Agentic AI-assisted coding offers a unique opportunity to instill epistemic grounding during software development
Magnus Palmblad, Jared M. Ragland, Benjamin A. Neely

TL;DR
This paper proposes GROUNDING.md, a community-driven epistemic grounding document for AI-assisted coding, to ensure scientific correctness and adherence to best practices in software development.
Contribution
It introduces a novel epistemic grounding framework using mass spectrometry-based proteomics as an example, enabling AI to enforce validity constraints in software creation.
Findings
Grounding document encodes non-negotiable validity invariants.
Overrides all other contexts to enforce scientific correctness.
Empowers non-domain experts to generate validated code and tools.
Abstract
The capabilities of AI-assisted coding are progressing at 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 document, such as project and method-scoped documents. Here we propose GROUNDINGmd, a community-governed, field-scoped epistemic grounding document, using mass spectrometry-based proteomics as an example. This explicit field-scoped grounding document encodes Hard Constraints (non-negotiable validity invariants empirically required for scientific correctness) and Convention Parameters (community-agreed defaults) that override all other contexts to enforce validity, regardless of what the user prompts. In practice, this will empower a non-domain expert to generate code,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
