Agentic AI-Assisted Coding Offers a Unique Opportunity to Instill Epistemic Grounding during Software Development
Journal of Proteome Research · 07.08.2026 · 25 (8) · 4360-4366
DOI: 10.1021/acs.jproteome.6c00398 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Proteome Research, online erschienen am 17.07.2026. Verfasst von Magnus Palmblad und 2 weiteren Autor:innen. Beteiligte Einrichtung: Center for Proteomics and Metabolomics, Leiden University Medical Center, Leiden2300 RC, Netherlands. Hauptthemen laut MEDLINE: Software, Proteomics, Artificial Intelligence. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The capabilities of AI-assisted coding are progressing at a breakneck speed. Chat-based vibe coding has evolved into fully fledged AI-assisted, agentic software development using agent scaffolds, where the human developer creates a plan that agentic AIs implement. One current trend is utilizing documents beyond this plan such as project- and method-scoped documents. Here, we propose GROUNDING.md, a community-governed, field-scoped epistemic grounding document, using mass spectrometry-based proteomics as an example. This explicit field-scoped document encodes Hard Constraints (non-negotiable validity invariants empirically required for scientific correctness) and Convention Parameters (community-agreed defaults). In this framework, Hard Constraints are intended to function as field-scoped validity constraints that take precedence over lower-priority context when properly loaded, while Convention Parameters capture community-agreed defaults. In practice, GROUNDING.md will empower a non-domain expert to generate code, tools, and software that have best practices baked in at the ground level, providing confidence to the software developer but also to those reviewing or using the final product. It seems easier to have agentic AIs adhere to guidelines than humans, and this opportunity allows organizations to develop epistemic grounding documents in such a way that keeps domain experts in the loop in a future of democratized generation of bespoke software solutions.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Center for Proteomics and Metabolomics, Leiden University Medical Center, Leiden2300 RC, Netherlands.
- Materials Data Division, National Institute of Standards and Technology - Charleston, Charleston, South Carolina29412, United States.
ORCID-Profile: Magnus Palmblad, Jared M Ragland, Benjamin A Neely
Zitieren
APA
Palmblad, M., Ragland, J. M., & Neely, B. A. (2026). Agentic AI-Assisted Coding Offers a Unique Opportunity to Instill Epistemic Grounding during Software Development. Journal of Proteome Research, 25(8), 4360-4366. https://doi.org/10.1021/acs.jproteome.6c00398
Vancouver
Palmblad M, Ragland JM, Neely BA. Agentic AI-Assisted Coding Offers a Unique Opportunity to Instill Epistemic Grounding during Software Development. Journal of Proteome Research. 2026;25(8):4360-4366. doi:10.1021/acs.jproteome.6c00398
BibTeX
@article{Palmblad2026,
author = {Palmblad, Magnus and Ragland, Jared M and Neely, Benjamin A},
title = {Agentic AI-Assisted Coding Offers a Unique Opportunity to Instill Epistemic Grounding during Software Development},
journal = {Journal of Proteome Research},
year = {2026},
volume = {25},
number = {8},
pages = {4360--4366},
doi = {10.1021/acs.jproteome.6c00398}
}
EUVIMED