He runs 100s of AI agents ... here’s how

<p>What does it actually look like to work with hundreds of AI agents?</p><p><br></p><p>In this episode of NEXT with John Koetsier, I chat with Steve Ancheta, founder and CEO of Zig.ai, an AI-native platform for relationship-driven sales.</p><p><br></p><p>Steve explains why what looks like a single AI agent to a user can actually be a swarm of hundreds of specialized agents working behind the scenes, handling copywriting, follow-ups, CRM updates, next-best actions, orchestration, and more.</p><p><br></p><p>We also dig into how Steve personally uses AI agents as force multipliers across his work, why he still writes important investor and customer messages himself, and why simply giving an agent access to documents isn’t enough. Steve shares his approach to building an effective agent harness, including two critical pieces many people overlook: governance and grounded truth.</p><p><br></p><p>We also discuss OpenClaw, NanoClaw, cloud-based agents, agent security, human-in-the-loop workflows, critical thinking, AI productivity, and the shift from reactive agents that wait for instructions to proactive agents that start doing useful work on their own.</p><p><br></p><p>Topics include:</p><p>- Why Steve believes many beginners shouldn’t build agents yet</p><p>- How hundreds of specialized agents can operate as one system</p><p>- AI agents as force multipliers rather than human replacements</p><p>- Why human taste and connection become more important as AI improves</p><p>- How Steve uses agents for planning, operations, scheduling, and analysis</p><p>- The dangers of AI-generated documents nobody actually reads</p><p>- Agent governance, guardrails, and permissions</p><p>- Giving agents a reliable source of truth</p><p>- Why vector databases alone aren’t a magic solution</p><p>- Balancing human interaction with AI-assisted work</p><p>- The move from reactive AI agents to proactive AI agents</p><p>- Why humans should remain in the loop for external actions</p><p><br></p><p>Guest: Steve Ancheta</p><p>Company: Zig.ai</p><p><br></p><p>00:00 Why beginners may not be ready for AI agents</p><p>00:24 Working with AI agents every day</p><p>01:34 Steve Ancheta’s journey into AI</p><p>03:00 The early days of agent workflows</p><p>04:36 OpenClaw, Hermes, and the agent boom</p><p>05:37 The security problem with early AI agents</p><p>06:00 Why Steve moved agents to the cloud</p><p>07:00 Local agents vs. cloud-based agents</p><p>08:00 How quickly agent technology is evolving</p>