Agents As Microservices

Agents as microservices is the architectural analogy that mature agent systems may evolve from one large general-purpose agent into smaller, specialized agents coordinated through protocols, gateways, and hardened interfaces [src-057].

Key points

  • Richardson says startups often begin with one large agent, while more mature companies tend to want smaller agents for flexibility and agility [src-057].
  • A customer analogy in the episode frames agents as the new microservices, which implies MCP servers may play a role similar to API gateways [src-057].
  • The analogy exposes a risk: many MCP servers are flexible but not yet as hardened, fortified, or governed as mature API gateways [src-057].
  • Agent discovery, permissions, payments, memory, and coordination become architecture questions once agents are no longer isolated experiments [src-057].
  • The pattern complements Enterprise Agent Governance and Model Context Protocol (MCP) because production agent fleets need identity, observability, policy checks, and reliable boundaries [src-057].

Related entities

Related concepts

Source references

  • [src-057] Amazon Web Services — “The Future of Agentic AI with Rory Richardson | AWS Humans In The Loop Podcast” (2026-05-01)

Robin Cartier perspective

This page is part of Robin Cartier's working AI knowledge graph: a practical research layer for production AI, recommendation systems, experimentation, GEO, and agentic web readiness.

The useful next step is to connect this concept back to applied product leadership and operating models.

Recommended next

Keep reading from this thread

From 477 indexed pages and articles.

  1. Wiki concept Agent-Native Infrastructure The redesign of tools, docs, services, and deployment surfaces so agents can sense, act, configure, and verify work directly instead of Related by microservices
  2. Wiki concept Agentic AI Adoption Culture The set of team norms that make agentic AI useful in practice: curiosity, experimentation, play, trust, humility Related by 057
  3. Insight Recommendation Systems in Production How recommendation systems become production decisioning systems through signals, ranking, constraints, feedback loops, and experimentation Readers have engaged with this next