My AI coding agent agrees with me a lot. It agrees when I’m right. It agrees when I’m wrong. It agrees while deciding on its own to remove validation logic, rewrite business rules, and confidently explain why this is an improvement.

This is what coding with AI agents looks like when context lives in the developer’s head rather than in the system.

This talk looks at how developers can make agents less agreeable and more effective by treating shared context as an engineering problem. We’ll show how prompts, rules, and other forms of system context and shared knowledge can be packaged into explicit, reusable units instead of living in ad hoc conversations. More importantly, we’ll look at how that context can be shared and reused consistently across tools and teams, using familiar distribution ideas borrowed from the way we already share libraries via registries and repositories.

On top of that foundation, we’ll cover when deterministic scripts are the better choice and how to embed them into agent workflows, how to assess prompt quality using concrete signals instead of “trust me, bro,” and how guardrails like tests and structure help agents fail loudly instead of silently drifting.

If your AI keeps agreeing with you even when it’s doing the wrong thing, you’re absolutely right: this talk is for you.

Many AI talks focus on what agents can do. This talk focuses on what they should be allowed to do, and how developers can enforce that through shared context, structure, and guardrails. It offers a grounded, engineering-first perspective that complements more exploratory or model-focused sessions.