Generative Conversational AI Interoperability
summary
Claims a concrete spec set — Universal API JSON envelope and manifest discovery — that lets heterogeneous assistants exchange utterances, invites and state transitions; shows a working Python sandbox (listens on port 60002) with demo agents (Cassandra, florist, post office) doing multi-agent handoffs; cites ~800–900k models on Hugging Face and widespread “open washing,” notes project joined Linux Foundation in Nov 2023, and explains use of RAG and fine‑tuning for domain specialists.
AI-written summary · about
chapters (9)
- 0:00Introduction
- 2:54AI models overview
- 6:54What is conversational AI
- 11:12Why interoperability needed
- 14:04Open Voice Interoperability
- 15:08Universal API for AI agents
- 18:21Live demo: AI interoperability
- 25:25Team, resources, contribute
- 27:28Q&A
related talks
31mGenerative Conversational AI Interoperability
42mConversational Assistants that Converse with Each Other
34mBuilding Multi-Agent Generative-AI Applications with AutoGen
10mKeynote: Next-Gen AI Applications via Multi-Agent Conversation
28mThe Put That Sh*t On Agent: Building Multi-Agent AI Systems That Actually Talk to Each Other*
26mAI powered automation & multi-agent orchestration
24mLightning Talk: Building the AIverse: Standardizing Autonomous AI Agents for a Decent...
01h 02m[Full Workshop] Building Conversational AI Agents