Agentic AI-assisted coding offers a unique opportunity to instill epistemic grounding during software development

2026-04-23

AI Summary

This work addresses the challenge that AI-generated code often compromises scientific or engineering validity due to insufficient integration of domain-specific knowledge, particularly when used by non-expert practitioners who struggle to ensure correctness. To mitigate this, the authors propose embedding community-governed, domain-specific cognitive grounding documents—termed GROUNDING.md—into the AI agent’s programming workflow. By enforcing hard constraints and standardized parameter conventions during code generation, this approach systematically upholds scientific validity and domain best practices. The method innovatively achieves cross-contextual alignment of domain knowledge, substantially enhancing the reliability and trustworthiness of code produced by non-experts, thereby fostering greater confidence among developers, reviewers, and end users in AI-generated software.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Application Domains: Software Engineering

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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 GROUNDING.md, 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, 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. Undoubtedly it is easier to have agentic AIs adhere to guidelines than humans, and this opportunity allows for organizations to develop epistemic grounding documents in such a way as to keep domain experts in the loop in a future of democratized generation of bespoke software solutions.

Problem

• Agentic AI
• epistemic grounding
• software development
• scientific correctness
• domain-specific constraints

Innovation

• Agentic AI
• Epistemic grounding
• GROUNDING.md
• Hard Constraints
• AI-assisted coding