Understanding Prompt Programming Tasks and Questions
Not on the map. Why?
Abstract (arXiv)
Prompting foundation models (FMs) like large language models (LLMs) have enabled new AI-powered software features (e.g., text summarization) that previously were only possible by fine-tuning FMs. Now, developers are embedding prompts in software, known as prompt programs. The process of prompt programming requires the developer to make many changes to their prompt. Yet, the questions developers ask to update their prompt is unknown, despite the answers to these questions affecting how developers plan their changes. With the growing number of research and commercial prompt programming tools, it is unclear whether prompt programmers' needs are being adequately addressed. We address these challenges by developing a taxonomy of 25 tasks prompt programmers do and 51 questions they ask, measuring the importance of each task and question. We interview 16 prompt programmers, observe 8 developers make prompt changes, and survey 50 developers. We then compare the taxonomy with 48 research and commercial tools. We find that prompt programming is not well-supported: all tasks are done manually, and 16 of the 51 questions -- including a majority of the most important ones -- remain unanswered. Based on this, we outline important opportunities for prompt programming tools.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 22 of its 65 references that are in the map. First posted on arXiv 23 Jul 2025.
Builds on
22 of 65 references.
References · 22
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2022PromptChainer: Chaining Large Language Model Prompts through Visual Programmingcited by 134
- 2023EvalLM: Interactive Evaluation of Large Language Model Prompts on User-Defined Criteriacited by 73
- 2022Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Modelscited by 70
- 2023Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language Modelscited by 67
- 2023Graphologue: Exploring Large Language Model Responses with Interactive Diagramscited by 65
- 2024PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinementcited by 61
- 2023Prompt Engineering a Prompt Engineercited by 53
- 2024"We Need Structured Output": Towards User-centered Constraints on Large Language Model Outputcited by 46
- 2024Supporting Sensemaking of Large Language Model Outputs at Scalecited by 26
- 2023A Meta-Summary of Challenges in Building Products with ML Components -- Collecting Experiences from 4758+ Practitionerscited by 22
- 2024Prompts Are Programs Too! Understanding How Developers Build Software Containing Promptscited by 19
10 more
- 2025From Prompts to Templates: A Systematic Prompt Template Analysis for Real-world LLMappscited by 19
- 2023Building Your Own Product Copilot: Challenges, Opportunities, and Needscited by 17
- 2023CoPrompt: Supporting Prompt Sharing and Referring in Collaborative Natural Language Programmingcited by 16
- 2024Prompting in the Wild: An Empirical Study of Prompt Evolution in Software Repositoriescited by 16
- 2023WorldSmith: Iterative and Expressive Prompting for World Building with a Generative AIcited by 13
- 2022Understanding Skills for OSS Communities on GitHubcited by 9
- 2024PromptHive: Bringing Subject Matter Experts Back to the Forefront with Collaborative Prompt Engineering for Educational Content Creationcited by 9
- 2024CoPrompter: User-Centric Evaluation of LLM Instruction Alignment for Improved Prompt Engineeringcited by 7
- 2021Leaving My Fingerprints: Motivations and Challenges of Contributing to OSS for Social Goodcited by 3
- 2025Composable Prompting Workspaces for Creative Writing: Exploration and Iteration Using Dynamic Widgetscited by 3
Built on by
Citing papers per year: 2025: 1.
1 paper.