Twelve Labs unveils a video intelligence stack built around search, memory and agentic workflows
qdrant_engine · x · 2026-07-29
Twelve Labs explains why video cannot be treated as just a bag of frames or a timestamped transcript: motion, causality, and temporal progression matter. At Vector Space Day SF, James Le described three failure modes in video systems — wrong context, wrong memory, and wrong reasoning — and introduced a stack built around Marengo for video search, Pegasus for structured answers, and Jockey as an agentic framework and memory layer, with Qdrant underneath for storage and retrieval.
More from coding & agent
- NewMax wires Grok into a multi-agent workflow for overseas ops — huangyun_122 · 2026-07-29
- Borrowing from Antiquity: New Framework Tackles 'Silent Failures' in Multi-Agent Chains — alizahidrajaa · 2026-07-29
- ISNAD brings claim-level provenance to multi-agent LLM chains — alizahidrajaa · 2026-07-29
- Claude Code’s 32k-token prompt is why some developers prefer a 1k-token harness — pauliusztin · 2026-07-29
- A multi-channel AI reply stack runs into Twilio’s $120 SMS subscription cost — Cuncirps · 2026-07-29
- Hobbyists are debating how to build a private personal AI operating system — DoctorTruthSeeker · 2026-07-29