// Engineering blog
Deep dives into distributed systems and the developer tooling needed to build, test, and ship production software with AI.
105 articles · page 3 of 9
How to give your agent full context over your running application.
How it works, why AI made it urgent, and what the trade-offs are.
What goes wrong with stringly-typed Redis, and what changes when the cache boundary is typed.
What vectors, similarity search, and RAG actually do under the hood, and why PostgreSQL handles most of it.
Your tracing code is a second description of your application's structure. The compiler already has that information.
What actually happens when a request hits your application, and what a distributed trace captures at every step.
Terraform solved the right problem. AI just made it the wrong answer.
And what happens when you actually let them.
Your backend architecture determines what AI tools see, send, and write.
Send and receive emails programmatically without running a mail server.
Closing the loop between code and cloud
