← All Series

AI Engineering

Essay

The Agent Control Loop — Engineering for Tolerance

Why agent reliability isn't magic model behavior — it's an environment where correctness is continuously verified. A framework for deciding when and how to delegate to AI agents.

Frederik Schubert & Yannick Augenstein
Case Study

"What Should We Work On Next?"

The story of building an 80,000-line autodiff library almost entirely through AI agents — and the verification infrastructure that made it possible.

Yannick Augenstein & Frederik Schubert