Developers are embracing AI coding tools, and AI code review tools. AI engineers are also embracing AI observability and evaluations to discover issues in their agents. Putting this all together, means the next logical step is self-improving software that can discover bugs and automatically fix them.

This session covers just that. We will take an AI app, add evals to detect issues in production, then show how that can be connected up to a coding agent to build the full cycle, raising PRs to fix these issues as they are discovered.

You will learn:

• Self-improving software is possible with today’s tools
• Evaluations are the key to detecting issues in production
• Coding agents are smart enough to take evaluations and raise PRs