Agents Are Where Microservices Were in 2015 — Roberto Milev & Uday Kanagala, Navan
Navan treats production agents as stateful services needing persistence, composable skills, traces, authorization gates, and trajectory-based tests before multi-agent complexity.
Navan’s emerging stack covers runtime, memory, context, operations, and orchestration. It persists and rehydrates sessions, composes context from independently testable **skills**, and places guardrails **before and after every tool call**.
Start with one reliable agent and progressively load domain skills instead of defaulting to a multi-agent graph. Capture goals, tool calls, inferred answers, and execution trajectories so failures can become test cases and policy changes.
Navan’s emerging stack covers runtime, memory, context, operations, and orchestration. It persists and rehydrates sessions, composes context from independently testable **skills**, and places guardrails **before and after every tool call**. Start with one reliable agent and progressively load domain skills instead of defaulting to a multi-agent graph. Capture goals, tool calls, inferred answers, and execution trajectories so failures can become test cases and policy changes. Cloud runtimes and tool protocols are converging, but cost prediction, replay, agent observability, and orchestration remain unsettled. Navan’s single-master pattern reflects its use cases rather than a universal architecture.
This reinforces a single-agent-first architecture in which independently testable skills, persistent sessions, tool-boundary guardrails, and captured trajectories form the operating stack. It makes multi-agent orchestration an earned escalation rather than a default, while leaving replay, observability, and cost prediction open. The pattern is credible as Navan’s implementation choice but not established as universal.