TableTalk: Scaffolding Spreadsheet Development with a Language Agent
Abstract
Spreadsheet programming is challenging. Programmers use spreadsheet programming knowledge (e.g., formulas) and problem-solving skills to combine actions into complex tasks. Advancements in large language models have introduced language agents that observe, plan, and perform tasks, showing promise for spreadsheet creation. We present TableTalk, a spreadsheet programming agent embodying three design principles -- scaffolding, flexibility, and incrementality -- derived from studies with seven spreadsheet programmers and 85 Excel templates. TableTalk guides programmers through structured plans based on professional workflows, generating three potential next steps to adapt plans to programmer needs. It uses pre-defined tools to generate spreadsheet components and incrementally build spreadsheets. In a study with 20 programmers, TableTalk produced higher-quality spreadsheets 2.3 times more likely to be preferred than the baseline. It reduced cognitive load and thinking time by 12.6%. From this, we derive design guidelines for agentic spreadsheet programming tools and discuss implications on spreadsheet programming, end-user programming, AI-assisted programming, and human-agent collaboration.
Cite
@article{arxiv.2502.09787,
title = {TableTalk: Scaffolding Spreadsheet Development with a Language Agent},
author = {Jenny T. Liang and Aayush Kumar and Yasharth Bajpai and Sumit Gulwani and Vu Le and Chris Parnin and Arjun Radhakrishna and Ashish Tiwari and Emerson Murphy-Hill and Guastavo Soares},
journal= {arXiv preprint arXiv:2502.09787},
year = {2025}
}