Omnigent: Composition, Control, and Collaboration for AI Agents
About this episode
Denny Lee discusses the evolution of AI agents and the introduction of Omnigent, a meta-harness for AI collaboration.
Denny Lee is PM Director, Startups & Ecosystem at Databricks, a longtime Apache Spark, MLflow, and Delta Lake contributor — and one of the people behind Omnigent, the open-source meta-harness Databricks just released under Apache 2.0. He joins Demetrios to explain why the industry is moving from models to harnesses to meta-harnesses, why token spend is replaying the CapEx-to-OpEx shift all over again, and why he's using debating AI agents to plan a matcha farm in Taiwan. In this episode: 🍵 Agents as research partners — Denny uses dueling agents to scout matcha-growing regions in Taiwan, down to soil pH, elevation, and processing infrastructure 🥊 Why agents should debate each other — letting two models argue surfaces the questions you didn't know to ask 🔱 Forking conversations — the missing UX pattern: branch a session, keep the shared context, explore two threads in parallel 🧠 The meta-harness layer — how Omnigent sits above Claude Code, Codex, Pi, and custom agents so models and harnesses become hot-swappable parts 👥 The two-pizza rule for agents — military span-of-control logic says you can manage 5–7 agents before you lose the thread 💸 Tokenomics is the new DevOps —…
More episodes of MLOps.community
- The Creator of FastMCP Explains the Future of MCP
- What Happens When Every Developer Has 20 AI Agents?
- AI Agents Should Be Treated Like Hackers
- Developers May Stop Depending on Libraries
- 10 Cities. 4 Countries. One Unexpected MCP Lesson.
- The Next Programming Language Is English
Explore listener stats, chart rankings, contacts and more on the MLOps.community podcast page.