Coding agents are only as effective as the context they can see—and for long-lived software, the repository is their real prompt. This practical talk explores how clear specifications, enforceable constraints, observable acceptance criteria and fast feedback loops can turn repeated AI mistakes into improvements that compound over time.

Seven months ago, our engineers said letting an AI approve pull requests was too risky. They were right, so we didn’t start there.

Instead, we built a bot for code reviews and capped it at 200-line PRs, watched every decision, and turned every mistake it made into a rule or a lint check. Then we raised the limit.

This talk covers that loop: small experiments, proof instead of promises, and a system that gets a little better every week.

You’ll leave with a playbook you can start on Monday, whatever tools your company gives you.

In this session, I’ll explore how AI-powered tooling is transforming large-scale refactoring and codebase migrations, making these complex tasks faster and more efficient. By leveraging tools like Large Language Models (LLMs), static analysis, and refactoring frameworks, we can automate repetitive code transformations, accelerate migration paths, and reduce human error. I’ll share practical examples of how we can migrate legacy systems to modern frameworks, break monolithic architectures into service-based structures, and automate large-scale code changes across thousands of files.

I’ll demonstrate how tools like OpenAI Codex, GitHub Copilot, and fine-tuned models for domain-specific transformations can assist in these processes, while still integrating with traditional migration tools and CI/CD systems. I’ll also cover the importance of developer oversight, highlighting lessons learned from real-world production rollouts and how to balance automation with manual reviews.

By the end of the talk, I want attendees to walk away with a clear understanding of how to use AI to enhance their refactoring and migration workflows, ensuring they can handle large-scale transformations while maintaining code quality, consistency, and governance.

Our coding agents are getting smarter, but the workspace we drop them into is probably not enabling them to use their full potential. The decisions, failed attempts, conventions, and product knowledge are still crucial context scattered across people’s heads, Confluence, old conversations, and forgotten pull‑request comments.

During this talk, we'll walk through the shift from the “good old” prompt engineering to agent experience, then I'll show a practical AX experiment at my current company that led to a better workspace for both agents and the people using them.