017 - The Future of Work: Agent Orchestration

Ryan, Travis and guest Shayne Boyer from Microsoft discuss “agent orchestration,” or humans coordinating multiple specialized AI agents to complete multi-step tasks. They cite recent developments like Perplexity Computer, Google/Samsung Gemini multi-step mobile agents, Open/Claude tools, and Microsoft Copilot Tasks, and explain that routing work to the best model and giving agents tool access are key trends. The conversation stresses that despite hype, agents are brittle, often produce low-value output, and require heavy human “composer/puppet master” supervision, clear prescriptions, guardrails, evaluation, and delegation skills. They compare multi-agent setups to specialized human teams, planning/execution/eval roles, and even autopilot risks around over-trust, while noting sustainability and cost/token limits. They encourage listeners to start small and gradually delegate tasks without becoming paralyzed.00:00 Welcome and Guest Intro01:05 What Agent Orchestration Means03:18 Why Agents Are Everywhere Now04:15 Travis on Agentic Computing06:11 Shane on Jarvis Dreams08:26 When Agents Fail Hilariously09:56 Tools and Model Routing11:38 Delegation and Trust Risks14:50 How Orchestration Works18:25 Ant Farm Multi Agent Experiment21:14 Why Multi Agent Helps25:49 Baseball Team of Agents27:56 Sustainable AI Pace28:55 Empowered PR Culture30:26 Grumpy Reality Check34:57 Gardening the Agents38:46 Supervision Is the Job42:27 Managing Agent Teams44:07 Multi Agent Life45:28 Token Costs and Access47:43 Demystify the Hype50:06 Try It Step by Step51:17 Wrap Up and Thanks This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit aiunprompted.substack.com