The Agentic Architect with Hugo Guerrero

Architecture patterns for agentic systems people can trust.

Notes for the people building the capabilities, context, controls, and operating models behind useful AI agents.

Latest articles

View all

MCP Is a Protocol. Your Architecture Still Matters.

The Model Context Protocol standardizes how agents talk to tools. It does not decide what a good tool is, who owns it, or what it is allowed to do. Those are still architecture decisions.

KubeCon Salt Lake City: Is the Pod Still the Unit?

My takeaways from KubeCon + CloudNativeCon North America 2026: agents strain the pod model, sandboxes compete for the runtime layer, identity becomes the control point, and what Solo.io shared in Salt Lake City.

What 20 Years of API Design Taught Me About Agents

We spent two decades making APIs easy for developers to discover and consume. Agents change the consumer, and the old lessons apply in a stricter form.

Your Agent Shouldn't Need Your Laptop

Proactive agents need integrations, live events, and compute that stays reachable. A better sandbox on a Mac mini is not production. The real requirement is an agent that is always available, not always running.

A Simple Agent Request Is Actually a Distributed System

Ask an agent for the weather and ten messages cross five components. Agentic AI is not only an AI problem. It is a distributed-systems problem, and it needs distributed-systems discipline.

Five themes, one thesis

All topics

Agent quality is bounded by the architecture around the model. Each theme covers one part of it.

  1. API Foundation

    The contracts and capabilities agents inherit: API design, discoverability, and outside-in architecture.

    3 articles
  2. Context Economy

    How context is assembled, moved, and governed: MCP, tools, retrieval, and the paths data takes.

    3 articles
  3. Agentic Infrastructure

    The connectivity layer around agents: gateways, registries, servers, and the controls that govern them.

    5 articles
  4. Agentic Reliability

    Making agent behavior dependable: deterministic boundaries, state, history, and evidence.

    1 article
  5. Event-Driven Agents

    Real-time context for agents: events as products, streams as memory, and contracts for change.

    1 article