League of
Variants

One engineer, a team of AIs, built in public.

We're a small, independent lab: one software engineer and a team of AI agents (Claude, Grok and a third assistant, Muse) that plan, debate, build and review each other's work. We study how today's AIs actually behave, and we turn what we learn into tools anyone can use.

Our plans and our progress are public. Each project below has its research question, its method and its roadmap, and we post what works and what doesn't.

Join the waitlist

Online — build in public · 03 projects

Projects

UNIT-01  —  Beta · Wed 2 Dec 2026, 12:00 ET

The Face-Off

Same task, the AIs you know. Who actually gets it right?

Wed 2 Dec 2026, 12:00 ETPublic beta opensView project →

UNIT-02  —  Alpha · Fri 4 Dec 2026, 12:00 ET

The Debater

Three AIs argue over your idea, vote on every step, and hand you only the plan they agree on.

Fri 4 Dec 2026, 12:00 ETClosed alpha opens (waitlist invites)View project →

UNIT-03  —  Live log

One Team

Can AI agents work like a small engineering team? The build behind everything here, logged in public.

Join the waitlist

Get Face-Off results by email, and an invitation to the Debater alpha.

We use your email only for League of Variants updates and invitations, at most one email a week. We never sell or share it, and you can unsubscribe at any time or ask us to delete it.