← back
Collaborative AI Engineering: One Dev, Two Dozen Agents, Zero Alignment — Maggie Appleton, GitHub
Takeaway
Coding agents have collapsed implementation cost so alignment must become continuous and multiplayer — not a PR-time afterthought.
Summary
- Maggie Appleton (GitHub Next) argues 'one dev + two dozen Claudes' fantasy ignores that software is a team sport — scaling individual output makes alignment worse, not better.
- Implementation is becoming a solved problem; deciding what to build is the new bottleneck, and current tools (GitHub PRs, Jira, Slack) weren't built for agentic workflows.
- With agent-speed implementation, all alignment now lands too late on the PR; planning, context, and decisions must happen continuously alongside coding.
- Demos ACE (Agent Collaboration Environment) — multiplayer Slack-like sessions backed by sandboxed micro-VMs on isolated Git branches, letting teammates jump into each other's prompting history and agent state.
agentscollaborationdeveloper-tools
Original description
Agentic engineering so far has been a solo story: one developer and a dozen agents moving at warp speed. But speed without thoughtful planning and team alignment is just wasting tokens. When everyone on a team is directing agents alone in their personal CLI tools with no shared context, you get duplicate work, conflicting changes, poorly-designed solutions, surprise features nobody else agreed to build, and everyone pulling in different directions. Serious software still requires serious collaboration. You need multiple perspectives and types of expertise to build great things. We need agentic environments where people can plan together, think critically together, and share the same context. In this talk I'll demo how we've tackled these design problems in Ace, a multiplayer agent environment from GitHub Next that uses real-time collaboration, proactive agents, and sandboxed micro VMs for rapid prototyping and exploration. Speaker info: - https://x.com/Mappletons