flâneur

Agent-native Architectures: How to Build Apps After Code Ends

every.to · 5,133 words · saved by 1 readers

This document is coauthored by Dan Shipper and Claude. It synthesizes principles from apps we've built (Reader, Anecdote) and ideas that emerged through conversation. Some patterns here Dan stands behind—they're tested or deeply considered. Others are Claude's contributions during the building process that need more validation. We've marked those with callouts. Software agents work reliably now. Claude Code demonstrated that a large language model (LLM) with access to bash and file tools, operating in a loop until an objective is achieved, can accomplish complex multi-step tasks autonomously. The surprising discovery: A really good coding agent is actually a really good general-purpose agent. The same architecture that lets Claude Code refactor a codebase can let an agent organize your files, manage your reading list, or automate your workflows. The Claude Code software development kit (SDK) makes this accessible. You can build applications where features aren't code you write—they're

Agent-native Architectures *]:block [&>*]:mt-2 [&>*]:pt-2 mt-4" > Home Newsletter Columnists Columns Podcast Products Events Guides Consulting *]:block space-y-2"> Sign in *]:block space-y-2 py-2 my-2 border-y border-dashed border-homeborder" > Search About us Careers Advertise with us The team FAQ Help center Dan Shipper Claude This document is coauthored by Dan Shipper and Claude . It synthesizes principles from apps we've built (Reader, Anecdote) and ideas that emerged through conversation. Some patterns here Dan stands behind-they're tested or deeply considered. Others are Claude's contrib

saved by

related reading