Philippe Martin presents the BMAD method (Breakthrough Method for Agile AI-Driven Development) as an indispensable "urban planning blueprint" for structuring the use of agentic AI within the software development lifecycle, as opposed to "vibe coding," which generates explosive technical debt.
The problem: since the arrival of LLMs, many teams have been "coding by feel" with AI — prompting, retrieving code, manual adjustment, starting over. In the short term, this is exhilarating. In the long term, it is like letting each developer negotiate alone with a contractor: extensions everywhere, no overall plan, an electrical network ready to catch fire.
The BMAD response: organize agents IA as a disciplined construction crew. Each agent plays the role of a specialized foreman: one agent clarifies the requirement and produces a genuine specification rather than a vague prompt, an architect proposes options aligned with standards, "craftsmen" generate code, tests and documentation, and controllers track defects and regressions. The human remains chief architect and project owner: defining the vision, the non-negotiable constraints, and deciding the structuring decisions.
Integration into the SDLC: the author proposes three insertion zones. Upstream, agents transform a business intent into a structured PRD much more quickly. In the middle, they propose architectures and generate code within a defined framework — "AI is not asked to 'write me an app,' it is asked to 'implement this module within this precise design.'" Downstream, agents monitor, analyze logs, and feed a prioritized technical debt backlog.
Legacy and technical debt: BMAD pushes toward addressing the structure rather than the paint layer. Agents map the code, identify risk areas, and propose progressive refactorings. Systematic generation of tests and documentation helps reduce the backlog.
Evolution of roles: the autopilot analogy in aviation illustrates the transformation — the pilot has not disappeared, but their job has changed. Developers become solution designers and demanding reviewers, architects orchestrate a system in which enterprise constraints are injected into the agents, and managers learn to frame the problem and evaluate the value produced by the hybrid chain.
Recommendations: start with the rules of the game before the tools, choose concrete pilot cases, measure and communicate the results, and accept that the framework will evolve — just as a good urban planning blueprint allows a city to be renovated without razing everything each time.