We the Agents: A Constitution for the Agentic SDLC

Every process a team follows is a scar — an inherited response to some past wound. We build process to compensate for how people work: we forget, we tire, we leave and take hard-won knowledge with us. But when a new kind of actor — an agentic AI — starts working inside your SDLC, "how do we carry these processes forward?" is the wrong question. The right one is why does each process exist, and does that reason still hold? This talk uses a real engineering constitution — a system where every rule is codified as a numbered, citable law that has to carry its own rationale — as the worked example. We'll walk through people, process, tooling, and scaling: why we build process at all, how we interrogated each one from first principles instead of inheriting it on habit, and what it took to make both humans and agents actually honor the rules that earned their place. It's not an argument for fewer guardrails or burning it all down — it's an argument for reasoning from first principles rather than tradition, drawn from real experience and real scars. You'll leave questioning your own processes, not adopting mine.