Metraipolis › archive › dc_ce57536f64bd
Tracybot: Preserving Developer Intent by Tracing Agent-Generated Code to Prompts — arXiv:2611.09395
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.09395
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-09T22:40:59.144Z
- SHA-256 of the archived text
260f1b5168458581146f87d70b6edcf854642f2424420ec9ebeb15c778cf39fa- Stable URL of this page
https://metraipolis.com/documento/dc_ce57536f64bd
How to cite
Tracybot: Preserving Developer Intent by Tracing Agent-Generated Code to Prompts — arXiv:2611.09395 — arXiv (en), https://arxiv.org/abs/2611.09395 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ce57536f64bd (Metraipolis archive dc_ce57536f64bd, sha256 260f1b5168458581146f87d70b6edcf854642f2424420ec9ebeb15c778cf39fa)
BibTeX
@misc{dcce57536f64bd,
title = {Tracybot: Preserving Developer Intent by Tracing Agent-Generated Code to Prompts — arXiv:2611.09395},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.09395},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ce57536f64bd; sha256 260f1b5168458581146f87d70b6edcf854642f2424420ec9ebeb15c778cf39fa},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09395. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) are now widely used in software development, and LLM-based coding agents are given increasing autonomy. With coding agents, many design decisions are made in the conversation between the developer and the agent. Typically, the developer starts a conversation with an agent and states their intent, the agent proposes options if needed, and the developer plans the change accordingly. Then, the resulting code is committed. However, in such scenarios, the decisions and the intent behind the changes remain in the conversation, with no link to the code they produced. In this paper, we present Tracybot, an open-source tool that integrates with VS Code, Git, and coding agents to keep track of relevant conversations in an LLM-assisted development process. Tracybot captures each change as a Tasklet which consists of optional planning prompts used to plan a change, together with a build prompt that produces it. Tracybot has two main features: (i) it maps line-level code changes made by coding agents to the Tasklets that produced them, and (ii) it allows the developer to export a Tasklet as a decision record when needed, for example when the decision concerns the architecture of the project. We developed the tool over two iterations of a design science study, while focusing the evaluation on the usability and user-friendliness of the tool. In a focus group (7 participants) and a survey (24 participants), we found that Tracybot was perceived as useful for activities like code review, and most participants found our Tasklet design and presentation to be a clear way to represent the developer's intent. Tool: this https URL . Video: this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.HC, nuovi lavori del giorno). Categorie arXiv: Software Engineering (cs.SE) ; Human-Computer Interaction (cs.HC). Pagina del lavoro: https://arxiv.org/abs/2611.09395 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-09T22:33:32.095Z dalla pagina https://arxiv.org/list/cs.HC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).