← back
Containing Agent Chaos — Solomon Hykes, Dagger
Takeaway
Coding agents need first-class containerized environments — sandboxes for execution aren't enough; the agent itself needs to develop inside the container.
Summary
- Docker co-founder Solomon Hykes (now Dagger) frames coding-agent operators as the new platform engineers — they enable agents to ship instead of shipping code themselves.
- Argues neither 'YOLO 10 agents in one repo' nor fully managed background-agent SaaS works; users want background, rails (project context/build/test/secrets), efficient stepping-in, and optionality across models/clouds.
- Dagger's answer is 'container-use': portable, isolated, customizable, multiplayer, open environments attachable to any coding agent (Claude Code, Codex, etc.) — analogous to Git worktrees but native to agents.
- Live demo of an unfinished open-source tool launching containers per agent to develop in parallel without stepping on each other.
agentscontainersdagger
Original description
AI agents promise breakthroughs but often deliver operational chaos. Building reliable, deployable systems with unpredictable LLMs feels like wrestling fog – testing outputs alone is insufficient when the underlying workflow is opaque and flaky. How do we move beyond fragile prototypes? This talk, from the creator of Docker, argues the solution lies outside the model: engineering reproducible execution workflows built on rigorous architectural discipline. Learn how containerization, applied not just to deployment but to each individual step of an agent's workflow, provides the essential isolation and environmental consistency needed. Discover how combining this granular container approach with patterns like immutable state management allows us to contain agent chaos, unlock effective testing, simplify debugging, and bring essential control and predictability back to building powerful AI agents you can actually ship with confidence. About Solomon Hykes Solomon Hykes is best known as the creator of Docker, the open-source platform that revolutionized software development and deployment through containerization. His work fundamentally changed how applications are built, shipped, and run by standardizing their execution environments. Drawing on his deep experience tackling complexity at the infrastructure level, Solomon is now Founder and CEO of Dagger, focusing on the foundational challenges of building and operating reliable, scalable AI agent systems. He is passionate about applying platform engineering principles to the emerging AI landscape, helping engineers navigate this technological shift and build more dependable systems. Recorded at the AI Engineer World's Fair in San Francisco. Stay up to date on our upcoming events and content by joining our newsletter here: https://www.ai.engineer/newsletter