Generic AI code reviewers don't know your codebase, but manual rule-writing is tedious. Discover how to unlock an invisible asset in your existing workflow to automatically train AI reviewers on your team's exact standards, without writing a single prompt.

Most engineers think performance is about output: writing more code, delivering faster, or being more productive. In this talk, I’ll share a practical model I’ve used over the last four years that reframes performance as something more fundamental: trust. We’ll explore how trust is built in engineering teams through a simple principle: “honoring your word.” This includes not only delivering what you commit to, but also actively clarifying and managing expectations before and during execution. This perspective changes how you approach tasks, communication, and responsibility in real engineering environments.

One year of agentic development, what have we learned so far, what worked, what didn't work and what are we letting go of today? What are the things that we have been running into? I'll show some real statistics, some real lessons learned and the things that we discovered and struggled with along the way. Real data, real examples, real disasters, and I will share my ideas on where engineering teams need to start heading next.

This talk explores the architecture and implementation of OAuth-based authentication for remote-hosted MCP servers. I'll walk through the specific challenges I encountered while building an MCP server at Tigris — including managing dynamic client registrations, token lifecycle management and scope handling across distributed environments.

I'll also cover UX choices like reducing friction in the auth flow, handling token refresh gracefully, and managing session state.

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.

TC39 is working on two proposals, import defer and export defer, whose goal is to allow developers to extract better performance from native ESM, both in the browser and on the server. Let's go together through how they work, and when and where you'll be able to use them!