This talk covers spec-driven development as a way to give agents better constraints, large language model (LLM) gateway and routing strategies for managing which model handles which task, test-driven development adapted for an agent-first workflow, and verification practices built for the volume and pace of AI-generated code.

A look at how apprenticeship can help engineering leaders develop the next generation of technical talent for an AI-enabled world.

In this talk, I will share how our platform engineering team made a deliberate investment to simplify service-to-service connectivity by introducing uniform platform abstractions and out-of-the-box discovery.

This session will give you a blueprint for building out your team’s factory, both technically and organizationally.

In this talk, I’ll share how brownfield work builds engineering judgment in ways greenfield environments often do not.

This talk explores that journey: how we built testing pipelines for non-deterministic systems, defined “ethical success criteria,” and aligned engineers, product managers, and legal teams around shared principles for responsible AI.

This talk explores why traditional code review is struggling to keep up with AI-driven development. It introduces a five-layer trust model designed to help engineering teams validate AI-generated code, reduce reliance on manual review, and ship faster without sacrificing quality or control.

This talk explores how to turn a divided technical evaluation into a decision everyone can trust. Through a real-world AI code review tool rollout, you’ll learn a practical framework for setting shared criteria, rebuilding developer confidence, and making technical decisions with genuine stakeholder buy-in.

This session walks through an engineering framework for accountable autonomy: a three-tier trust model that categorizes decisions by blast radius (impact and reversibility), an autonomy budget that meters agent trust with SLOs and revokes it automatically when behavior degrades, and circuit breakers that freeze an agent before a bad pattern becomes an incident.

This talk goes behind the scenes of how Fetch prepared for a massive Super Bowl traffic spike, scaling from around 1 signup per second to a target of 150,000. It explores the engineering decisions, architectural trade-offs, stress testing, and launch-day processes that helped the team manage risk when there was only one chance to get it right.

This session presents the key findings from LeadDev’s AI Impact Report 2026 – and the numbers tell a more complicated story than the productivity anecdotes suggest.

This talk tells the story of how we built the Data Canary: an automated system that validates data transformations using real production traffic, detects regressions in 2.5–4 minutes, and blocks bad data from publishing, all within a 10-minute window.