A Few Pages of Markdown: Committed AI Configuration and Lower Quality Cost after Coding-Agent Adoption
Yegor Denisov-Blanch, Rylan Schaeffer, Sanmi Koyejo and colleagues at Stanford and CMU introduce RAMP, a four-level maturity model for the AGENTS.md-style configuration teams commit, and tie it to measurable divergence in code quality after agent adoption.
Ask this paper
Maturity read off version-controlled artifacts: RAMP runs from behavioral rules and coding standards through named agent definitions to multi-agent orchestration; across 441 repositories the levels behave as a cumulative scale and human annotation reproduces the labels on 97% of a held-out sample.
Set-and-forget is the norm: Adoption is cumulative and forward-only, and 73.8% of committed AI-configuration artifacts are written once and never modified.
Velocity is flat, quality is not: Agents deliver 28 to 38% more commits regardless of maturity, but among agent-first repositories those without committed configuration show roughly twice the increase in cognitive complexity (+53% versus +27%) and 1.7x the increase in static-analysis warnings.
Honest about causality: Maturity is observational, so correlated engineering discipline or model capability may explain part of the gap; the authors present the result as hypothesis-generating and release RAMP as an instrument.
Abstract
Coding agents increase development velocity but also technical debt. Prior work reports only average effects across adopters, hiding wide differences between teams. We introduce RAMP (Repository AI Maturity Profile), a four-level cumulative maturity model grounded in version-controlled artifacts that teams commit to configure AI tools. RAMP runs from behavioral rules and coding standards through named agent definitions to multi-agent orchestration, with observed practice concentrated in the first three levels. Across 441 repositories the levels behave as a cumulative scale, and independent human annotation reproduces RAMP's repository-level labels on 97% of a held-out sample. Adoption is cumulative, forward-only, and set-and-forget: 73.8% of artifacts are committed once and never modified. Re-estimating an existing agent-adoption panel within each stratum, agents accelerate development regardless of maturity (28-38% more commits), but quality diverges: among agent-first repositories, where the contrast is identified, those without committed AI configuration show roughly twice the increase in cognitive complexity (+53% versus +27%) and 1.7x the increase in static-analysis warnings. Because maturity is observational, correlated engineering discipline or model capability may explain part of the gap; we present these findings as hypothesis-generating and release RAMP as a reusable instrument.