One format jumps out as almost universally useful: Markdown with frontmatter. It’s a retread of the headers pattern we see in packets, email, and HTTP: a block of structured data, followed by free text. The combination offers something for everyone. Code can leverage the structured data, while AI gets natural language. This feels like the closest thing to an AI-native data format. I’ve been experimenting with variations of the frontmatter pattern in agent harnesses, and not just limited to Markdown files. In SQL, for example, you can leverage jsonb features to the same effect, with something like…