vibe-qc: expert-directed agentic engineering for scientific software development

About the paper

Generative AI can implement scientific software, but useful development also needs executable comparisons, inspectable results and a record of scientific decisions. This case study describes how vibe-qc is developed this way. The expert sets the physical problem, selects diagnostic controls and interprets the evidence. AI agents implement and execute those tasks. The retained development records keep failed attempts and separate changes in physical conventions from implementation errors. Formaldehyde, diamond and lithium hydride serve as worked examples, with vibe-scheduler managing the calculations and vibe-viewer with QVF for inspection and reproducible figures. The paper does not claim autonomous scientific judgment or a measured productivity gain.

@misc{vibe-qc-agentic-2026,
  title = {{vibe-qc: expert-directed agentic engineering for scientific software development}},
  author = {Peintinger, Michael F.},
  year = {2026},
  doi = {10.26434/chemrxiv.15011503/v1},
  url = {https://doi.org/10.26434/chemrxiv.15011503/v1},
  howpublished = {ChemRxiv},
  note = {Preprint, version 1}
}