Agent-Native Application Architecture Principles

we're only building agent-native apps @every now here's what that means: traditional software architecture: you write code that defines what happens. The computer executes your instructions. agent-native architecture: you define outcomes in natural language. the agent figures out how to achieve them using tools. in an agent-native world, features are prompts not code. good agent-native architectures have the following characteristics: - parity. anything the user can do in the app, the agent can do. - granularity. features are prompts, not tools. the agent has access to tools that are more atomic than features so a few tool calls are composed into a single feature. - composability. this enables composability: the agent can combine tool calls in new ways easily. this allows developers to move faster—and allows users to customize the application more easily with prompts. all of the above enables emergent capability in your app—it can do things you didn't plan for. this allows you to discover latent demand from your users that inform your roadmap. this a core way that @bcherny builds features in Claude Code—which is architected with all of the above characteristics