Ex-Meta CV researcher builds AdaL v2, a chat-driven video agent harness for GTM
Scobleizer · x · 2026-11-12
A former Meta AI computer vision researcher spent two years building AdaL v2, a video-first agent harness aimed at GTM workflows. His thesis: coding agents made building easy, so launching is now 10× more competitive — and video is the next frontier after code.
Unlike adding plugins such as HyperFrames or Higgsfield MCPs inside Claude Code, AdaL v2 is a full coding agent harness natively optimized for video, with its own desktop app:
- Generate and edit video, images, and audio entirely through chat
- Version control to explore ideas and reproduce any asset from past versions
- Multiple videos per project, from the main launch film to per-platform formats
The author claims 10× more control (you direct the whole production visually), 10× faster iteration, and 10× easier use compared to plugin-based approaches.
More from coding & agent
- Hackathon project lets AI agents spend company money, but only within CFO-approved limits — kleffew94 · 2026-11-12
- In real orgs the model is rarely the problem — the context it gets is, says Salesforce engineer — msrivastav13 · 2026-11-12
- Salesforce Winter '27 adds AiAgentDefinition metadata for versioned agent deployments — msrivastav13 · 2026-11-12
- Solo dev builds zombie horde level with Tripo P2.0, Fable and new Kaigen engine — gdechichi · 2026-11-12
- United Airlines to Ban Personal AI Agents From Booking Flights for Customers — Polymarket · 2026-11-12
- Agentic Search explained: a 4-search loop costs about 5x one search — and queries leak to more companies — adnan_hashmi · 2026-11-12