Agile for Agents -- Managing Robots The Way We Manage Humans.

AI coding agents are powerful — and chaotic. They forget everything between sessions, can't coordinate across a team, and have no concept of a project's history or direction. Sound familiar? We've solved this before.

This session introduces the Agent Management System (AMS): a lightweight, tool-agnostic approach to bringing Agile-style discipline to AI agent workflows. Borrowing from Scrum, Kanban, and 70 years of managing human programmers, AMS uses plain markdown files to give agents persistent memory, project context, and structured handoffs — without vendor lock-in or complex tooling.

We'll cover:

• The core Agent Handoff Protocol: how sessions start, run, and end
• The .ams/ directory convention and how it stays out of developers' way
• Tool-specific integrations (Claude Code plugin and more)
• How teams — not just solo developers — can coordinate agents the way they coordinate humans

Whether you're just starting to use AI coding tools or already managing a fleet of agents, you'll leave with a working protocol you can drop into any project today.