Deploying AI Agents in Airgapped and Low-Latency Enterprise Systems
Nick Kuhn explains why enterprise AI agents must run on-premises, satisfy strict compliance rules, and eliminate network latency.
From AGENTS.md to Enterprise Deployment
Nick Kuhn from VMware Tanzu Platform joins Daniel Whitenack and Chris Benson to discuss the realities of deploying AI agents in enterprise environments. They explore the transition from running agents locally to production platforms using agent buildpacks, AGENTS.md specifications, Model Context Protocol (MCP) gateways, and shared memory architectures. The conversation also addresses organizational adoption hurdles, security sandboxing, and why enterprise platform engineering practices remain critical for agentic systems.
Key takeaways
- Nick Kuhn spent 14 years inside large corporate IT environments before his 5 years at VMware Tanzu, learning that assuming external internet access kills enterprise deals on day one. Read more →
- Local AI agents store context in local markdown files, but ephemeral cloud containers destroy that file system state on restart. Read more →
- Centralized Model Context Protocol (MCP) gateways manage and bind agents to specific subsets of tools, replacing unmanaged tool connections across 30 to 40 backend servers. Read more →
- Enterprise approvals often stall for six months in internal review councils; counter this delay by shipping small, approved iterations rather than monolithic overhauls. Read more →
- Running autonomous agents on a local laptop breaks the moment you close the lid; production workflows demand 24/7 runtimes with managed lifecycles. Read more →
5 articles from this episode
Cloud AI Agents Need 12-Factor Memory
Nick Kuhn explains why file-based agent memory fails in the cloud and how 12-factor decoupled state services fix ephemeral container memory.
Why AI Agents Need MCP Gateways and Identity Pass-Through
Nick Kuhn explains how MCP gateways solve agent security, identity pass-through, and rogue tool call loops in production systems.
Stop Building Isolated AI Teams: How Enterprise AI Actually Ships
Nick Kuhn explains why isolated AI squads stall in enterprise committees, and how office hours and small iterations get models into production.
Tanzu Agent Buildpacks: Deploying AGENTS.md to Production
Nick Kuhn shares how VMware Tanzu uses buildpacks and AGENTS.md to move AI agents from developer laptops to secure enterprise runtimes.
More Practical AI episodes
- Computer-Use Agents and the Future of the Agentic InternetSep 13 · 4 articles