Everyone's at Level 1, and it unlocks nothing
Chapter 15 - A maturity model sorted by what depends on what, not by what's cheap The Agentic Development Lifecycle - @praveen govindaraj Most teams adopting AI coding agents start by creating an AGENTS.md file. They document coding conventions, explain the architecture, and tell agents which tests to run. It's useful—but how do you know the agent actually follows those instructions? In a study…
The article argues that many teams adopting AI coding agents often focus on creating shared context files and conventions (Level 1 of a maturity model) without realizing that these steps do not necessarily lead to effective feedback loops or systematic learning. The maturity model proposed by the author consists of five levels, with Level 2 introducing blocking checks, sensors, and execution traces, and Level 3 introducing controls in response to recurring failures.
The key insight is that maturity is about which feedback loops a team can actually close, rather than simply adding more tools or documentation. The article also points out that the conventional progression of maturity steps is backwards, as some capabilities do not depend on previous ones. It suggests starting with a practical blocking check, such as a type checker, to move beyond Level 1 and begin a more systematic approach to AI-assisted development.
Brief written by urgent.news from Dev.to's own syndicated text. Machine-written — may contain errors; check the original before relying on it.
