Peyton Montei

Coding agents help us ship fast, but they’ve introduced a new challenge: ensuring developers can understand, trust, and maintain agent-generated code.

That challenge now shows up across the software development lifecycle:

1. Context is scattered across multiple sessions. 2. Developers have more code to review and less context to review it with.
2. Code hosts face more automated activity than they were designed for.
3. Agents burn tokens just trying to understand the codebase.

Solving these problems requires a new workflow and mindset for working with agents. In this hands-on workshop, you’ll learn how to preserve context across sessions, reduce wasted tokens, and review agent-generated changes with the context you need to merge confidently.

This workshop is for engineers, tech leads, and reviewers of all experience levels who want to work more efficiently with coding agents.

Coding agents are writing code faster than ever, picking up issues and stories with growing autonomy. Yet context is fragmenting across chats, prompts, sessions, and branches, leaving agents stateless and developers without a shared understanding of intent, decisions, and learning. And the human developer still sits at the center of the pull request, reviewing code and suggestions.

It's time for a new software development lifecycle for a world of agent-to-human and agent-to-agent collaboration, one that collapses planning, coordination, design, implementation, review, and deployment into a continuous loop. And one that removes bottlenecks while preserving quality, trust, and developer happiness. Join Joseph Katsioloudes for a demo-filled talk on what this loop looks like in practice today, where it breaks, and what you can start changing in your own workflow.