical interface for comparison of responses across models and prompt variations. Our system was designed to support three tasks: model selection, prompt template design, and hypothesis testing (e.g., auditing). We released ChainForge early in its development and iterated on its design with academics and online users. Through in-lab and interview studies, we find that a range of people could use ChainForge to investigate hypotheses that matter to them, including in real-world settings. We identify three modes of prompt engineering and LLM hypothesis testing: opportunistic exploration, limited evaluation, and iterative refinement.
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Top Cited PapersOpen AccessChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing
Evaluating outputs of large language models (LLMs) is challenging, requiring making—and making sense of—many responses. Yet tools that go beyond basic prompting tend to require knowledge of programming APIs, focus on narrow domains, or are closed-source. We present ChainForge, an open-source visual toolkit for prompt engineering and on-demand hypothesis testing of text generation LLMs. ChainForge provides a graphical interface for comparison of responses across models and prompt variations. Our system was designed to support three tasks: model selection, prompt template design, and hypothesis testing (e.g., auditing). We released ChainForge early in its development and iterated on its design with academics and online users. Through in-lab and interview studies, we find that a range of people could use ChainForge to investigate hypotheses that matter to them, including in real-world settings. We identify three modes of prompt engineering and LLM hypothesis testing: opportunistic exploration, limited evaluation, and iterative refinement.
- Open Access
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-3
ChainForge: An open-source visual programming environment for prompt engineering
Prompt engineering for large language models (LLMs) is a critical to effectively leverage their capabilities. However, due to the inherent stochastic and opaque nature of LLMs, prompt engineering is far from an exact science. Crafting prompts that elicit the desired responses still requires a lot of trial and error to gain a nuanced understanding of a model’s strengths and limitations for one’s specific task context and target application. To support users in sensemaking around the outputs of LLMs, we create ChainForge, an open-source visual programming environment for prompt engineering. ChainForge is publicly available, both on the web (https://chainforge.ai) and as a locally installable Python package hosted on PyPI. We detail some features of ChainForge and how we iterated the design in response to internal and external feedback.
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessChainForge: An open-source visual programming environment for prompt engineering
Prompt engineering for large language models (LLMs) is a critical to effectively leverage their capabilities. However, due to the inherent stochastic and opaque nature of LLMs, prompt engineering is far from an exact science. Crafting prompts that elicit the desired responses still requires a lot of trial and error to gain a nuanced understanding of a model’s strengths and limitations for one’s specific task context and target application. To support users in sensemaking around the outputs of LLMs, we create ChainForge, an open-source visual programming environment for prompt engineering. ChainForge is publicly available, both on the web (https://chainforge.ai) and as a locally installable Python package hosted on PyPI. We detail some features of ChainForge and how we iterated the design in response to internal and external feedback.