Markdown Is Becoming the Application Layer of AI Apps

Most AI apps started from a reasonable fear. Models were unpredictable, prompts were fragile, and nobody wanted production behavior living inside a magic paragraph. So we did what engineers usually do when a system feels unsafe: we wrapped it in code.We built chains, graphs, routers, callback handlers, retrievers, memory abstractions, evaluation layers, and handoff nodes. Some of that was necessary. If an AI system moves money, changes permissions, updates customer data, deploys software, or touches production infrastructure, the hard boundaries belong in code. Nobody should trust a paragraph in a Markdown file to enforce access control.But we took that instinct too far. A lot of AI application behavior is not a hard boundary. It is procedure, policy, tone, source discipline, review expectations, escalation rules, examples, and handoff shape. Those are the parts of a workflow that change often, depend on domain judgment, and are usually maintained by people who should not have to…