// Engineering blog
Deep dives into distributed systems and the developer tooling needed to build, test, and ship production software with AI.
22 articles in AI · page 1 of 2
Give coding agents an isolated sandbox with a complete backend inside it — and keep both in your own cloud.
Let your coding agents build and verify against real infrastructure, inside a sandbox.
Keep the agent session behind every Encore change, directly in Git.
Now a Cursor agent can provision your cloud infrastructure from the same code it writes, on your own AWS or GCP.
An agent only fixes what it can see before it stops, and a compile error is the one signal that always lands in time.
We set out to run one benchmark across five TypeScript backend frameworks. Reading the diffs sent us into two more runs, and the picture changed each time.
The interface you give AI agents determines what they can break.
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 vectors, similarity search, and RAG actually do under the hood, and why PostgreSQL handles most of it.
Terraform solved the right problem. AI just made it the wrong answer.
And what happens when you actually let them.
