← Latest products

NUA an agent that tests for product correctness

Nua builds video decision models. Artificer, our 4B robotics model, judges task success and progress from video at frontier level, for robot evaluation, data labelling and VLA training. Backed by Y Combinator. We’ve been using background Claude loops a lot recently, and we would wake up to PRs that didn’t solve the problem we wanted, made on assumptions that were wrong.

Visit trynua.devexternal site

Reactions (1)

Similar products

by description similarity

  1. Frontier robotics task evaluation in 4B parameters

    Hacker News11 pts

  2. GTM infrastructure for agent builders to scale and monetize.

    Product Hunt122 votes

  3. Spec27

    spec27.ai

    Spec-driven validation for AI agents

    Hacker News13 pts

  4. NuPlay

    nuplay.ai

    AI transformation, run on one self-improving platform

    Product Hunt112 votes

  5. Guardians

    github.com

    Verify tool-using agent workflows before execution

    Hacker News8 pts