Search papers, labs, and topics across Lattice.
This paper introduces Model-Based Agentic Software Engineering (MAGE), a framework designed to enhance the reliability and transparency of coding agents in software development. By addressing both representation and authority challenges, MAGE externalizes essential engineering knowledge and establishes governance through constraints and validation mechanisms. The framework was refined through a longitudinal case study and six industrial accounts, demonstrating its potential to transform commodity intelligence into sustainable engineering practices.
MAGE transforms how coding agents operate by externalizing engineering intent and establishing governance, paving the way for more reliable software development.
Coding agents increase implementation capacity without automatically making project intent, system structure, or acceptance evidence explicit. As implementation becomes abundant relative to engineering judgment, the scarce work shifts toward choosing useful abstractions, producing evidence, and determining which obligations govern acceptance. Existing workflows address parts of this gap through larger prompts, repository retrieval, or perchange review, but still require agents and engineers to reconstruct consequential properties. As an alternative, we present Model-Based Agentic Software Engineering (MAGE). MAGE is a framework and a theory for building trustworthy autonomy from commodity intelligence. MAGE addresses a representation problem and an authority problem: it externalizes the smallest purposeful representation needed to answer an engineering question, then gives settled obligations proportionate authority through constraints, sensors, validators, and gates. It keeps uncertain intent open and turns recurring reconstruction and judgment into durable engineering structure that later work can inherit. We developed MAGE from a longitudinal case and refined it through six independently reported industrial accounts. Across these sources, MAGE explains how externalized knowledge, bounded action, independent evaluation, and retained human authority can compose into a governed engineering environment, and proposes tests of when that environment turns commodity intelligence into durable engineering progress.
