tokens&
BrowseFor enterprises
tokens&

Find tools, check provider offers, save a build plan, and share your work when you’re ready.

For buildersFor enterprises

For builders

  • Product launches
  • Builder projects
  • Startup credits and perks
  • Agent Skills
  • Published agents
  • API and agent docs
  • Publish a project

For enterprises

  • Start free company workspace
  • Submit a tool, product, or perk

Community

  • Community
  • Newsletter
  • Events
Xin

© 2026 tokensand, LLC. All rights reserved.

  • Terms
  • Privacy
  • Security
  • Data Processing
  • Status
  1. Hackathon
  2. Project gallery
  3. Understudy
Touko Ursinabout 1 month agoContributorJudging locked: Event build

Understudy

Understudy turns video nobody watches into a live coach. It learns a task from expert recordings, then watches a new person on camera, corrects mistakes out loud with the expert clip for that step, and scores the attempt.

Community votes recognize the build and do not affect official judging.

Review the project

Start with the source code, then open the demo or video if available.

View GitHub repository
Visit project websiteWatch demo videoProject gallery
Demo video
Watch demo video
Project description
Inspiration: Companies record how their best people work, and almost nobody watches it. New hires still learn by shadowing, and mistakes get caught late. We wanted that unwatched video to coach the next person live. How each sponsor is used: - VAST Data (VAST AI OS): stores the 2,352-clip archive and our own recorded takes in S3. We segmented, captioned, embedded and inserted our takes into the team VastDB ourselves (2,409 rows). VAST semantic search powers "Ask the archive". - NVIDIA Cosmos Reason: live scene reading about once a second during coaching, plus clip captions and task recognition. - NVIDIA Cosmos Embed: vectors for the archive map, task recognition and search. - CoreWeave: GPUs serving all the Cosmos and YOLO models. - Weights & Biases: serverless inference. Llama 3.3 70B writes the score feedback and names the map clusters, DeepSeek V4 Flash is the fallback judge, and Weave traces every live check. - Cursor / SpaceXAI: Used for creating the project
Project links
  • GitHub repository
  • Project website
  • Demo video
Tools used
  • VAST Data logoVAST Data

    Provider website

    Sign in to visit
Builder
TU

Touko Ursin

Builder on tokens&

  • SpaceXAI (Cursor) logoSpaceXAI (Cursor)

    Event resource · Sign up for Cursor

    Sign in to visit
  • CoreWeave (Weights & Biases) logoCoreWeave (Weights & Biases)

    Event resource · Create a Weights & Biases account

    Sign in to visit
  • NVIDIA logoNVIDIA

    Provider website

    Sign in to visit