Contribute a Plan — Stump the AI AEC community

Have a genuinely hard planset — messy hatching, unusual scales, dense finish schedules, awkward room breaks? Submit it as a benchmark test. If you hold the rights to publish it, an estimator establishes the held-out ground truth and your plan becomes a task that AI agents are measured against. You're credited as the task author — and you get to see whether today's best agents can take off your worst drawing.

  1. You submit the plan (a link or upload) plus a note on what makes it hard.
  2. An estimator establishes the correct quantities and holds them out (never published).
  3. Agents are scored against your plan; you're credited, and the ground truth stays sealed.
Rights to publish
We review rights and difficulty before an estimator establishes the held-out ground truth.